Geriatric Healthcare Supported by Decision-Making Tools Integrated into Digital Health Solutions

Abstract

The aging population requires cutting-edge approaches to geriatric care, with digital health technologies playing a crucial part in meeting the challenging demands of healthcare. Current approaches frequently fall short of the goal of providing comprehensive, real-time monitoring and merging contextually complex information for use in the treatment of patients. This paper addresses these limitations by integrating the innovative approaches within the RO-SmartAgeing system and the NeuroPredict platform to boost geriatric-care outcomes. It emphasizes the multifaceted design and development processes of these digital health solutions, emphasizing a multidisciplinary approach and a meticulous choice of decision-making tools. This paper presents the inclusion of decision-making tools, namely the Medical Blackbox and Gaitband, into the RO-SmartAgeing system and the NeuroPredict platform; these tools have been developed for the purpose of gathering complex physiological data and allow for in-depth evaluations of gait patterns and vital health parameters in elderly individuals. The present research emphasizes major breakthroughs in sensing technology and decision-making capabilities, illustrating the manner in which these tools enhance patient outcomes by providing timely, data-driven insights. The results demonstrate that these tailored decision-making tools significantly improve patient outcomes, underscoring the need for such ongoing improvements able to address digital health solutions tailored to the dynamic demands of an increasingly aging population.

1. Introduction

The global population is aging at an unprecedented rate, presenting significant challenges and opportunities for health systems around the world. The share of the global population aged 65 and over is projected to increase from 10% in 2022 to 16% in 2050. At that time, the number of people aged 65 and over worldwide is expected to be more than twice the number of children under 5 and about the same as the number of those under 15 [1]. Health systems must adapt to meet the complex and multifaceted needs of older adults.

Aging populations face increased levels of chronic diseases and geriatric syndromes and declines in physical and cognitive functions. This necessitates a shift from reactive healthcare to proactive, personalized, and preventative healthcare. Data-driven decision support is essential for geriatric assessment, utilizing data and analytical models to enhance decision-making processes. By leveraging real-time data, this approach offers healthcare providers valuable insights and accurate information. Integrated with various decision-making tools and systems, it facilitates comprehensive geriatric assessments (CGAs), significantly improving the identification of health issues, treatment planning, and overall care for elderly patients. Moreover, data-driven decision-support systems employ advanced algorithms and predictive analytics to analyze large datasets, enabling healthcare professionals to make decisions which are more informed. These tools include electronic health records, wearable health monitors, telehealth platforms, and patient management software, which collectively streamline the workflow, reduce errors, and ensure personalized care.

One key consideration, Digital Health Solutions (DHS), represents a wide spectrum of technologies which can be organized into categories such as applications, devices, and systems. Each of these categories plays a pivotal role in advancing healthcare, particularly in the management of the care of elderly persons. Applications typically provide user-friendly platforms for patients and healthcare providers, facilitating continuous monitoring and real-time health management. Conversely, devices are designed to collect and analyze specific health metrics, supplying crucial data to support decision-making. Systems, in turn, integrate these applications and devices into cohesive frameworks, promoting a more comprehensive and holistic approach to patient care.

This study focuses specifically on the systems aspect of DHS, examining how these integrated solutions can enhance the quality of care for elderly patients. The paper presents the integration of decision-making tools, such as the Medical Blackbox and Gaitband, into the RO-SmartAgeing system and the NeuroPredict platform.

1.1. Comprehensive Geriatric Assessment Boosted by Personalized Digital Health Solutions

Geriatric assessments optimize the health and treatment of older adults by assessing their overall health and care needs. Comprehensive assessments, including social and psychological factors, provide holistic care. Older adults often report greater emotional well-being due to enhanced emotional regulation and a focus on positive experiences, a trend explained by socioemotional-selectivity theory. This positive bias in health care leads to greater satisfaction but may lead to underestimation of negative health information. Providers should frame information positively but realistically in order to improve patient relationships and ensure balanced communication [2].

Psychological empowerment in older adults includes feelings of control, competence, and self-determination in managing their health. This fosters confidence in influencing health outcomes and motivates active healthcare participation. Empowered individuals better understand medical information and engage with providers. Research shows they prefer active involvement in healthcare decisions, with health literacy mediating this relationship by turning motivation into action. Empowerment motivates, while health literacy provides the necessary skills. [3].

High-quality social support networks also play a crucial role. They offer emotional, practical, and informational assistance, enhancing psychological well-being and encouraging active engagement in healthcare. Public health initiatives should focus on strengthening these support networks in order to boost empowerment and healthcare engagement in older adults [3,4,5].

CGAs help in diagnosing medical conditions, planning treatments, managing care, and evaluating long-term care needs. They include the assessments of physical health, cognition, mental health, and socioenvironmental circumstances [2,6]. Unlike standard medical assessments, this approach focuses on functional capacity and quality of life, often involving a multidisciplinary team. This approach provides a deeper understanding of the patient’s medical, functional, and psychosocial problems. Functional ability is evaluated through activities of daily living (ADL) and instrumental activities of daily living (IADL), using tools like the Katz ADL Scale and Lawton IADL Scale [2,7].

In busy clinical settings, geriatric assessments are often focused on specific problems, but for patients with multiple problems, a “rolled” assessment with multiple visits is recommended [8]. These assessments help identify hidden problems and ensure that medical conditions are accurately diagnosed, that treatment plans are effectively created, and that long-term care needs are determined. By focusing on positive outcomes and aligning decisions with patient values, healthcare providers can enhance patient satisfaction and overall well-being by addressing the unique health challenges older adults face [2,7].

Screening for conditions such as diabetes, hypertension, and glaucoma, along with conducting nutritional assessments, is crucial for older adults to prevent future morbidity [9,10]. Particular attention is paid to the prevention of falls, osteoporosis, polypharmacy, depression, and dementia, using validated tools such as the ”Tinetti Balance and Gait Assessment” and the ”Geriatric Depression Scale” [11].

Evaluating socio-environmental factors, like living conditions and social support, provides a complete view of the patient’s health, enabling the creation of personalized care plans. This thorough assessment is key to diagnosing conditions, developing treatment plans, coordinating care, and determining long-term care needs [8].

Geriatricians recognize the importance of digital technologies in supporting geriatric healthcare, and have integrated digital solutions in geriatric assessment which can significantly improve care for older adults by enhancing accuracy, promoting active aging, and enabling timely interventions [8]. However, addressing challenges such as digital literacy, usability, and the need for comprehensive training for healthcare providers is crucial for successful implementation. Geriatric specialists highlight the need for tailored solutions to address the medical, social, and functional challenges faced by older adults [12]. Physical and cognitive declines, social isolation, and economic instability all impact well-being and quality of life. Developing products that support autonomy and independent living, while involving older adults in the design process, is essential [13].

DHS significantly improve healthcare for aging populations by improving access, monitoring, and self-care. Their success is based on their patient-centered design, interdisciplinary collaboration, and overcoming barriers to adoption. Geriatricians support customized DHS tailored to the specific needs of older adults, which benefits both patients and healthcare professionals [14].

Personalized DHS provides elderly patients with customized health information and recommendations, encouraging empowerment and active participation. These systems monitor vital signs and mobility changes based on individual needs and provide real-time feedback for timely health plan adjustments.

Efficient allocation of resources is another advantage, as tailored DHS focuses on the most pertinent monitoring parameters for each patient, allowing healthcare professionals to optimize their time and efforts. The abundance of personalized data supports data-driven decision-making, enabling proactive healthcare strategies and timely interventions based on the evolving health status of elderly patients.

The traditional generic approach has become inadequate in managing the health complexities associated with aging populations, as it often overlooks individual variations and multifaceted health evolutions. This necessitates tailored DHS that prioritize patient-centric care.

For patients, customized DHS offer several significant advantages. These solutions provide personalized health insights and recommendations, which are more aligned with the unique health profiles of each individual. This customization fosters greater patient engagement and active participation in their own healthcare journey [15]. Additionally, DHS can be adapted to monitor the specific health parameters that are most relevant to each elderly patient, ensuring that the care provided is both meaningful and effective.

Moreover, tailored DHS enhance patient engagement through real-time feedback and interactive features, offering immediate guidance and support. This real-time interaction not only strengthens the connection between the patient and the monitoring system but also improves the overall effectiveness of disease management by facilitating timely adjustments to health plans [16]. Personalization also plays a crucial role in improving adherence to health recommendations. By aligning monitoring routines and interventions with the patient’s lifestyle and preferences, DHS reduce the perceived burden of monitoring, making it easier for elderly patients to follow prescribed plans [17].

Importantly, DHS that integrate seamlessly into patients’ daily lives become supportive companions in managing health, rather than additional burdens [18]. This integration ensures that monitoring activities and interventions fit naturally into the patient’s routine, thereby enhancing the effectiveness of disease management and improving the overall quality of life.

For healthcare professionals, tailored DHS provide the precision needed in disease management. These solutions offer detailed and relevant data for targeted interventions, allowing health professionals to focus on the specific aspects of a patient’s health that require attention [19]. This targeted approach enhances the precision of interventions and treatment plans, optimizing the use of healthcare resources and minimizing unnecessary procedures. In addition to targeted interventions, personalized DHS contribute to diagnostics which are more accurate by adapting to the unique characteristics of each patient. This customization aids in identifying patterns, trends, and potential risk factors associated with aging-related health challenges. Furthermore, tailored DHS streamline communication between elderly patients and healthcare providers by providing a shared platform for discussions [20]. The personalized data generated by these systems serve as a foundation for informed and meaningful interactions, enabling healthcare professionals to better understand their patients’ experiences and tailor their guidance accordingly [21].

Integrating decision-making tools into DHS for geriatric care faces several challenges. Key issues include the seamless integration of health data for real-time interventions, designing tools tailored to older adults, and ensuring accessibility and usability [22,23]. Many tools lack user-friendly designs and fail to present data in an easily understandable format, limiting patient engagement [24,25]. Data security, digital literacy, and the complexity of integrating these tools into clinical workflows add further barriers, highlighting the need for continuous professional training and better regulatory frameworks [26,27].

The importance of DHS in this research lies in its ability to transform traditional healthcare approaches by providing tools that improve patient engagement and adherence and optimize healthcare delivery. Using technologies such as the RO-SmartAgeing system and the NeuroPredict platform, the research demonstrates how DHS can integrate different health metrics into a cohesive system that provides predictive analytics and real-time decision support. This integration is crucial to addressing the aging population’s complex and multifaceted health challenges.

1.2. RO-SmartAgeing System and NeuroPredict Platform—Innovative Digital Health Solutions for Enhancing Geriatric Care

Aging populations present huge issues for global healthcare systems, with a rising number of older people needing ongoing care for chronic diseases including Alzheimer’s disease (AD) and Parkinson’s disease (PD). These disorders significantly decrease the quality of life for the people diagnosed and place substantial budgetary pressures on healthcare systems as a result of the continual requirement for specialized treatment and constant monitoring. Traditional healthcare models are frequently unable to manage chronic illnesses and provide tailored medical care, resulting in excessive expenditures and a lower quality of life for patients. Current approaches usually do not have real-time monitoring capabilities and fail to include advanced decision-making tools that are able to generate relevant data informing prompt actions. The RO-SmartAgeing system and the NeuroPredict platform fill these key gaps by providing sophisticated digital health solutions that improve both the quality and the outcomes of care. The RO-SmartAgeing system enhances geriatric care by combining comprehensive health monitoring and real-time data management, allowing for customized care and lowering hospitalization rates through proactive actions. Likewise, the NeuroPredict platform expands on these capabilities to meet the particular requirements of patients suffering from neurodegenerative disorders, including the provision of customized tools for remote monitoring, cognitive tests, and early diagnosis of disease progression. By addressing these gaps, these digital solutions help to promote a more viable, data-driven approach to managing aging and mental health conditions, eventually boosting patient outcomes and lowering healthcare costs.

The RO-SmartAgeing system was created with the explicit goal of improving geriatric care by offering a complete health monitoring solution adapted to the special demands of the aged population. This system includes important capabilities that are important for medical service providers, notably comprehensive patient data management, individualized adaption of the smart environment based on medical features and lifestyle, and secure multi-user authentication, as well as advanced decision-making tools designed to significantly enhance geriatric-care outcomes [28].

The RO-SmartAgeing system is built on advanced decision-making tools, including the Medical Blackbox, Ambiental Blackbox, and Gaitband. These devices are specifically designed to collect and evaluate complex physiological data, allowing for in-depth assessments of important health parameters and gait patterns in the elderly. These features provide healthcare professionals with relevant information that promotes customized care and allows for the prompt measures that are essential to enhancing patient outcomes in geriatric care [29]. The system enables healthcare practitioners to make informed clinical decisions, improve interventions, and react rapidly to possible health risks, thereby addressing the challenges provided by the expanding older population.

In clinical settings, the RO-SmartAgeing system improves the monitoring capacities of institutionalized seniors through the integration of physiological data monitoring, the monitoring of adherence to therapy, and safety measures, including location tracking. These aspects improve the efficacy and reactivity of healthcare delivery models, and this is becoming more and more essential as the need for individualized reliable healthcare solutions for the elderly grows. The system’s capacity to monitor and manage diseases proactively corresponds with the current move toward data-driven and patient-centered healthcare, highlighting its potential influence on geriatric care.

The NeuroPredict platform represents a sophisticated extension of the RO-SmartAgeing system, one specifically tailored to address the complex healthcare needs associated with neurodegenerative diseases prevalent among aging populations. Built upon the foundational capabilities of the RO-SmartAgeing system, NeuroPredict integrates advanced functionalities essential for managing conditions such as Parkinson’s Disease (PD), Alzheimer’s disease (AD) [30], and Multiple Sclerosis (MS). These functionalities include robust data management capabilities, adaptive smart environment customization based on medical specifics and lifestyle, secure multi-user authentication features, and specialized decision-making services.

Central to the NeuroPredict platform are its advanced decision-making tools, including the improved Medical Blackbox, as well as the Ambiental Blackbox and Gaitband. These tools are meticulously engineered to capture and analyze complex neurological and physiological data essential for assessing cognitive functions, behavioral patterns, and neurological responses in patients with neurodegenerative conditions. By leveraging these tools, the NeuroPredict platform empowers healthcare providers with actionable insights in order to make informed clinical decisions, personalize treatment strategies, and intervene proactively as needed, thereby improving patient outcomes, and enhancing overall quality of life.

The NeuroPredict platform offers significant advantages to individuals managing these neurodegenerative diseases through remote health monitoring [31]. It enhances healthcare efficiency by enabling timely interventions and providing personalized support tailored to each patient’s specific needs.

In clinical environments, the NeuroPredict platform can ensure precise monitoring and management of patients with PD, AD, and MS using advanced sensor technologies, real-time cognitive assessments, and safety features like fall detection and emergency-response systems. This comprehensive approach supports a more responsive and personalized model of care, aligning with the evolving needs of aging populations affected by neurological disorders [32].

The RO-SmartAgeing system aims to enhance geriatric healthcare by offering comprehensive and personalized health monitoring tailored specifically to elderly patients. This advanced system integrates robust data management, adaptable living environments, secure multi-user access, and sophisticated decision-making tools [33].

From a societal perspective, the RO-SmartAgeing system promotes a sustainable and patient-centric healthcare model [34]. It reduces both financial and human resource consumption while advancing accessible, individualized care for the elderly. This aligns with the modern shift towards data-driven and patient-centered healthcare, demonstrating the transformative potential of DHS in geriatrics.

The NeuroPredict platform extends the capabilities of the RO-SmartAgeing system in order to address neurodegenerative diseases like PD and AD. It employs advanced decision-making tools to monitor cognitive and physiological health, providing healthcare providers with valuable insights for personalized treatment strategies and timely interventions. This approach enhances care for patients with neurodegenerative conditions, promoting better health outcomes and quality of life.

Both the RO-SmartAgeing system and the NeuroPredict platform exemplify significant advancements in geriatric care. They focus on delivering personalized, preventive, and efficient healthcare solutions that cater to the unique needs of elderly patients and those with neurodegenerative diseases, ultimately improving their quality of life and fostering a more sustainable healthcare system.

2. Literature Review

The global aging trend requires innovative care solutions using smart technology to support healthy aging worldwide. Geriatric specialists have explored the use of DHS to enhance the quality of life and provide better healthcare outcomes for older adults.

2.1. Leveraging Digital Health Solutions for the Care of the Elderly

Digital health technologies, including telehealth platforms, mobile health applications, and wearable devices, significantly improve healthcare access for older adults and enhance CGA capacity by increasing data availability and utilization for healthcare decisions [24,35]. By adopting these technologies, healthcare providers can better address the unique needs of aging individuals, ensuring that care is more effective and personalized [14,36]. Additionally, these tools enable continuous monitoring, early detection of health issues, and better communication between patients and healthcare providers, ultimately enhancing the quality of life and autonomy of older adults [24,35]. Geriatricians highlight the benefits of personalized digital coaching for the promotion of health literacy, physical activity, cognitive training, emotional well-being, and social connection. These interventions facilitate better communication between patients and healthcare providers and support subjective well-being [37].

Innovations in digital health, such as intelligent sensors and Internet of Things (IoT) systems, support an active lifestyle, enhance sensory experiences, promote social interaction, and deliver continuous remote monitoring [38,39,40]. Wearable devices such as smartwatches and fitness trackers are frequently used to monitor vital signs like heart rate and blood pressure, as well as physical activities, including steps taken and sleep patterns [41]. This ongoing data collection enables healthcare providers to remotely oversee patients’ health and promptly intervene when necessary [40,42,43]. Additionally, smart devices play a crucial role in preventing social isolation by providing accessible ways for elderly individuals to stay connected and engaged with their communities, which is vital for their mental and emotional well-being. IoT systems facilitate interaction through various activities and communication tools, ensuring that the elderly maintain meaningful relationships and participate in social activities crucial for their overall quality of life [43].

Highlighted in [44] is the implementation of IoT systems, which includes the use of smart sensors for continuous remote surveillance and support. These systems aim to enhance the quality of life (QoL) and independence of elderly individuals. The specific technologies mentioned encompass augmented reality-based intelligent glasses for those with mild cognitive loss, fuzzy-inferential adaptable neural networks for analyzing camera and speech data, and the Quida platform for unobtrusive daily routine tracking.

Designing DHS with the specific needs and preferences of older adults in mind is crucial for their successful implementation and widespread acceptance [13,42,45]. Many studies highlighted the critical importance of addressing the needs of the elderly through modern healthcare and technological advancements [12,13,44].

During the COVID-19 pandemic, when older people faced significant challenges, including increased vulnerability to severe illness, social isolation, and difficulty accessing healthcare, the development and implementation of digital health systems became increasingly important [46]. For instance, remote patient monitoring systems can detect early signs of health deterioration, allowing for timely medical intervention and potentially preventing hospitalizations. These technologies also empower older adults to manage their health independently, enhancing their sense of control and improving their quality of life [40].

The systematic study conducted by Paiva et al. (2020) [47] reveals that most mobile applications for healthcare for the elderly are designed for independent users. Independent elderly individuals are those who can use these applications without the need for assistance from caregivers or family members. This focus stems from the need to promote autonomy and self-management of health among elderly individuals, thereby enhancing their quality of life.

The vINCI system integrates various devices to monitor the health and well-being of older adults, enhancing assisted living through an intelligent environment. Key devices include smart insoles, depth cameras, smartwatches, and a mobile application. These devices offer continuous, real-time monitoring of health parameters, enabling proactive management and early detection of issues. By integrating data from multiple sources, healthcare professionals can develop personalized treatment plans and reduce the need for frequent hospital visits. Safety features and patient-engagement tools promote adherence to treatment plans and healthy behaviors, providing a comprehensive approach to improving the well-being of older adults [40,48].

A comprehensive digital health solution that aims to improve patient outcomes, support clinical decision-making, and reduce healthcare costs through early detection and proactive management is presented in the paper by Papachristou et al. (2023) [49]. The LifeChamps digital platform integrates several devices to monitor the health of older cancer patients. The Artificial Intelligence (AI) and big-data analytics engine processes multimodal data to enable predictive modeling, while the IoT edge device ensures seamless data collection and transmission. These technologies collectively support continuous health monitoring, functional assessment, and data integration. They enable predictive modeling and personalized care, enhancing clinical decision-making and improving outcomes for older cancer patients [49].

The study described in [50] aimed to assess whether digital home monitoring combined with centralized specialist support could optimize medical therapy and improve the quality of life in patients with chronic heart failure more effectively than digital home monitoring alone. The findings suggest that while enhanced patient monitoring with specialist support is feasible, it may not significantly improve outcomes beyond levels achieved through standard digital home monitoring. This underscores the need for further research to identify which elements of remote monitoring and management can truly enhance patient care and outcomes.

In recent years, the metaverse has emerged as a new frontier in healthcare, offering a virtual environment where elderly patients can access healthcare information and engage in educational activities related to their health conditions. This immersive experience, powered by virtual reality and augmented reality, significantly enhances their decision-making capabilities. By providing strategies and educational information tailored to their needs, the metaverse aims to improve healthcare delivery for the elderly, transforming how they interact with their health [51].

A system comprising mobile applications and wearable devices that monitor health data to provide real-time feedback and support individualized care plans for elderly myocardial-infarction patients is presented in the ValueCare project. A key feature of this approach is continuous interaction with a virtual coach, which improves decision-making and ensures efficient management of care plans. The study assesses the impacts of these digital tools on the improvement of health outcomes and care management for elderly patients [52].

In the realm of integrated care, the combination of the IoT and big-data analytics has proven to be transformative. IoT devices collect comprehensive health data, which are then analyzed using big-data techniques to identify patterns and inform healthcare decisions. This integration not only helps in creating personalized care plans but also focuses on preventing accidents and maintaining the quality of life among elderly individuals [53]. Similarly, the blockchain–edge framework integrates edge computing and blockchain technology to offer reliable, low-latency digital healthcare applications. This combination enhances security and trust in remote monitoring systems, making real-time data processing and secure data management possible. As a result, decision-making for remote health monitoring becomes more reliable and timely, ensuring that elderly patients promptly receive the care they need [54]. Agile Dwelling Units represent another innovative approach, integrating Information and Communication Technologies (ICT) to provide personalized, sustainable solutions for independent living. These units adapt to the needs of older adults throughout the lifespan of the patient, using various ICT tools to support health monitoring and management. This personalized and adaptive decision-making process ensures that care of elderly patients is both effective and responsive to individual needs [55]. The TeNDER project emphasizes a person-centered approach in the development of new health-technology systems. By focusing on personalization and using user feedback, the project ensures that health technologies meet the unique needs of different aging populations. This approach not only enhances usability and satisfaction but also ensures that decision-making processes are tailored to individual requirements, improving overall care quality [17]. Lastly, the integration of AI and wearable IoT devices in intelligent healthcare systems offers comprehensive monitoring and management of health. These technologies reduce the burdens on families and promote health in long-term care environments. By supporting continuous health monitoring and providing predictive insights, AI and wearable IoT devices enhance decision-making, ensuring that elderly individuals receive the care they need in a timely and efficient manner [56].

Table 1. Comparisons between the RO-SmartAgeing system, the NeuroPredict platform, and other applications/systems.

Application/System	Key Attributes	Disadvantages/Shortcomings	Advantages of Brought by RO-SmartAgeing System and NeuroPredict Platform
Telehealth Platforms [24,35]	Enhance healthcare access, support continuous monitoring, and improve CGAs by enhancing data availability.	Lack of integration with advanced decision-making tools, limited data analysis capabilities.	Offer more comprehensive real-time monitoring and advanced decision-making tools.
Mobile Health Applications [47]	Support continuous monitoring, enable early detection of health issues, and improve communication between patients and providers.	Often limited in scope, focusing on specific health metrics without integration into broader healthcare systems.	Provide a more holistic approach, integrating various health metrics and offering predictive analytics.
Wearable Devices [52]	Monitor vital signs and physical activities and enable remote health oversight.	Limited to specific functions (e.g., heart rate and steps), may not provide comprehensive health insights.	Integrate data from wearables into a larger system that supports complex decision-making.
IoT Systems [44]	Support active lifestyles, enhance sensory experiences, promote social interaction, and deliver continuous remote monitoring.	Potentially complex to manage, may not offer real-time predictive analytics.	Streamline data from IoT devices into actionable insights for proactive healthcare management.
vINCI System [40,48]	Integrates devices like smart insoles, depth cameras, smartwatches, and a mobile application for continuous monitoring and early detection.	Might lack integration with broader healthcare systems and advanced predictive analytics.	Offer a more integrated approach with advanced analytics and real-time decision-making capabilities.
LifeChamps Digital Platform [49]	Integrates AI and big-data analytics for predictive modeling and supports continuous health monitoring and functional assessment for older cancer patients.	Focuses on a specific patient group (older cancer patients), which may limit broader applicability.	Are designed to cater to a wider range of geriatric and neurodegenerative conditions with broader system integration.
Metaverse [51]	Provides a virtual environment for elderly patients to access healthcare information and engage in educational activities.	Primarily educational, may not offer direct health monitoring or real-time data integration.	Focus on real-time health monitoring and data-driven decision-making rather than purely educational experiences.
Agile Dwelling Units (AgDUs) [55]	Integrate ICTs to provide personalized, sustainable solutions for independent living, adapting to older adults’ needs throughout the patient’s lifespan.	May lack advanced health monitoring and decision-making capabilities.	Integrate environmental monitoring with health data analysis for comprehensive management of the care of elderly patients.

presents a concise summary of the previously mentioned applications, highlighting their key attributes and identifying their respective disadvantages or shortcomings, as well as highlighting how they differ from the RO-SmartAgeing system and the NeuroPredict platform.

By leveraging digital health technologies, healthcare systems can better address the needs of aging populations, ultimately improving health outcomes and the quality of life for older adults. The addressing of issues related to usability, trust, and technological barriers is essential to maximize their adoption and effectiveness.

2.2. Opportunities Brought by Decision-Making Tools for Geriatric Care

Digital health technologies, particularly decision-making tools, are emerging as pivotal components in the enhancement of geriatric care. These tools enhance the accuracy of geriatric assessments by utilizing real-time data, enabling early identification of health issues and interventions which are more effective [57].

One of the most significant advantages of digital health technologies is their ability to provide continuous monitoring of patients’ health status. Wearable devices and IoT sensors collect real-time data on vital signs, activity levels, and environmental conditions. This comprehensive data collection allows for early detection of potential health issues, enabling timely interventions. For older adults, who often have multiple chronic conditions, regular monitoring is crucial for effective management and maintaining overall health. Personalized healthcare for the elderly has also improved with decision-support algorithms that assign tailored ICT devices and services based on individual health and social needs, as highlighted by Brunzini et al. (2023) [58].

By using AI and machine learning, decision-making tools significantly enhance patient outcomes. These tools aid in the prevention, diagnosis, and treatment of diseases, and support clinical decision-making and patient monitoring. As a result, they improve the management of chronic conditions and overall health outcomes [59,60].

The use of digital health technologies in the administration of CGAs in long-term care settings has shown promise. According to Molinari-Ulate et al. (2023), these technologies can significantly improve communication and data transfer between patients and healthcare providers, leading to better-informed decision-making and improved patient care plans [24].

In geriatric psychiatry, decision-making tools offer new opportunities for diagnosis and clinical care. Depp et al. (2019) emphasized the potential of these technologies to improve patient engagement and enable continuous monitoring, ultimately enhancing the quality of care and patient outcomes [23].

Tools like InvolveMe, designed to improve patient–provider communication in chronic healthcare settings, are also making a difference. Seljelid et al. (2020) demonstrated that such tools could facilitate better reporting of symptoms and communication of preferences, thereby promoting shared decision-making and potentially improving patient outcomes [61].

In addition, clinical decision-making tools in long-term care facilities have shown promise for improving the quality of care. As noted by Lapp et al. (2022), these tools can help manage various conditions, such as medication management, pressure-ulcer prevention, and dementia care [60].

2.3. Challenges in Decision-Making Tools for Geriatric Care

Despite substantial developments in digital health technology for geriatric care, some research gaps remain unaddressed. While various studies have shown the benefits of continuous monitoring and real-time data collecting, there has been little research on how to successfully incorporate these technologies into current healthcare systems without imposing new demands on healthcare providers. Furthermore, the long-term impact of these technologies on patient outcomes, especially among diverse and underprivileged communities, has not been fully investigated. An additional significant gap exists in the personalization of DHS. Though existing tools provide some customization, there is inadequate proof that these systems can be adapted according to the changing needs of older patients as they age, particularly in the cases of patients with intricate, co-morbid diseases. There is an inadequate amount of reliable data on the cost-effectiveness of adopting such technologies at scale, an assessment which is critical for widespread adoption. While AI algorithms demonstrate potential for the improvement of decision-making, further study is required to evaluate these tools in real-world clinical environments, notably in terms of confidence, ethical issues, and the risk of bias in decision-support algorithms. The use of new technologies, such as the metaverse and blockchain, in geriatric care is still in its beginning stages and further research is needed in order to properly appreciate their potential advantages and limits.

The RO-SmartAgeing system and the NeuroPredict platform are designed to directly address several of these identified research gaps. These DHS are especially designed to integrate easily into existing healthcare systems. They alleviate the pressure on healthcare professionals by providing enhanced decision-making tools and real-time predictive analytics, speeding the process of the integration of digital health solutions into regular healthcare while not overloading personnel. Both of these DHS emphasize a significant level of customization, using AI and machine learning to adapt to the distinctive needs of older patients over time. This capacity guarantees that medical strategies are accurate and efficient regardless of how patients’ health conditions change. The emphasis on multifaceted data integration across several health parameters enables a more comprehensive approach, addressing the gap in personalized healthcare solutions for complex comorbidities. In regard to cost-effectiveness and scalability, the designs of these DHS encompass flexible and scalable components, rendering them appropriate for widespread implementation in multiple healthcare settings. This versatility is critical for fostering wider acceptance and guaranteeing that these technologies can be successfully implemented in various communities, including underprivileged ones. These DHS are based on advanced AI algorithms with an emphasis on openness and ethical considerations, seeking to minimize inefficiencies in decision-support approaches. The decision-making tools and technologies addressed in this research, i.e., the RO-SmartAgeing system and the NeuroPredict platform, have been developed by our research team, a group which comprises the authors of this paper. This indicates that the approaches and innovations presented are directly informed by our significant competence and active involvement in the field.

3. Materials and Methods

Following the initial design and development of the RO-SmartAgeing system, the authors of this paper, together with the broader development team, continued to develop the NeuroPredict platform (which is currently in progress). This chapter is geared toward improving the RO-SmartAgeing system’s capabilities by providing advanced predictive analytics and personalized decision-making tools for managing neurodegenerative conditions. The NeuroPredict platform encompasses and improves upon the RO-SmartAgeing system’s present functionalities, boosting its usage from geriatric care broadly to the management of specific neurodegenerative diseases.

Each decision-making tool was chosen based on its ability to convey unambiguous and relevant information. The Medical Blackbox provides the vital health parameters which are required to identify acute health issues, thus enabling timely decision-making. The Gaitband gives insights on gait and posture, which are essential when assessing fall risk and impaired mobility and implementing preventive measures. The Ambient Blackbox monitors ambient factors that impact health, which is needed for making decisions regarding living arrangements or treatments.

The RO-SmartAgeing system is at the forefront of a mix of advanced technologies configured for meeting the complex demands of geriatric care. This system was designed and developed using a methodical approach, with the goal of building an integrated system that incorporates decision-making tools to improve geriatric care. Several key phases and interdisciplinary collaborations took place during the development process to ensure the system’s efficacy and flexibility.

During the conceptualization and requirements-analysis phase, the distinctive requirements of geriatric patients were identified, as well as the objectives of the RO-SmartAgeing system. Key stakeholders, such as healthcare professionals, geriatric specialists, and technology experts, were approached to determine the expanded requirements. The work of this phase made sure that the system would include key elements of elderly care, such as ongoing health monitoring, fall detection, and environmental assessment.

The design and prototyping phase involved the creation of the system’s architecture with a focus on integrating multiple decision-making tools. The design prioritized adaptability and scalability to meet changing technology breakthroughs and user demands. The RO-SmartAgeing system integrates a variety of decision-making tools to improve geriatric care. Among these, the Medical Blackbox, Gaitband, and Ambient Blackbox stand out as distinctive, specially developed, and thoroughly implemented components. Prototypes of these devices were developed for the purpose of assessing the design principles and capabilities; they were iteratively tested and improved in response to feedback from users and performance assessments.

Throughout the development and integration phase, the system’s hardware and software components were diligently set up and configured. Particular care was taken to ensure device compatibility and the easy integration of data flows into the RO-SmartAgeing system. This phase involved thorough testing to guarantee that the gathered data were accurate and reliable.

Though the system has been thoroughly assessed in confined laboratory circumstances, clinical trials will begin once all necessary regulatory procedures have been completed. Periodic enhancements and system maintenance will be carried out to include user feedback and adapt to changes in the technology, ensuring that the system serves as a reliable modern geriatric-care solution.

The design and implementation of the three original devices—the Medical Blackbox, Gaitband, and Ambient Blackbox—were important for the development of both the RO-SmartAgeing system and the NeuroPredict platform. Our research team, comprising the authors of this publication, has been creating the decision-making tools and technologies presented in this paper, which makes certain that the provided outcomes are based on our solid backgrounds in the DHS domain. These new devices highlight the paramount significance of decision-making tools in the development of geriatric care. Their implementation illustrates the groundbreaking power of merging real-time data gathering with advanced analytics to support informed decision-making and tailored health protocols in geriatric and neurodegenerative circumstances.

3.1. Design and Development of Genuine Decision-Making Tools within the RO-SmartAgeing System

The Medical Blackbox, Gaitband, and Ambient Blackbox have been carefully chosen to improve informed decision-making in geriatric and neurodegenerative care. The rationale for their selection is based on their ability to boost decision-making (through presentation of comprehensive data, which ensures that decision-makers are privy to a broad understanding of both physiological and environmental parameters), support real-time decision-making (through their potential to provide real-time data and insights), and address complex healthcare challenges (through a multidimensionality that enables an in-depth comprehension of diseases and their influencing variables).

The Medical Blackbox is an essential component of the RO-SmartAgeing system, precisely developed around the intricate requirements of geriatric health monitoring. Its design comprises independent, low-cost, Arduino-compatible sensors, leading to a tailored solution for continuous health evaluation.

The Medical Blackbox is run on an Arduino Mega board which manages the data collection and processing. This board was chosen for its effective processing capabilities and its interoperability with a variety of sensors. The device’s main microcontroller unit (MCU) enables accurate data handling and low power consumption, which is particularly important for long-term monitoring. A rechargeable lithium-ion battery provides power, and a complex power management system ensures peak efficiency over long periods of time. A Wi-Fi module facilitates connectivity and allows for easy data transmission to the RO-SmartAgeing system. The adoption of these communication protocols guarantees that updates are trustworthy and in real time, as well as that the unit will integrate seamlessly with the entire health-monitoring system.

A key part of the Medical Blackbox is its array of sensors, each intended for their specific purpose in monitoring vital health parameters (

Table 2. Main characteristic of the sensors encompassed in the Medical Blackbox.

Sensor Type	Function	Key Specification	Technical Details
Alcohol Gas Sensor (MQ-2) [62]	Measures alcohol concentration in breath	Detection range: 10–1000 ppm ethanol; Operating voltage: 5 V; Response time: Typically within 10 s	Measurement principle: Uses a semiconductor sensor that changes resistance in the presence of ethanol; Components: MQ-2 sensor element, heater, and sensitive layer; Sensitivity: Detects various gases, including alcohol, methane, and propane
EKG Sensor (AD8232) [63]	Monitors electrical activity of the heart	Signal output: Analog; Operating voltage: 3.3 V to 5 V; Bandwidth: 0.5 to 40 Hz; Noise rejection: High	Measurement principle: Extracts and amplifies the small electrical signals generated by the heart; Components: AD8232 IC, electrodes, amplification circuit; Signal conditioning: Includes filtering for noise and motion artifact removal
Pulse Oximeter Sensor (MAX30102) [64]	Measures blood oxygen saturation and heart rate	SpO2 range: 70–100%; Heart rate range: 30–240 bpm; Operating voltage: 1.8 V to 3.3 V; Data rate: Up to 1 kHz	Measurement principle: Photoplethysmography uses LEDs to emit light and photodetectors to measure the absorption of light by blood; Components: Internal LEDs (red and infrared), photodetectors, low-noise electronics; Ambient light rejection: Designed to minimize interference from external light sources
Temperature Sensor (DS18B20) [65]	Measures ambient temperature (inside the Medical Blackbox)	Temperature range: −55 °C to +125 °C; Accuracy: ±0.5 °C (from −10 °C to +85 °C); Operating voltage: 3.0 V to 5.5 V	Measurement principle: Uses a digital sensor to provide temperature readings; Components: DS18B20 sensor chip, one-wire digital interface; Resolution: Programmable 9- to 12-bit precision
Color Detection Sensor (TCS230) [66]	Detects changes in color on urine test strips to analyze biochemical parameters	Detection range: Full-spectrum color detection; Operating voltage: 2.7 V to 5.5 V; Output: Frequency proportional to the color intensity	Measurement principle: Uses an array of photodiodes and filters to detect RGB color values, converting them to a frequency signal; Components: TCS230 sensor element, RGB LEDs, photodiodes, and an internal oscillator; Application: Suitable for monitoring biochemical parameters in urine via colorimetric analyses on test strips

).

The combined use of these sensors (Figure 1) using the Arduino Mega board enables extensive data gathering. Signal conditioning, such as filtering and amplification, is applied to the raw data collected in order to improve signal quality while decreasing noise. The MCU provides real-time processing, using embedded algorithms to assess the data from sensors and identify abnormalities, allowing for prompt alerts and actions. The transmission of data from the Medical Blackbox to the RO-SmartAgeing system is made possible via a NodeMCU ESP8266 module which enables a wireless network connection. The module sends the data to a Raspberry Pi 4 Model B, which serves as the gateway device. The Raspberry Pi receives data from the NodeMCU and sends it to the cloud for additional processing and visualization. The communication protocol used is the Inter-Integrated Circuit (I2C) serial bus interface protocol, which is acknowledged for its straightforwardness and reliability when combined with Arduino boards, requiring just two wires to transfer data.

The Medical Blackbox includes an LCD monitor and a keypad to facilitate user interaction. The Arduino IDE-programmed LCD displays the device’s measured parameters. Users can choose the health parameters they want to be measured using the keypad, and after a 10 s delay, the LCD displays the most recent measurement. The measured data can also be visualized using the appropriate functionalities of the RO-SmartAgeing system.

The design of the Medical Blackbox fosters user-friendliness and reliability. The compact shape reduces possible issues associated with the performance of daily tasks while providing health monitoring. The device was developed to withstand regular use and environmental factors, maintaining its accurate performance in a variety of scenarios.

The Gaitband device is an original component of the RO-SmartAgeing system, meant solely to track and monitor the position, movement, and posture of seniors. This smart device is intended to be positioned at chest level (although it can also be placed around the ankle) and uses current sensor technology to identify movements, as well as possible falls, allowing for continuous and accurate monitoring.

The Gaitband comprises several different sensors, including a 6-axis accelerometer, and a gyroscope (

Table 3. Main characteristics of the sensors encompassed within the Gaitband.

Sensor Type	Function	Key Specification	Technical Details
Accelerometer (LSM303D, 6-axis) [68]	Measures acceleration and orientation	Measurement range: ±2 g, ±4 g, ±8 g, ±16 g; Operating voltage: 2.5 V to 3.6 V; Interface: I2C	Measurement principle: Detects acceleration in three axes and magnetic fields in two axes; Components: Micro-electro-mechanical systems accelerometer and magnetometer; Sensitivity: High precision for motion and orientation tracking
Gyroscope (LSM303D, 6-axis) [68]	Measures angular velocity and rotational movement	Measurement range: ±250°/s to ±2000°/s (combined with accelerometer); Operating voltage: 2.5 V to 3.6 V; Interface: I2C	Measurement principle: Detects rotational changes around three axes; Components: Integrated with the accelerometer in the LSM303D; Sensitivity: Precision in rotational motion detection
Wi-Fi Module (Espressif NodeMCU 8266) [69]	Facilitates wireless data transmission	Operating voltage: 3.3 V; Interface: I2C, UART; Data rate: Up to 80 Mbps	Measurement principle: Provides wireless connectivity for data transfer to the cloud; Components: Wi-Fi transceiver module; Sensitivity: Reliable connection for real-time data transmission

). These sensors are combined to collect detailed information on acceleration, rotation, and posture. The accelerometer tracks variations in body acceleration across three dimensions, whereas the gyroscope detects rotational movements. This setup allows the Gaitband to assess gait patterns, postural alterations, and movement characteristics in real time.

The Gaitband is powered by a 5 V input and is configured to collect and analyze data in real time. The integrated accelerometer and gyroscope sensors provide precise measurements of movement, orientation, and acceleration. These data are handled by an integrated MCU, which conducts basic signal conditioning, such as filtering and noise reduction. The processed data are subsequently sent to the RO-SmartAgeing cloud database via a Wi-Fi module. The I2C interface streamlines communication between the sensors and the MCU, providing effective data management and tailoring based on the needs of the individual user (Figure 2). The Gaitband is set up to transmit necessary information to the ICIPRO cloud, where it is integrated with the capabilities of RO-SmartAgeing system.

The Gaitband enables the provision of insightful data on posture and gait, which is critical for assessing fall risk and recommending additional treatment changes. The Gaitband has an ergonomic shape intended to enhance comfort during prolonged usage.

Alongside the Medical Blackbox, the Ambient Blackbox enhances the RO-SmartAgeing system’s capabilities by providing a smart and sensitive environmental monitoring solution in the patient’s environment. This device is designed to monitor a variety of environmental conditions.

The Ambient Blackbox is built on an Arduino UNO board, which was chosen for its adaptability and its capacity to manage several sensors successfully. The Arduino UNO orchestrates data collection and processing actions with low power consumption, which is required for continuous environmental monitoring. Power is supplied via an adequate power source embedded within the system. An Espressif NodeMCU 8266 Wi-Fi module enables connectivity to the RO-SmartAgeing system, ensuring proper transmission of data. This module allows for real-time updates and effortless interaction with the other monitoring capabilities, similar to the connectivity solutions deployed in the Medical Blackbox. The Ambient Blackbox features a range of sensors, each selected for its specific role in environmental assessment (

Table 4. Main characteristics of the sensors encompassed within the Ambient Blackbox.

Sensor Type	Function	Key Specification	Technical Details
Temperature and Humidity Sensor (DHT11) [70]	Measures ambient temperature and humidity	Measurement range: 0–50 °C, 20–80% RH; Operating voltage: 3.3 V–5 V	Measurement principle: Uses a digital sensor with a humidity-sensitive component and a temperature sensor; Components: DHT11 sensor element; Accuracy: ±1 °C for temperature, ±5% RH for humidity
Temperature and Pressure Sensor (BMP280) [71]	Measures ambient temperature and atmospheric pressure	Measurement range: 300–1100 hPa; Operating voltage: 1.8 V–3.6 V	Measurement principle: Uses piezoelectric technology to measure pressure and temperature; Components: BMP280 sensor element; Accuracy: ±1 hPa for pressure, ±1 °C for temperature
Temperature Sensor (LM35) [72]	Measures ambient temperature	Measurement range: −55 °C–150 °C; Operating voltage: 4 V–30 V	Measurement principle: Produces a linear voltage output that is directly proportional to temperature; Components: LM35 sensor element; Accuracy: ±0.5 °C
Light Sensor (TSL2591) [73]	Measures light intensity	Measurement range: 0–88,000 lux; Operating voltage: 3.3 V	Measurement principle: Uses photometric technology to measure light intensity; Components: TSL2591 sensor element; Accuracy: ±20 lux
Air Quality Sensor (CCS811) [74]	Measures CO2 concentration and volatile organic compounds	Measurement range: 400–8192 ppm CO2; Operating voltage: 3.3 V	Measurement principle: Detects CO2 levels and volatile organic compounds using a metal oxide sensor; Components: CCS811 sensor element; Accuracy: ±50 ppm for CO2
Gas Sensor (MQ2) [75]	Detects presence of gases (CH4, CO) and smoke	Measurement range: 10–1000 ppm; Operating voltage: 5 V	Measurement principle: Uses a semiconductor sensor that changes resistance in the presence of gases; Components: MQ2 sensor element, heater, and sensitive layer; Sensitivity: Detects alcohol, methane, and propane
Motion Sensor (PIR) [76]	Detects motion in the environment	Detection range: 1–7 m; Operating voltage: 5 V	Measurement principle: Uses passive infrared technology to detect motion; Components: PIR sensor element; Sensitivity: Adjustable to detect movement within different ranges

):

The Ambient Blackbox, like the Medical Blackbox, integrates its sensors with an Arduino UNO board, which allows for the gathering of a complete set of data. In order to achieve high-quality environmental measurements, the raw data are processed by signal conditioning, a process which includes filtering and amplification. The MCU manages real-time processing, using embedded algorithms to interpret sensor data and deliver precise environmental information. The NodeMCU 8266 Wi-Fi module manages the transmission of data between the Ambient Blackbox and the RO-SmartAgeing system. This module sends data to a Raspberry Pi gateway device, which then transmits the data to the ICIPRO cloud for additional processing and visualization. The I2C serial bus interface protocol is used for accurate data transmission and easy communication between components. The Ambient Blackbox has a 1602 × 2 LCD display for user interaction. It displays data about the environment in real time and can be adjusted using the Arduino IDE. The display enables users to quickly obtain key ambient data and make knowledgeable choices based on the information gathered (Figure 3).

Incorporating the Ambient Blackbox within the RO-SmartAgeing system ensures that environmental data are securely transmitted and managed.

3.2. Expanding the Functionalities Provided by the Decision-Making Tools within the NeuroPredict Platform

The NeuroPredict platform makes significant improvements to the decision-making tools that were initially developed to expand the capabilities of the RO-SmartAgeing system. The Medical Blackbox, Gaitband, and Ambient Blackbox have been enhanced with new sensors to improve their usefulness and decision-making capabilities.

The NeuroPredict platform’s improvements consist of the inclusion of broadened sensor capacity within the three basic decision-making tools. The rationale for these modifications arises from the need to address the changing demands of neurodegenerative-disease management and improve general decision-making capabilities in geriatric care.

Table 5. Main characteristics of the newly added sensors and technology within the decision-making tools encompassed within the NeuroPredict platform.

Decision-Making Tool	Newly Added Sensor	Main Characteristics	Enhanced Decision-Making Capabilities
Medical Blackbox	Waterproof Temperature-Probe Sensor (DS18B20) [78]	Measures temperature in a range of −20 to 105 °C under various environmental circumstances	Provides information necessary for monitoring body temperature fluctuations that can be suggestive of infections or other health disorders, and is especially important in managing neurological diseases in cases where the regulation of temperature may be affected.
Medical Blackbox	Sensirion CO2 Sensor (SFM3300-D) [79].	Measures air and gas flow with high precision and a digital interface	Improves the capacity to monitor respiratory function and air quality, which is significant for people with neurological diseases like PD, where respiratory problems are widespread. Accurate CO2 measurements enable immediate action and care improvements.
Medical Blackbox	Galvanic Skin Response Sensor [80]	Measures galvanic skin response, indicating physiological or emotional activity levels by changes in skin conductivity	Assesses stress and psychological alterations that might impact cognitive performance and general well-being in individuals with neurodegenerative diseases. Addressing these characteristics enables better management of symptoms associated with emotional or psychological stress.
Gaitband	Accelerometer (6-Axis) and Magnetometer (GY-511 LSM303DLHC) [81]	Provides extensive movement and orientation data by combining accelerometer and magnetometer measurements	Improves gait and posture monitoring, which is vital for early identification and continuing evaluation of neurodegenerative disorders such as PD disease or AD, as motor symptoms and postural instability are prominent.
Gaitband	GPS Module (SAM-M10Q) [82]	High-accuracy GPS module supplied with a u-blox SAM-M8Q GPS receiver for accurate location and navigation information	Supports tracking, including outdoor activities, patient mobility, and spatial orientation, which is essential for patients with cognitive decline or movement disorders. It facilitates safeguarding and assistance by identifying differences from usual movement patterns or potential wandering.
Gaitband	Bluetooth Module (HM-10) [83]	Supports Bluetooth Low Energy 4.0 for efficient and low-power communication	Improves real-time data synchronization across devices and allows for easy integration into the health management system. For neurodegenerative patients, this enables constant monitoring and rapid adaptations according to the data gathered, thereby enhancing geriatric and neurodegenerative care management.
Ambient Blackbox	Gas Sensor (MH-Z16) [84]	Measures CO2 concentrations up to 50,000 ppm, useful for assessing air quality	Enables the monitoring of environmental conditions that impact respiratory health, which is important for the management of neurological diseases with respiratory consequences. Enhanced air-quality data allow the creation of a safe and healthy living environment for patients who are at risk.

outlines the integration of additional sensors into the original decision-making tools inside the NeuroPredict platform, highlighting how these enhancements significantly expand decision-making capabilities for both geriatric care and neurodegenerative-disease management.

Figure 4 illustrates the data flow for the three decision-making tools included in the NeuroPredict platform. Each device came with a range of sensors and technologies, some of which were specifically introduced with the NeuroPredict platform, and are marked in red. The diagram shows all stages of data gathering, processing, and visualization.

The data flow diagram highlights the framework of the NeuroPredict platform’s decision-making capabilities. Each decision-making tool—including the Medical Blackbox, Ambient Blackbox, and Gaitband—includes a variety of sensors for the measurement of significant healthcare parameters. The new sensors add features to this data-gathering, providing measurements which are more detailed and accurate. Data collected are transmitted through the Raspberry Pi interface, which guarantees that data from various sensors within each tool are merged and ready for further processing. The data are subsequently sent to the cloud for secure storage and processing. The cloud-based platform enables comprehensive data analysis, employing advanced algorithms to interpret all of the intricate data generated by the tools. Ultimately, the processed data are made available via visual interfaces on computers or tablets.

Figure 5 presents the architecture of the RO-SmartAgeing system and the NeuroPredict platform, describing all of their fundamental components and processes. It depicts the entire data lifecycle, from data sources to user engagement: data sources (comprising all the sensors and equipment which gather diverse physiological and environmental data, establishing the cornerstone of the data-gathering process); data transmission (data gathered from the sources are transmitted over secure and effective channels to guarantee that the data ascends to the computational units with no damage, thereby ensuring data integrity); data processing (The data are preprocessed before being analyzed in depth. This stage involves data cleansing and first-processing to make sure that only high-quality, relevant information is transmitted); cloud processing (The cloud architecture is separated into two key parts: analysis and processing. The process involves advanced algorithms and analytical tools that assess raw data and extract relevant patterns and insights. This phase is important for converting gathered data into useful knowledge and applications; processed data are used in a variety of applications meant to improve geriatric care and manage neurodegenerative diseases. These applications enable real-time information and support for decision-making); user interaction (This features a visualization and interaction interface that allows healthcare professionals and patients to access and comprehend data via user-friendly dashboards on computers and tablets. This accessibility guarantees that the insights gained from the data can be easily accessed for prompt and informed decision-making).

By displaying the common framework, Figure 5 highlights the architecture’s strength and scalability, advantages which can enable complex healthcare solutions across several DHS. This feature of shared architecture ensures that improvements made in one system may be easily transferred to the other, fostering ongoing development and innovation in geriatric and neurodegenerative care.

3.3. Data-Driven Decision Support

The integration of complex decision-making tools such as the Medical Blackbox, Gait-band, and Ambient Blackbox into the RO-SmartAgeing system and the NeuroPredict platform demonstrates the new potential of data-driven decision support in geriatric care. Such systems use real-time data collection and analysis to generate exhaustive health insights, allowing healthcare providers to make decisions which are more informed. By continuously monitoring a variety of important health data, these tools enable the early detection of possible health disorders, leading to timely healthcare procedures. Additionally, the integration of predictive analytics into these systems allows for the prediction of health patterns and the optimization of therapeutic strategies adapted to particular patient requirements. This data-driven approach not only boosts the precision and effectiveness of medical interventions but also promotes a proactive tailored healthcare paradigm, considerably enhancing the quality of life and health outcomes for elderly patients.

The data-driven decision support provided by the three decision-making tools—Medical Blackbox, Gaitband, and Ambient Blackbox—within the RO-SmartAgeing system and the NeuroPredict platform is enhanced by means of the following:

• Complex health parameters: To achieve comprehensive monitoring, multiple health parameters must be tracked concurrently, such as blood glucose levels, vital signs, dietary patterns, physical activity, and other pertinent biomarkers. A more comprehensive and nuanced picture of a person’s health is provided by the integration of data from many sources [85]. This integrated approach not only facilitates personalized healthcare but also supports the proactive management of chronic conditions prevalent in elderly populations, thereby improving overall health outcomes and quality of life. In geriatric healthcare, where holistic assessment and personalized interventions are paramount, leveraging comprehensive health data enables data-driven decision-support systems to analyze complex health patterns over time. This capability empowers healthcare providers to tailor care plans specifically to the evolving needs of elderly patients, ensuring timely interventions and optimizing treatment efficacy.
• Real-time data synthesis: When connected to a DHS like the RO-SmartAgeing system or the NeuroPredict platform, decision-making tools facilitate the synthesis of health data in real-time, giving healthcare professionals fast access to the most recent information. By leveraging real-time data synthesis, healthcare providers can implement timely adjustments to treatment plans, ensuring optimal care strategies tailored to the evolving health needs of elderly patients, thus enhancing their health management experience, and reducing healthcare costs associated with preventable complications. This capability exemplifies the transformative impact of DHS in geriatric care, where proactive monitoring and real-time insights enable data-driven decision support to enhance clinical outcomes and patient satisfaction.
• Interconnected medical devices: Integration is the process of efficiently integrating different medical devices into DHS to build a networked environment. The total effectiveness of disease care is improved by this interconnection [86], which offers a more thorough picture of the patient’s health evolution. This interconnectedness is crucial in facilitating data-driven decision-making processes that empower healthcare professionals to intervene proactively, anticipate health deterioration, and optimize treatment strategies specifically tailored to the complex healthcare needs of elderly patients, thereby promoting personalized care and improving health outcomes.
• Predictive analytics: Predictive modeling is made possible by DHS’ advanced analytics, in conjunction with extensive monitoring. Predictive analytics can foresee potential challenges or deviances from the intended health evolution by examining patterns and trends in health data across time [87]. In geriatric healthcare, predictive analytics play a crucial role in enhancing data-driven decision-support systems, enabling proactive management of chronic conditions and personalized care planning based on predictive insights derived from comprehensive health data.
• Patient engagement and empowerment: By giving patients direct access to their health data, smart monitoring environments integrated with DHS encourage patient involvement ([25]. Enhanced patient engagement fosters a collaborative healthcare environment in which elderly patients become active partners in their care journey, leading to improved adherence to treatment regimens, better health outcomes, and increased satisfaction with healthcare services, ultimately promoting a patient-centered approach to geriatric care.
• Customized treatment plans: Treatment plans that are both individualized and data-driven may be created due to the integration of comprehensive health data within DHS. Tailored medical care approaches enhance patient compliance and lead to better results. DHS that support customized treatment plans based on comprehensive health data enable data-driven decision-support systems to optimize care delivery and enhance treatment efficacy for elderly patients, highlighting the critical role of these treatment plans in modern geriatric healthcare practices.
• Secure data management: Robust data security measures are necessary inside DHS, given their monitoring capacity, in order to protect sensitive health information [88]. To guarantee patient privacy and comply with healthcare standards, secure data transmission and storage, as well as access constraints, should be given top priority in smart environments. DHS that prioritize secure data management enhance patient trust and healthcare-provider confidence in the usage of DHS for comprehensive health monitoring and data-driven decision support, thereby promoting sustainable and patient-centric geriatric healthcare practices.

4. Results

The designs of the Medical Blackbox, Gaitband, and Ambient Blackbox, as outlined in previous sections, represent a significant achievement in terms of decision-making tools for geriatric care. These tools reflect a complex integration of sensor technology and real-time data processing which is specifically designed to improve healthcare for older people. The following presentation focuses on these devices’ functions and efficacy, considering their capacity to provide accurate, timely, and proactive health information, and hence improving patient outcomes and enabling data-driven healthcare approaches.

The Medical Blackbox was constructed as an intricate decision-making tool which incorporates several sensors to collect an array of health parameters. This multi-sensor approach ensures extensive and precise data gathering, giving accurate, real-time insights to enable informed decision-making in geriatric healthcare. The Medical Blackbox’s front view, as illustrated in Figure 6a, shows its user-centric design, which was intended for easy integration into a variety of healthcare environments. The user-friendly interface (Figure 6b) enables quick data gathering for both healthcare professionals and patients, allowing straightforward use in clinical and home settings. The keyboard allows the user to select a particular parameter for measurement, and the LCD display (which has four rows and 20 characters per row) presents the parameters that can be measured (1—Temperature; 2—Alcohol; 3—Pulse and Oxygen Saturation; 4—EKG; and 5—Spectrogram), as presented in Figure 6a. The internal structure of the Medical Blackbox (Figure 6c) emphasizes refined circuitry and sensor integration. This configuration enables trustworthy data collection and management, with high-precision sensors enabling exact health signals in a variety of environments, including clinical and residential settings. The device features the ability of real-time data transmission and processing, with latency times of less than two seconds.

As previously stated, the Medical Blackbox is now being improved for integration with the NeuroPredict platform, which includes the previously described intricate sensors. These additional features considerably improve the device’s decision-making capabilities by delivering information about physiological signs, ambient circumstances, and emotional reactions which is more detailed. We made modifications based on laboratory testing of the initial Medical Blackbox designed for the RO-SmartAgeing system. We decided to remove the temperature sensor that was initially included, as it measured the internal temperature of the device rather than the user’s body temperature. To address this, we replaced it with a sensor specifically designed for measuring body temperature, ensuring that the health data were more relevant. We also chose to discontinue the use of the urine sensor due to the challenges involved in maintaining sterile conditions for the sample. We also determined that the test strips used for urine analysis did not provide the level of accuracy needed for reliable health data collection. These adjustments reflect our commitment to improving the precision and reliability of the Medical Blackbox in real-world applications. This extended sensor array better empowers the Medical Blackbox to provide precise and meaningful information for the management of neurodegenerative disorders, allowing for earlier identification, tailored therapies, and enhanced therapeutic strategies. Figure 7 depicts the placement of the accessories necessary for using the new sensors.

The Gaitband, another decision-making tool, was developed with the particular aim of improving fall-detection abilities. This device uses a modern accelerometer and gyroscope to monitor variable movement patterns with a high level of accuracy. The Gaitband collects complex biomechanical data to facilitate advanced insights into monitored patients’ balance and gait stability, enabling prompt action and enhanced general protection and mobility for seniors.

The Gaitband has high-precision sensors for movement combined within a supportive structure that may be worn on different parts of the body. Figure 8 shows various placement choices for the Gaitband: (a) on the chest and (b) on the ankle. In addition, (c) shows the internal view of the device.

When placed on the chest (Figure 8a) or ankle (Figure 8b), the Gaitband continuously monitors movement features to identify falls. Initially intended for ankle placement, the device’s laboratory testing showed a few drawbacks: it turned out to be uncomfortable, particularly for elderly patients, and at risk of generating incorrect results when the user was in lying down or in a recumbent position, misinterpreting these postures as falls. The Gaitband has effective sensors, notably a three-axis accelerometer and a three-axis gyroscope (Figure 8c). These sensors are connected in order to collect complete movement data. The accelerometer determines linear acceleration across three orthogonal axes, while the gyroscope measures rotational velocity, providing information on the user’s posture and movement patterns. To improve fall-detection reliability, the Gaitband periodically assesses the patient’s posture using sensor data. When a probable fall is identified, the device performs a secondary evaluation after a two-minute period. This a second evaluation examines fluctuations in acceleration and angular velocity to see if the identified anomaly remains, suggesting a possible fall after which the monitored individual may be unable to recover to a standing position. If the parameters fail to return to baseline values that indicate an upright posture, an alert is set up and transmitted to healthcare professionals, caretakers, or family members.

Experimental data shows that placing the Gaitband on the chest (Figure 8a) enhances detection accuracy. This positioning decreases false alerts and improves the accuracy of fall detection by giving more reliable assessments of body posture and movement, as opposed to ankle placement.

Ongoing enhancements to the Gaitband device have boosted its fall-detection and monitoring features. The combined use of a high-performance accelerometer and a gyroscope is expected to increase sensitivity in gathering and evaluating dynamic movement patterns. These improved sensors provide a more precise measurement of gait stability and balance, which is important in developing successful fall-prevention approaches. Other than that, the use of GPS technology enables real-time monitoring and localization of the monitored patient, providing important benefits in emergency circumstances and allowing immediate action. While these updates are still currently in development, it is anticipated that they will not only extend the Gaitband’s capacity to detect falls, giving it better precision, but also increase its usefulness for managing neurodegenerative diseases through its ability to supply extensive information on movement and position. This comprehensive approach enables monitoring and interventions which are more effective, optimizing the outcomes for patients while leading to a geriatric healthcare setting that is both more proactive and more reactive.

The Ambient Blackbox is a key component of an array of new technologies intended to improve geriatric healthcare through extensive environmental monitoring. This device utilizes high-precision sensor technology to provide continuous and broad assessments of environmental factors, augmenting the physiological data acquired from the Medical Blackbox and Gaitband.

The Ambient Blackbox includes a variety of sensors that detect significant conditions such as temperature, humidity, and ambient light levels. These sensors are easily integrated into an ergonomically built device, as shown in Figure 9. The Ambient Blackbox’s front view (Figure 9a) highlights its minimal, discreet design, one which renders it suitable for usage in several kinds of scenarios, ranging from clinical environments to individual residences. Figure 9b shows the device’s internal layout, which includes an assembly of sensors and circuitry adjusted for accurate data collection and processing.

The Ambient Blackbox sensor kit was intended to provide high-resolution, real-time monitoring of environmental factors that may have an influence on older people’s health and well-being. The Ambient Blackbox was designed with consideration to seniors, and, once set up, needs no additional operation from the monitored patient. When the device becomes operational, it immediately sends gathered data to the gateway. If the gateway is connected to the cloud, remote data management and sensor setup without the need for specialized interaction is possible. This extensive integration not only facilitates uniform data interchange and visualization, but it also improves the overall efficacy of the DHS by assuring robust data transmission and accessibility.

The Ambient Blackbox’s set of sensors plays an important role in providing a secure and supportive living environment for seniors. By constantly tracking a variety of environmental metrics, the device facilitates the detection and mitigation of factors that might have a negative impact on health. Monitoring ambient light levels, for instance, contributes to the management of circadian rhythms, which may have a substantial impact on sleep patterns and general well-being. Experimental testing demonstrates that the Ambient Blackbox succeeds in delivering accurate and constant environmental monitoring. Its capacity to provide real-time alerts and notifications when environmental factors differ from predefined criteria can be essential for enabling a timely response. This capability guarantees that any detrimental alterations to the environment that might significantly impact the health of older people are quickly addressed, hence improving the overall efficacy of the healthcare system.

At present, the Ambient Blackbox is being improved as a result of its integration with the NeuroPredict platform. This development entails the integration of refined sensors, as described in Section 3, which are intended to expand the device’s functionality and maximize its value in geriatric healthcare. These new sensors are intended to provide a more intricate and thorough assessment of environmental factors, allowing the Ambient Blackbox to better support comprehensive insights into the link between environmental conditions and individual health, and considerably enhancing its decision-making features.

Figure 10 illustrates the combined layout of these three decision-making tools and their data management capabilities. Figure 10a displays the integration configuration, demonstrating how the Medical Blackbox, Gaitband, and Ambient Blackbox interact with peripheral devices and their components. The LCD display on the Raspberry Pi indicates real-time data gathered by the Ambient Blackbox, allowing users to observe current conditions directly on the screen. This feature operates even if wireless communication from the NodeMCU to the Raspberry Pi is hindered. Also, the Raspberry Pi has a keyboard, which allows users access to the different functions, as needed. The tablet displays the main page of the RO-SmartAgeing system. Figure 10b shows data storage in the system’s database, illustrating how the Gaitband data have been stored and structured. This centralized data repository enables efficient data management and retrieval, allowing for real-time analysis and long-term monitoring of health and environmental indicators. A robust data storage infrastructure is necessary for maintaining data integrity and providing decision-making processes with accurate, relevant data.

As to the decision-making tools generated for the RO-SmartAgeing system and the ongoing improvements inside the NeuroPredict platform,

Table 6. Technical and functional comparison of decision-making tools: RO-SmartAgeing system vs. NeuroPredict platform.

Feature	RO-SmartAgeing System Decision-Making Tools (Medical Blackbox, Gaitband, Ambient Blackbox)	NeuroPredict Platform Decision-Making Tools (Medical Blackbox, Gaitband, Ambient Blackbox)
Number of Sensors and Technology	15	17, of which 5 are new and 1 is improved
Physiological Parameters in Medical Blackbox	EKG, heart rate, alcohol concentration in breath, blood oxygen saturation, heart rate, spectrogram, internal temperature	EKG, heart rate, alcohol concentration in breath, blood oxygen saturation, body temperature, air and gas flow, galvanic skin response
Environmental Parameters in Ambient Blackbox	Ambient temperature, humidity, atmospheric pressure, light intensity, CO2 concentration and volatile organic compounds, presence of gases (CH4, CO) or smoke, motion in the environment	Ambient temperature, humidity, atmospheric pressure, light intensity, volatile organic compounds, presence of gases (CH4, CO) or smoke, motion in the environment, improved measurement of CO2 concentrations
Motion Parameters in Gaitband	Acceleration, orientation, angular velocity, rotational movement	Improved detection of acceleration, orientation, angular velocity, and rotational movement due to the 6-axis accelerometer with enhanced sensitivity for fall detection, GPS
Gaitband Response Time	Immediate fall-detection response	Improved algorithm reduces false alarms and enhances response time (currently under development)
Monitoring Interval	Continuous monitoring, with periodic manual checks	Continuous with adaptive intervals based on patient condition
Fall-Detection Sensitivity	Moderate, with occasional false positives	Improved fall-detection accuracy due to enhanced algorithm, sensors and technology (currently under development)
Battery Life	Gaitband: 48 h (504060 battery)	Gaitband: 50 h (103450 battery)
Wireless Connectivity	Wi-Fi connectivity	Bluetooth 4.0, Wi-Fi connectivity
Data Storage and Security	Secure storage with basic encryption	Advanced security protocols, with additional data protection features (currently under development)
Physical Dimensions	Compact and portable, suitable for elderly users	Slightly reduced size for easier wearability and handling
Material Used for 3D Printing the Devices	Polylactic acid—unprotected environmentally friendly material, with rapid degradation	Polylactic acid with an extra layer to ensure minimal environmental impact with slower degradation
Potential for Using Collected Data for Customized Decision-Making Support	Tailored to geriatric health profiles	Enhanced personalization, with cognitive and environmental factors associated with PD, AD, and MS

provides a quick comparison of their technical and functional features. It provides a brief summary of their current features and the improvements in these tools. This table illustrates the interim progress and upgrades for the NeuroPredict platform project, which is in the second year of a four-year development cycle. It demonstrates the main distinctions between the RO-SmartAgeing system and the NeuroPredict platform in terms of the three decision-making tools, with a focus on advances in sensor technology, functionality, and performance. This comparison highlights the ongoing attempts to optimize these tools, illustrating how they are currently being developed to improve tailored healthcare and better address the requirements of senior patients.

The NeuroPredict platform provides advanced sensors and algorithms indicative of specific advancements in sensor technology and performance. These involve the integration of additional sensors, as well as improvements in fall-detection accuracy and environmental measurements, indicating another leap forward in system capabilities. Functional improvements, like increased battery life, wireless connectivity, and data storage, assist with the enhancement of decision-making capabilities and system performance in general. While both DHS are designed for senior patients, the NeuroPredict platform provides outcomes which are more personalized by combining cognitive and environmental factors related with specific diseases such as PD, AD, and MS. This shows a shift toward greater customization and condition-specific therapy practices. The comparison includes both the sensor technology and their performance. For example, the NeuroPredict platform’s usage of a 6-axis accelerometer with higher sensitivity improves fall-detection performance when compared to the RO-SmartAgeing system. This demonstrates how new developments in sensor technology have led to enhanced precision and effective monitoring. The table emphasizes gains in data storage and security, as well as changes in device design for a better user experience, as well as an ongoing commitment to sustainable practices.

As for the experimental design, The RO-SmartAgeing system was assessed under controlled laboratory circumstances in order to simulate real-world scenarios. This approach aimed to evaluate the system’s performance and collect information on its usability. A team of 15 testers, all members of the development team, was established to thoroughly examine the RO-SmartAgeing system and its three decision-making tools (Medical Blackbox, Gaitband, and Ambient Blackbox). To ensure an in-depth assessment, these testers took on several roles that represented expected end users, such as seniors, healthcare professionals, and technical-support individuals. This action of the workgroup contributed by ensuring that the system was evaluated from a variety of user viewpoints. Since the RO-SmartAgeing system had only been evaluated in a controlled laboratory setting, the assessment was intended to simulate real-world conditions as faithfully as possible.

The RO-SmartAgeing system’s decision-making tools were tested for usability, functionality, and dependability. For several weeks, testers interacted with the devices in a number of scenarios intended to simulate real-life situations that the tools might come across in a geriatric-care setting. Feedback was obtained on important issues, including device usability, sensor accuracy, system responsiveness, and overall user-experience. The insights gathered during this testing phase provided input which was indispensable for the NeuroPredict platform’s ongoing development, which is now in its second year of a four-year development cycle.

Table 7. User feedback and corresponding enhancements in the NeuroPredict Platform.

Aspect Evaluated	Feedback Summary	Comments	Enhancements in NeuroPredict Platform
Ease of use	Generally intuitive, but varied feedback depending on the tester’s role. Healthcare providers found it efficient, while elderly testers struggled with the small display on the Medical Blackbox.	Medical Blackbox: The 4-row LCD screen was noted as being challenging for elderly users with visual impairments. Healthcare providers suggested a more prominent and clear display.	Medical Blackbox: Plans to introduce a larger, high-contrast display with voice-assisted navigation (currently under development)
Sensor accuracy	Accurate in most conditions, but discrepancies were noted by testers simulating patient roles, particularly in fall detection with the Gaitband.	Gaitband: Improved fall-detection sensitivity was observed by healthcare providers, but false positives were reported by those in patient roles, especially in dynamic environments.	Gaitband: Enhanced algorithms and sensors are being integrated to reduce false positives and increase accuracy levels across different conditions (currently under development)
System responsiveness	Immediate response in most cases; however, technical support testers noticed a slight delay in data transmission in low-connectivity environments.	Ambient Blackbox: Responsiveness was satisfactory, but Wi-Fi interruptions affected real-time data availability, particularly in more complex testing scenarios.	Ambient Blackbox: Implementation of a dual-connectivity option (Wi-Fi and Bluetooth) to ensure a more reliable transmission of data
Overall user experience	Positive overall, but testers in prolonged usage scenarios suggested improvements in battery life and connectivity.	Gaitband: Healthcare providers appreciated the extended monitoring capabilities, while users simulating patients suggested the need for better battery performance for continuous use.	Gaitband: Battery-life improvements are being made, along with enhanced connectivity options to assure consistent performance
Setup and configuration	Straightforward for tech-savvy users, challenging for elderly users or those less familiar with technology.	All decision-making tools: Elderly testers found the setup process complex, while technical support testers suggested a more streamlined and intuitive configuration process.	All decision-making tools: Development of a simplified, step-by-step setup guide with visual aids and a more intuitive interface is planned
Comfort during use	Generally comfortable, though testers in patient roles found the Gaitband’s chest placement slightly restrictive.	Gaitband: Elderly users noted the chest placement as being somewhat uncomfortable during prolonged use. Healthcare providers suggested alternative placements or adjustments for increased comfort.	Gaitband: Redesigns are underway to offer alternative placements and designs which are more ergonomic for enhanced comfort.
Device durability and build quality	Robust and durable, but concerns were raised about long-term wear and tear, particularly by testers simulating active patient roles.	All Tools: The materials used were praised for their durability by healthcare providers, but testers in active roles expressed concerns about the sensors’ longevity and the casing’s ability to withstand daily wear.	All Tools: Ongoing material improvements aim to increase durability while maintaining lightweight and user-friendly designs.
Environmental impact of materials	Positive feedback overall, with elderly testers appreciating the eco-friendly materials, but concerns about rapid degradation were noted by those in technical roles.	All Tools: The use of polylactic acid was appreciated for its environmental benefits, though technical testers raised issues regarding its durability and rate of degradation.	All Tools: An improved material composition that balances environmental responsibility with longevity is being developed.

summarizes the user feedback and the associated improvements being developed in the NeuroPredict platform to solve the elicited challenges. This comparison underscores the ongoing attempts to develop and improve decision-making tools, ensuring that they better fulfill the demands of their intended users.

The input obtained throughout the testing process underlines the necessity of iterative design and user-centered development in improving decision-making tools. By tackling the difficulties raised during the RO-SmartAgeing system assessment, it is anticipated that the NeuroPredict platform will provide a more comprehensive and user-friendly approach. The projected advancements, notably those relating to sensor accuracy, system responsiveness, and user interface design, show a commitment to continuing improvement. These developments strive not only to go beyond identified limitations, but also to foresee future demands, so that the platform will evolve to keep up with both technological advancements and user expectations.

5. Discussion

The combined use of these tools not only boosts real-time monitoring but also allows for deeper assessment, resulting in better-informed healthcare decisions. By merging physiological data with environmental factors, the DHS facilitate a proactive approach to managing geriatric care, tackling potential challenges before they worsen. The comprehensive data storage and management framework guarantees that relevant data are easily accessible to healthcare professionals, supporting immediate responses and customized therapeutic approaches. By combining a wide variety of physiological and environmental data, these devices provide an integrated picture of patient health, which is critical for precise diagnosis and prompt intervention.

A key strength of these integrated decision-making tools is their capability to facilitate proactive healthcare management. These integrated decision-making tools excel at facilitating proactive healthcare management. The Medical Blackbox, Gaitband, and Ambient Blackbox make possible continuous and thorough data gathering, allowing healthcare professionals to foresee potential health problems prior to the point at which they become severe. For example, through merging real-time health data from the Medical Blackbox with environmental parameters monitored by the Ambient Blackbox, physicians might detect developing patterns, along with potential issues, beforehand. This proactive approach promotes preventative measures, which may decrease hospitalizations and lower overall healthcare expenses, resulting in improved efficiency and effectiveness in patient care.

A key benefit of these decision-making tools is their ability to improve tailored medical care. The combined use of the Medical Blackbox, Gaitband, and Ambient Blackbox allows for a more personalized approach to patient healthcare management, one that shifts for specific health profiles and requirements. This personalization allows healthcare professionals to leverage thorough and relevant data to make knowledgeable decisions tailored to each patient, which leads to improved monitoring and treatments which are more appropriate. These approaches improve healthcare systems’ responsiveness by integrating data in real time. By constantly monitoring both physiological and environmental parameters, the devices enable prompt adjustments to treatment plans based on the most recent information. This dynamic response capability proves essential for addressing difficult situations in geriatric care, for which prompt interventions might avoid a worsening and improve overall outcomes. The multiple dimensions of information collected by these decision-making tools additionally helps to provide a more complex comprehension of patient health. Healthcare professionals have access to a holistic image of a patient’s health status by merging different kinds of data, such as movement patterns and environmental impacts. This comprehensive perspective facilitates better management strategies and assists in detecting slight modifications in medical condition that may not be obvious with typical monitoring methods. One additional significant advantage of these tools is their ability to facilitate an increase in the collaborative nature of patient healthcare. These decision-making tools improve collaboration among healthcare teams by enhancing data-exchange capabilities. This interactive setting allows a more integrated care paradigm in which many different professionals may contribute to and gain insight from a centralized set of patient information, resulting in care methods which are more coherent and successful.

One additional strength is that the design of these decision-making tools reveals an explicit commitment to being more user-centric, which is important to their effective application in geriatric care. The Medical Blackbox and Gaitband have ergonomic and simple designs that are tailored exclusively to meet the requirements of older people, resulting in ease of use and accessibility. The Ambient Blackbox comes with automated transmission of information and remote configuration capabilities, which decrease the need for recurrent human involvement. This emphasis on usability not only improves the usefulness of the tools, but also corresponds to the preferences and skills of senior patients, making the devices acceptable for regular use

The cohesive layout of these tools emphasizes the necessity for advanced data management and analytics in geriatric care. By storing and structuring broad datasets, the DHS allow for deep analysis and long-term monitoring of health parameters. This robust data management structure is imperative in generating data-driven insights and customized therapeutic strategies. Advanced analytics capabilities improve the quality as well as accuracy of information used to support clinical decision-making, creating the groundwork for evidence-based practice. The advanced data storage capabilities integrated into the DHS provide beneficial understanding and support informed decision-making, ultimately increasing the overall quality of care.

Despite the benefits, it is important to acknowledge the limitations affecting the general efficacy and utility of these decision-making tools:

• The Medical Blackbox might encounter limitations in sensor performance and reliability that can be impacted by external factors such as electromagnetic interference and calibration inaccuracies, leading to inappropriate decision-making support. While its design is user-friendly, the interface’s four-row LCD display may pose challenges for senior users, especially those with visual impairments. Real-time data transmission may be disrupted in places with limited internet connectivity, influencing the timely availability of key health data.
• The Gaitband’s performance varies based on its placement on the body. While chest placement enhances accuracy, it may cause discomfort, whereas ankle placement might result in false positives, particularly in sitting-down circumstances. The device’s three-axis accelerometer and gyroscope may occasionally fail to correctly make distinctions between real falls and other movement disturbances, leading to possible errors and needless alerts. The fall-detection algorithm’s periodic posture assessments may even generate false alarms if non-fall situations are incorrectly classified as falls, making for unnecessary anxieties.
• The Ambient Blackbox’s environmental sensors may face calibration errors or deviations from the norm, compromising data accuracy. Data transmission may be hampered by breaks in wireless connectivity or communication difficulties with the NodeMCU, affecting the promptness of monitoring and response. Although the device requires minimal user engagement once installed, initial setup and configuration may be difficult for certain senior users or their caretakers, which would require simple instructions and easy setup procedures.

6. Conclusions

The RO-SmartAgeing system enhances healthcare efficiency and communication, as well as the independence of older adults, through real-time monitoring and personalized environments. The NeuroPredict platform extends these capabilities to manage neurodegenerative conditions, offering data-driven insights for better patient outcomes and reduced hospitalizations.

The inclusion of the Medical Blackbox, Gaitband, and Ambient Blackbox within these DHS frameworks represents a significant step forward in geriatric healthcare. The development team, which includes the authors of this paper, put forward the decision-making tools and technologies considered in the present research, such as the RO-SmartAgeing system and the NeuroPredict platform. This commitment ensures that the approaches and innovations given are thoroughly rooted in our established knowledge and operational expertise in the field of DHS. These decision-making tools improve care quality by providing an extensive way to monitor physiological and environmental parameters in real time. Their designs enable an effortless adoption of modern technology with intuitive interfaces, rendering the devices useful in both clinical and residential environments. This association implies that healthcare professionals will have access to a wide range of data, allowing for more informed decisions and prompt procedures.

The factor that distinguishes these tools from other associated ones is their capacity to collaborate to provide an extensive overview of a senior’s health. The Medical Blackbox’s comprehensive sensor set and refal-time data processing capabilities enable accurate health monitoring. The Gaitband is optimized for fall-detection and movement assessment, with accurate sensors and versatile placement choices, and the Ambient Blackbox enables diverse forms of environmental monitoring to establish a more secure habitat. This thorough approach aims to identify potential risks before they become more severe, resulting in improved medical conditions and a higher quality of life for the elderly.

To increase the efficiency and influence of the Medical Blackbox, Gaitband, and Ambient Blackbox inside the RO-SmartAgeing System and the NeuroPredict Platform, several directions for future development and enhancement are underscored:

• Integrating these devices with forthcoming technology can considerably improve their performance. For example, integrating advanced machine-learning algorithms and AI might increase the accuracy of data analysis and prediction capabilities, allowing for more accurate and useful insights into patient health.
• Increasing the number of physiological and environmental parameters monitored by devices can provide a more complete assessment of a patient’s health. Integrating sensors that collect additional health metrics or ambient factors might improve the identification of possible concerns and enable tailored solutions.
• Improving user experience and device security is critical. For instance, with regard to the Gaitband, this would entail refining its design for greater comfort during extended usage and lowering the number of errors that occur.
• Validation and testing in real-world situations are vital for addressing the changing demands of older patients and healthcare professionals.

These decision-making tools are distinguished by their regular improvement and adjustment. The determination to continually improve these tools demonstrates an eagerness to meet the constantly evolving requirements of geriatric care. As new technologies develop, these tools will acquire enhanced functionality and extended monitoring capabilities, which will boost their prominence in the DHS ecosystem.