Search Results (150)

Wearable healthcare technologies are transforming the healthcare landscape by enabling remote, real-time health data collection, supporting early diagnosis, personalizing treatment plans, and reducing healthcare costs and medical burdens. Central to these advancements are wearable sensors, which continuously capture physiological data such as heart rate, temperature, activity levels, and biomarker concentrations. However, the large volume and complexity of this data demand effective processing to extract meaningful medical insights. Artificial intelligence (AI) and machine learning (ML) have significantly enhanced the capabilities of wearable sensors by enabling advanced data analysis, pattern recognition, and predictive modeling. AI-enhanced wearable sensors can detect early signs of health issues, such as heart attacks, chronic diseases, and mental health conditions like stress, often before clinical symptoms become apparent. This review examines the integration of AI/ML models with wearable sensors across physical activity recognition, stress assessment, cardiovascular monitoring, personal exposure monitoring, and sweat biomarker detection. Unlike prior application-centered reviews, we emphasize methodological and translational evaluation by comparing task formulations, sensing modalities, dataset scale, validation protocols, performance metrics, and deployment constraints across domains. We further discuss advanced architectures, multimodal fusion, explainable AI, edge deployment, privacy and regulatory considerations, and the translational gap between research prototypes and clinically deployable wearable AI systems. Full article

Background and Objectives: Mental illnesses place a substantial burden on healthcare systems and often require complex pharmacological management. However, it remains unclear whether early antipsychotic polypharmacy independently predicts length of stay after adjusting for important confounders. This study aimed to investigate drug utilization patterns, including polypharmacy and drug–drug interactions (DDIs), assess anticholinergic burden, and identify predictors of the length of hospital stay in a psychiatric inpatient setting. Materials and Methods: This retrospective, observational study was conducted at Bolu İzzet Baysal Mental Health and Diseases Hospital with 280 adult patients admitted during 2022. Medication data were extracted from electronic medical records based on medication orders within the first 72 h of admission. Potential DDIs were assessed using Lexi-Interact, and anticholinergic burden was calculated using the ACB, ADS, and ARS scales. Predictors of the length of stay (LOS) were modelled using negative binomial regression. Results: The mean age of the population was 38.65 ± 13.86 years, and 62.1% were male. Polypharmacy was present in 37.9% of patients, while antipsychotic polypharmacy was observed in 63.9%. Potential DDIs were identified in 88.9% of patients, with a significantly higher prevalence in those with polypharmacy. Mean ACB and ADS scores were high at 5.56 ± 3.32 and 4.15 ± 2.79, respectively. Multivariable regression analysis revealed that antipsychotic polypharmacy was the primary independent predictor of prolonged hospitalization, associated with a 20.9% increase in LOS (IRR = 1.209, 95% CI: 1.044–1.400, p = 0.011). While age was also statistically significant (IRR = 1.006, 95% CI: 1.001–1.012, p = 0.019), its clinical impact was minimal, representing only a 0.6% increase in LOS per year. Conclusions: Antipsychotic polypharmacy within the first 72 h of admission is a significant independent predictor of prolonged hospitalization. The high prevalence of drug interactions and substantial anticholinergic burden highlight the need for systematic early medication review. Instead of general monitoring, targeted medication therapy review focusing on antipsychotic polypharmacy in the early period of admission may be essential to identify and mitigate modifiable risk factors for prolonged hospitalization, thereby optimizing pharmacotherapy in psychiatric inpatient settings. Full article

Background: Generative AI (GenAI) mental health chatbots are increasingly being developed to help address persistent barriers to mental healthcare. Unlike earlier rule-based and retrieval-based systems, GenAI chatbots generate open-ended outputs that can be inaccurate and unsafe. Documented harms from general-purpose GenAI chatbots have highlighted the need for purpose-built interventions with dedicated safeguards, yet how safety is implemented in such interventions remains poorly understood. Methods: This scoping review followed the Joanna Briggs Institute methodology and PRISMA-ScR guidelines, with a prospectively registered and peer-reviewed protocol. A systematic search of seven academic databases and search engines including MEDLINE, Scopus, PsycINFO, ACM Digital Library, IEEE Xplore, Google Scholar and Consensus was conducted in July 2025. Two reviewers independently screened records and extracted data. Safety mechanisms and risk mitigation strategies were narratively synthesised across three pre-specified domains: technical safeguards, pre-deployment safety considerations, and delivery-phase risk mitigation strategies. Results: Twenty-one studies across 11 countries were included. Most interventions incorporated at least one technical safety mechanism, most commonly fine-tuning and prompt engineering. A smaller subset implemented layered safety architectures combining retrieval systems, content filters or risk classifiers, and rule-based algorithms. Pre-deployment safeguards included clinical expert and user co-design approaches, research ethics procedures, and data privacy measures. During intervention delivery, detailed onboarding with role clarification was common, but human oversight was limited. Crisis referral protocols varied in rigour but were mostly underdeveloped, and systematic adverse event monitoring was sparse. Documented safety failures included missed suicidal ideation and provision of inaccurate clinical information. Conclusions: GenAI chatbot interventions require a robust sociotechnical approach that integrates technical safeguards with user co-design, procedural controls, and human oversight. Future research is needed to evaluate efficacy, improve safeguards and standardise safety outcome measurement. Regulatory oversight proportional to the risks these systems carry is required to enable integration into stepped or blended mental healthcare. Full article

Background: Digital health (mHealth) interventions are increasingly integrated into maternity care to improve health literacy and reassure expectant mothers. However, the “double-edged sword” of continuous monitoring may be associated with heightened anxiety. This study aimed to describe mHealth usage patterns and investigate the association between technology engagement and mental health outcomes among pregnant women in Romania, where perinatal distress is a significant public health challenge. Methods: This observational, cross-sectional study included 100 pregnant and immediate postpartum women at a tertiary maternity unit in Romania. Participants were stratified into mHealth Users (n = 52) and Non-Users (n = 48). Validated instruments, including the PHQ-9, GAD-7, and EPDS, assessed depressive and anxiety symptoms. Predictors of adoption were identified using multivariable binary logistic regression. Results: mHealth users were predominantly from urban environments (80.8% vs. 54.2%, p = 0.004) and reported higher rates of daily physical activity (p < 0.001). Users experienced significantly higher median scores for depression (PHQ-9: 6 vs. 4, p = 0.047), generalized anxiety (GAD-7: 7 vs. 6, p = 0.015), and pregnancy-specific anxiety (35 vs. 29.5, p = 0.028) compared to non-users. In the multivariable model, high psychological distress (OR 0.08 for low-stress vs. high-stress, p = 0.009) and urban residency (p = 0.043) were independent predictors of mHealth adoption. Notably, 96.2% of users shared their digital data with healthcare providers. Conclusions: mHealth adoption in this population is characterized by a “paradox of monitoring,” where usage is strongly associated with pre-existing psychological vulnerability and associated with higher distress. While these tools serve as markers for mental health risk, the high rate of data sharing offers a clinical opportunity for a hybrid model of care. Obstetricians should view high digital engagement as a prompt for targeted mental health screening and proactively mediate patient-generated data to mitigate anxiety. Full article

Postpartum depression (PPD) affects a substantial proportion of women globally and is often underdiagnosed due to barriers in screening, stigma, and limited access to care. This study presents the design and pilot evaluation of an mHealth application (“HeartHabit”) intended to support user awareness, self-monitoring, and potential identification of symptoms of PPD among Greek-speaking mothers. An alpha version of the application was evaluated through an online survey with 30 women within the first postpartum year, using a walkthrough video. The evaluation focused on perceived usability and acceptability rather than clinical outcomes or real-world use. Usability and app quality were assessed via the System Usability Scale (SUS) and a qualitative version of the user Mobile Application Rating Scale (uMARS), respectively, adopting a mixed-methods approach. Demographics, and mood and stress screening data were also captured. Quantitative data were analysed via descriptive statistics and qualitative responses via Framework Analysis. The results indicated high perceived usability (mean SUS = 83.7/100). Qualitative findings highlighted the importance of practical usability, self-regulation tools, personalisation, and connectivity with healthcare professionals. Privacy, data transparency, and user control over personal data were perceived as critical for trust. The application was perceived as a potentially useful adjunct to formal care or as at-home support when access to services is limited. Larger, controlled trials, clinical implementation protocols and clinician training are needed to promote the app’s safe integration into formal care. This mixed-methods evaluation, incorporating usability assessment and patient involvement, may offer a useful paradigm for early-stage digital mental health intervention development. Full article

Heart rate variability (HRV) has emerged as a key biomarker for assessing autonomic nervous system activity, stress, fatigue, and emotional states. With the rapid development of wearable sensor technologies, HRV analysis has expanded from clinical environments to real-world, continuous monitoring. This review summarizes current applications of HRV metrics in wearable devices, including fitness tracking, mental stress assessment, sleep quality evaluation, and early detection of physiological or psychological disorders. Recent advances in photoplethysmography (PPG)-based HRV estimation have enabled noninvasive and user-friendly measurement, though challenges remain in accuracy under motion and variable environmental conditions. We also discuss methodological considerations, such as artifact correction, data segmentation, and the integration of HRV with other biosignals for multimodal analysis. Emerging research suggests that combining HRV with metrics such as respiration rate, skin conductance, and accelerometry can enhance robustness and interpretability in dynamic settings. Finally, future directions are proposed toward personalized health analytics, emotion-aware computing, and real-time adaptive feedback systems. This review highlights the growing potential of wearable HRV analysis as a foundation for preventive healthcare and human–machine symbiosis. Full article

This bibliometric study examines the role of ubiquitous computing and intelligent systems in the treatment of mental and neurological disorders. Ubiquitous computing integrates computational intelligence into everyday environments, enabling seamless monitoring and support of patients. Intelligent systems, including wearable devices, environmental sensors, and mobile health applications, collect real-time data on behavior, physiology, and environmental factors. These systems support early detection of symptom changes, adherence to treatment, and crisis prediction through context-aware analysis. Artificial intelligence (AI) processes the collected data to generate personalized therapeutic feedback and notify healthcare providers when intervention is needed. In mental health care, intelligent environments can monitor mood, sleep, and social interaction patterns, providing valuable objective information about mental health status. In the case of neurological conditions such as Parkinson’s disease or epilepsy, intelligent systems facilitate movement tracking, seizure detection, and cognitive assessment outside of the clinical setting. Integration with electronic health records and telemedicine platforms ensures coordinated and responsive care. Ethical design, privacy protection, and patient consent remain key to successful implementation. In this way, ubiquitous computing is transforming care models by increasing autonomy, precision, and continuity in the treatment of complex neurodegenerative diseases, including those related to neurodegeneration in aging. Full article

Major depressive disorder (MDD) is a prevalent mental health condition that inflicts a high burden on individuals and healthcare systems. There is a clinical need to detect MDD relapse practically and effectively to improve treatment outcomes for patients. To address this, we developed a smart monitoring system using an Artificial Intelligence (AI) approach to estimate MDD severity and relapse risk from patients’ smartphone behavioral data (i.e., digital phenotyping). Thirty-five MDD patients were recruited from the Institute of Mental Health in Singapore, who installed the smartphone study app Sallie. Their symptoms were quantified using the Hamilton Depression Rating Scale (HAMD-17) at the start of the trial, and every 30 days after over 3 months. The app collected behavioral data such as activity, activity type, and GPS location used to train AI models such as logistic regression, decision trees, and random forest classifiers. We found that passive data collection continued for most participants (up to 79% retention rate) after 3 months. We also used five-fold cross-validation to predict HAMD-17 severity ranging from two to four classes and the relapse status, achieving 91%, 88%, and 78% accuracies for two to four classes, respectively, and a relapse prediction accuracy of 86% whereby four patients relapsed during the study. Additionally, anxiety factors within the HAMD-17 were significantly predicted (Pearson correlation coefficient = 0.78, p = 1.67 × 10⁻¹⁴). These results demonstrate the promise of using smartphone behavioral data to estimate depressive symptoms and identify early indicators of relapse. Full article

Major Depressive Disorder (MDD) is a significant global health burden that contributes to disability and reduced quality of life. Its impact extends beyond individuals, placing emotional, social, and economic strain on families and healthcare systems worldwide. Despite its prevalence, MDD remains widely misunderstood, with limited mental health literacy and persistent stigma often preventing individuals from seeking help. This research explored the prediction of MDD utilising social media data via Natural Language Processing (NLP), Machine Learning (ML), and explainable Machine Learning (xML) techniques. The research aimed at identifying depressive indicators on X (formerly Twitter) and developing interpretable models for depression risk detection. The study’s methodology followed the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework to ensure a systematic approach to data analysis. Data was collected via X’s API and processed using regex-based noise removal, normalisation, tokenisation, and lemmatisation. Symptoms were mapped to DSM-5-TR criteria at the post-level, with user-level MDD risk assessed based on symptom persistence over a two-week period. Risk levels were classified as No Risk, Monitor, and High Risk to facilitate early intervention. Six ML models were trained and tested, while the Synthetic Minority Over-sampling Technique (SMOTE) was applied to mitigate class imbalance. The dataset was partitioned into training and testing sets using an 80:20 split. ML models were evaluated, and the Extreme Gradient Boosting model outperformed the others. Extreme Gradient Boosting achieved an accuracy of 0.979, F1-score of 0.970, and ROC-AUC of 0.996, surpassing benchmark results reported in prior studies. Explainability techniques, such as LIME and tree-based feature importance, enhance model transparency and clinical interpretability. Depressed mood consistently emerged as the highest-weighted predictor across different models. The findings highlight the value of aligning ML models with validated diagnostic frameworks to improve trustworthiness and reduce false positives. Future research can expand beyond text-based analysis by incorporating multimodal features to broaden diagnostic depth. Full article

Background: Truck drivers constitute a high-risk occupational group due to irregular schedules, prolonged sedentary work, fatigue, and limited access to healthcare, contributing to adverse physical and mental health outcomes. Although mobile health (mHealth) tools offer potential to support driver health, sustained engagement remains a persistent challenge. Objectives: This systematic review aimed to identify behavioural, technological, and contextual determinants influencing truck drivers’ compliance, retention, and long-term engagement with digital health interventions. Methods: Following the PRISMA 2020 guidelines, six eligible studies were identified and thematically synthesised across technology acceptance, behaviour change, and persuasive system design perspectives. Results: Across studies, sustained engagement was facilitated by self-monitoring, real-time feedback, goal-setting, coaching support, and simple, flexible system design. In contrast, technological complexity, high interaction demands, limited digital literacy, privacy concerns, misalignment with irregular schedules, and fatigue consistently undermined engagement and retention. Autonomy, trust, and voluntary participation emerged as cross-cutting determinants supporting continued use. Based on the synthesis, an integrative framework was developed to explain how behavioural, technological, and contextual factors interact to shape truck drivers’ compliance, engagement, and retention with mHealth. Despite generally moderate to high study quality, the evidence base remains fragmented and dominated by short-term evaluations. Conclusions: The findings highlight the importance of context-sensitive, user-centred design to support effective digital health interventions in the trucking sector. Full article

Background/Objectives: Given the critical role of vaccinations and venipunctures in disease prevention and health monitoring, it is concerning that over half of children ages 4 to 8 experience some level of needle fear. Higher levels of fear result in longer procedure times, ineffective pain management, distressing memories of needles, and ultimately, healthcare avoidance. Exposure-based therapy with a therapist is recommended for high levels of fear. However, access is limited due to cost, wait times, clinician shortages, system barriers, and social stigma. Thus, there is a need for an evidence-informed, caregiver-directed educational resource for management of moderate to high needle fear in young children. Methods: To address this gap, such a resource was drafted which included a caregiver guide and an illustrated children’s book. The current objective was to gather key user feedback on this initial version of the resource. Participants reported their perceptions of the content, coping strategies, design, organization, and accessibility of the resource through semi-structured interviews and limited quantitative ratings. Participants were children with moderate to high levels of needle fear (N = 6), their caregivers (N = 6), and healthcare professionals (N = 6; including needle providers, child life specialists, and mental health clinicians). Interviews were coded with inductive content analysis; descriptive statistics were calculated for quantitative ratings. Results: Participants reported satisfaction with the e-resource and highlighted strengths (e.g., CARD^TM system, children’s book) and improvement areas (e.g., length, language). Conclusion: Feedback informed revisions to the e-resource in preparation for further evaluation in a follow-up study. Full article

Dementia is a progressive condition that affects cognition, communication, mobility, and independence, posing growing challenges for individuals, caregivers, and healthcare systems. While traditional care models often focus on symptom management in later stages, emerging artificial intelligence (AI) technologies offer new opportunities for proactive and personalized support across the dementia trajectory. This concept paper presents the Assistive Intelligence framework, which aligns AI-powered interventions with each stage of dementia: preclinical, mild, moderate, and severe. These are mapped across four core domains: cognition, mental health, physical health and independence, and caregiver support. We illustrate how AI applications, including generative AI, natural language processing, and sensor-based monitoring, can enable early detection, cognitive stimulation, emotional support, safe daily functioning, and reduced caregiver burden. The paper also addresses critical implementation considerations such as interoperability, usability, and scalability, and examines ethical challenges related to privacy, fairness, and explainability. We propose a research and innovation roadmap to guide the responsible development, validation, and dissemination of AI technologies that are adaptive, inclusive, and centered on individual well-being. By advancing this framework, we aim to promote equitable and person-centered dementia care that evolves with individuals’ changing needs. Full article

Mobile Global Positioning System (GPS) data offer a promising approach to inferring mental health status through behavioural analysis. Whilst previous research has explored location-based behavioural indicators including location clusters, entropy, and variance, persistent GPS measurement errors have compromised data reliability, limiting the practical deployment of smartphone-based digital phenotyping systems. This study develops and validates an algorithmic preprocessing method designed to mitigate inherent GPS measurement limitations in mobile health applications. We conducted comprehensive evaluation through controlled experimental protocols and naturalistic field assessments involving 38 participants over a seven-day period, capturing GPS data across diverse environmental contexts on both Android and iOS platforms. The proposed preprocessing algorithm demonstrated exceptional precision, consistently detecting major activity centres within an average 50-metre margin of error across both platforms. In naturalistic settings, the algorithm yielded robust location detection capabilities, producing spatial patterns that reflected plausible and behaviourally meaningful traits at the individual level. Cross-platform analysis revealed consistent performance regardless of operating system, with no significant differences in accuracy metrics between Android and iOS devices. These findings substantiate the potential of mobile GPS data as a reliable, objective source of behavioural information for mental health monitoring systems, contingent upon implementing sophisticated error-mitigation techniques. The validated algorithm addresses a critical technical barrier to the practical implementation of GPS-based digital phenotyping, enabling the more accurate assessment of mobility-related behavioural markers across diverse mental health conditions. This research contributes to the growing field of mobile health technology by providing a robust algorithmic framework for leveraging smartphone sensing capabilities in healthcare applications. Full article

Background: The integration of artificial intelligence (AI) into mobile health (mHealth) applications has been accelerated by the widespread adoption of smartphones and recent technological advances, particularly in the wake of the COVID-19 pandemic. This experience has expanded the role of AI-powered apps in real-time health monitoring, early detection, and personalized treatment pathways. Aim: This review aims to summarize recent evidence on the use of AI in healthcare-related mobile applications, with a focus on clinical trends, practical implications, and future directions. Methods: Studies were prioritized based on methodological rigor, with systematic reviews forming the core of the analysis. Additional literature was considered to capture emerging trends and applications where a relevant rigorous screening and scoring procedure was applied to ensure methodological quality and relevance. Only studies addressing healthcare applications, rather than computational or computer science frameworks, were included to reflect the journal’s clinical scope. Results and Discussion: Fifty-six secondary studies were analyzed in detail. Thematic synthesis revealed a post-pandemic shift toward applications targeting mental health, chronic care management, and preventive services. Additional screening showed that, despite their increasing use in clinical contexts, few AI-based apps were formally classified as medical devices. This highlights a gap between technological innovation and regulatory oversight. Ethical concerns—including algorithm transparency, clinical responsibility, and data protection—were frequently reported across studies. Conclusions: This review underscores the growing impact of AI in mobile health, while drawing attention to unresolved challenges related to regulation, safety, and clinical accountability. A more robust integration into health systems will require clearer governance frameworks, validation standards, and interdisciplinary dialogue between developers, clinicians, and regulators. Full article

While most prison healthcare litigation seeks individual relief, some cases lead to broader structural reform via consent decrees—court-approved “legally binding performance improvement plans” designed to improve conditions. This study systematically analyzes 121 such settlements from 1970 to 2022 to assess their policy goals and implementation strategies. We identify the substantive areas targeted—general medical care, mental health, dental services, and treatment for specialized conditions like HIV, Hepatitis C, and COVID-19—and trace trends across time and geography. These agreements span 39 states and the federal system, with most states subject to multiple cases. They frequently mandate changes to budgets, staffing, facility infrastructure, training, and patient rights, alongside monitoring for quality improvement. Our findings suggest that consent decrees function not only as judicial remedies but as tools of policy development and institutional reform, shedding light on the role of courts in shaping correctional healthcare delivery. These findings also show how institutional responses to healthcare failures in prisons shape the conditions under which serious harm—and in some cases, preventable death—occur behind bars. Full article