Digital-Focused Approaches in Cancer Patients’ Management in the Post-COVID Era: Challenges and Solutions

Abstract

The COVID-19 pandemic has significantly accelerated the adoption of telemedicine and digital health technologies, revealing their immense potential in managing cancer patients effectively. This article explores the impact of recent technological developments and widened consumer perspectives on personalised healthcare and patient awareness, particularly in oncology. Smartphones and wearable devices have become integral to daily life, promoting healthy lifestyles and supporting cancer patients through remote monitoring and health management. The widespread use of these devices presents an unprecedented opportunity to transform clinical trials and patient care by offering convenient and accessible means of collecting health data continuously and non-invasively. However, to fully harness their potential, it is crucial to establish standardised methods for measuring patient metrics to ensure data reliability and validity. This article also addresses the challenges of integrating these technologies into clinical practice, such as cost, patient and professional reluctance, and technological oversaturation. It emphasises the need for continuous innovation, the development of robust digital infrastructures, and the importance of fostering a supportive environment to integrate these advancements permanently. Ultimately, the convergence of technological innovation and personalised healthcare promises to enhance patient outcomes, improve quality of life, and revolutionise cancer management in the post-COVID era.

1. Introduction

Cancer is a disease that can be defined in many ways, but one could summarise the essence of this pathology through the following definition: a disease caused by unregulated cell proliferation and a tendency of the cells to disseminate in other parts of the body [1]. More recently, due to improvements in the management of cancer, in most high-income countries, the mortality of most types of cancers decreased. Nevertheless, this improvement was not observed in medium- and low-income countries [2]. Regarding this type of disease, patients face psychological burdens and different physical impairments; thus, early diagnosis and effective disease management paired with patient empowerment over their symptoms and behaviours in relationship with the disease may alleviate the suffering and improve the overall survival and quality of life (QoL).

Recent technological developments and expanded consumer perspectives on technology present new opportunities for personalised healthcare and enhanced patient awareness regarding cancers and their bodies. Integrating advanced technological solutions into healthcare can significantly improve individualised treatment plans and empower patients with more knowledge and control over their health outcomes. This shift towards personalised medicine is particularly relevant in oncology, where understanding and monitoring specific patient needs can lead to more effective treatments and better overall prognosis [3,4,5].

The COVID-19 pandemic, as the most recent major medical event, has underscored the critical importance of health maintenance and preventive medicine. Similarly, the pandemic has strongly highlighted how outdated and faulty some traditional approaches are in the face of an overwhelming event that can completely halt even the most well-administered healthcare systems [6,7]. This pandemic has consequently spurred a renewed focus on the significance of proactive health management and the essential role of preventive healthcare practices [8,9].

In this landscape, smartphones and other consumer wearable devices have emerged as integral components of daily life, serving as catalysts for promoting healthy lifestyles. These devices, such as Garmin and Apple Watch, are prevalent among the general population and increasingly adopted by cancer patients. Their integration into everyday routines offers a unique opportunity to motivate and monitor health behaviours, providing continuous support for healthy individuals and those undergoing treatment for cancer [10,11]. The widespread ownership of smartphones and, to a lesser extent, smartwatches among adults facilitates their utilisation in clinical trials [12,13,14]. These devices offer a convenient and accessible means of collecting health data, potentially transforming the landscape of medical research and patient care. However, significant adjustments are necessary to harness their full potential in clinical settings. Establishing accurate, standardised methods for measuring patient metrics via these devices is crucial to ensure that the data collected is reliable and can be regarded as valuable and verifiable medical information. This standardisation process is essential for effectively integrating consumer technology into clinical practice, enhancing patient outcomes and advancing the field of personalised medicine [8].

This paper explores integrating digital health technologies, such as smartphones and wearable devices, in cancer management, particularly in the post-COVID era. We highlighted telemedicine’s accelerated adoption, personalised healthcare benefits, and the necessity for standardised patient metrics. Additionally, we wanted to address the challenges and solutions for permanently incorporating these technologies into clinical practice to enhance patient outcomes and support preventive medicine.

2. Materials and Methods

An electronic search was conducted in May–July 2024 through Medline, Web of Science, Scopus, Embase, Central, Cinahl, and Cochrane Central Registry of Controlled Trials. Following the initial results, we extended the search to similar articles and references mentioned in the retrieved results. There were no limitations regarding the year of publication. Only articles published in English were included in the screening process. The keywords and excluded articles are presented in Figure 1.

3. Results

3.1. Digital Health—Telemedicine and Personal Digital Health

Telemedicine can provide a medium to facilitate the connection between patient and doctor. For example, cancer screening is possible for patients suffering from potentially malignant skin lesions. Teledermatology, for instance, is more efficient than face-to-face interaction when considering time, as patients can be seen on short notice. Although more convenient for both parties, diagnostic accuracy can be lower in this case, as the lesion is seen in a picture or, in the best-case scenario, in a high-quality video. The precision of the diagnostic remains to be improved [15]. Breast cancer is another pathology which can be assessed virtually. Not only screening but also follow-up/surveillance was feasible with the help of telemedicine. A small percentage of patients needed an in-person evaluation when an in-detail physical exam was required. Most cases had benefited from online consultation, thus reducing time-consuming and unnecessary appointments [16].

An essential goal of the medical community is to make telemedicine more attractive for the elders, especially oncological patients. In several studies regarding teleoncology, it has been shown that the majority of people above 65 years who accessed telemedical resources during the COVID-19 pandemic came back very quickly to the traditional ways, such as in-person appointments. Although more affordable, convenient, and accessible, as declared by the patients in several surveys, this approach was not sufficient to withstand the familiarity of the classical medical exam; thus, after the pandemic, many patients returned to personal interactions with the doctor [17] (Figure 2).

Digital biomarkers offer the possibility of measuring biological responses to diverse changes in external factors such as stress and diet over a more extended period of time, with the advantage of highlighting subtle alterations in the normal biological equilibrium. These novel biomarkers are called resilience biomarkers and can be established by digital biomarkers. They can detect early signs of disbalances in the normal regulatory processes and characterise the spectrum of healthy and unhealthy.

Personal digital health is an innovative way of using different wearables, mobile phones, and applications to track one’s health in a continuous, non-invasive, and social context. A few of the health indicators that digital tools can assess are heart rate, oxygen saturation, sleep pattern, and skin temperature. Monitoring health status may give insights into the body’s ability to be resilient in the face of daily stressors, diet, and exercise, as well as resilience that diminishes with age and disease when compensatory mechanisms are impaired. Conventional health assessment instruments such as blood sample analysis, imaging, and doctor’s appointments are not meant to evaluate health status continuously and non-invasively; they only offer a view of one’s health in an episodic time frame [4].

The oncological field may benefit from the impact wearable devices have on reporting symptoms and vital parameters in an objective approach that may increase the quality of life in the long run. The use of wearables in reporting medical status has advantages: the ability to track symptoms passively, continuously, and remotely and communicate with medical professionals through apps, relatively low costs, daily medication reminders, and community support [18]. Wearables monitor three main parameters and can help patients and physicians track symptoms and adverse effects: physical activity, sleep, and heart rate. Physical activity is one of the health metrics that can shed light on the severity of future chemotherapy side effects and overall well-being (both emotional and physical) [18,19,20]. It can be measured as steps or calories per day or hour. Different apps use this metric to generate graphs that keep up with patients’ evolution and reactions after medication and exercise. This feature can be helpful to doctors, as it facilitates history taking and adjustments to medication and behaviours.

Survival, as well as subsequent unfavourable outcomes, are dependent on physical activity, which is measured as step counts. Higher step counts were correlated with reduced risk of developing complications, while lower step counts negatively impacted survival. Physical and heart rate monitoring can indicate if patients are experiencing side effects from chemotherapy. Some pharmacological agents can have a detrimental effect on the heart, which results in bradycardia, arrhythmias (most commonly atrial fibrillation), and life-threatening tachycardias such as torsades de pointes. Wearables can detect those conditions by measuring heart rate and providing a single-lead electrocardiogram (ECG).

All the health parameters measured by wearables can constitute a digital phenotype that encompasses not only the patient’s vitals (heart rate, oxygen saturation) but also their health risks and shared risks with their family, friends, and neighbourhood. New wearables can also measure UV exposure (significant for patients with a history of dermatological cancers such as melanoma) and even aid in detecting glioblastoma (GBM) by wearing headbands, all of which have the potential to become part of preventive medicine. Some of the consumer devices that have the potential to aid oncological patients during and after their treatments can be included in clinical trials to outperform current use: smartwatches, smartphones, wristbands, jewellery, and headbands. Smartphones contain sensors capable of giving information about step counts, location, screen time, social interaction, and patient environment: accelerometer, gyroscope, and magnetometer. Smartwatches can measure sleep patterns, skin temperature, oxygen saturation, and heart rate, and the newer models can generate single-lead ECGs [18].

The behavioural pattern from analysing the individual’s digital phenotype can help identify patients at risk of developing complications during or after treatments (surgery, chemotherapy, and radiotherapy). Many studies on oncological patients (lung, gastrointestinal, breast, gynaecologic cancers) using solely smartphone data or wearable devices data or a combination of the two proved that by measuring certain biomarkers or by establishing different behavioural patterns, patients who experience worsening symptoms could be identified (1 patient suffering from gynaecologic cancer who experienced severe nausea and vomiting and whose symptoms were managed remotely) and treated faster. Decreasing daily step counts could alert physicians if patients are experiencing chemotherapy toxicity, and, as a result, earlier medical management could be implemented [8]. Decreased levels of daily step count and overall activity could also be linked to a decline in QoL, performance status, worsening health over a more extended period of time, an increase in patient-reported symptoms (fatigue, pain, diarrhoea) and an increased risk of hospitalisation, postoperative complications, and acute health events that require emergency department visits [19]. Predictors for emergency department visits are an increased resting heart rate, decreased heart rate variability, and increased step speed. In a study consisting of 37 patients with advanced cancer, an increase in daily step counts reduced the odds of inpatient medical care and mortality. Wearable devices may help patients benefit from personalised physical activity support and changes in behaviour to sustain an active lifestyle that is nonetheless linked to an improvement in QoL. The mental health of oncological patients can also be characterised by a few parameters: locations that suggest that more time spent at home or amongst family and friends can result in less anxiety and depression, while the opposite was true for greater time spent in medical facilities. Parameters such as speed of movement and screen unlocks can indicate a digital phenotype related to depression, anxiety, and concentration issues. As oncologic therapies require good adherence but are hard to tolerate and can induce severe side effects and, thus, aggravate the health status, an objective assessment of performance status before and during the treatments is needed. Smartphones and wearable devices may aid patients, caregivers, and clinicians alike in rapidly and effectively evaluating if there are any health alterations and support timely and efficient care by triggering notifications when certain limits have been exceeded [21] (Figure 3).

Biofluids such as sweat, tears, and saliva contain multiple metabolites and biomarkers that can be detected with new portable consumer devices in a continuous, passive, and non-invasive manner [18,19,20]. The three biofluids mentioned above can be monitored via wristbands, patches and textiles (sweat), contact lenses (tears), tooth enamel, mouthguard, and pacifier (saliva). They can offer information about glucose levels, electrolytes, antibodies, and enzymes. All consumer devices use sensors to analyse the biomarkers; some are potentiometric, amperometric, colourimetric, and fluorometric sensors. Although wearables can provide essential information in the clinical setting, challenges must be overcome to bring about large-scale usage in the medical field.

3.2. Microneedle Technology

Since advances in mobile health (m-health) and communication are helping physicians and patients better supervise health status, evaluate symptoms, and offer timely assistance in case of deterioration, novel methods for early diagnosis and treatment administration are much needed for patients suffering from CDs, especially cancers. Although microneedle (MN) technology has been around for decades, only recent advances in their manufacturing permitted broad and scalable research [22]. Gold standards for diagnosis, monitoring, and treatment administration are PCR, ELISA, mass spectrometry, and hypodermic needles [23]. They offer high efficiency in detecting disease biomarkers but also present disadvantages, mostly related to their complexity, costs, inability to provide immediate results and psychological effects on patients.

Early diagnosis and monitoring are essential for the prognosis and treatment of cancer patients, and MNs can be an aiding tool for these challenges. The biomarkers that MNs can detect are carcinoembryonic antigen (CEA), vascular endothelial growth factor (VEGF), nitric oxide (NO), and exosomes (containing nucleic acids and proteins derived from cells) [22,23,24]. CEA in breast cancer was detected with the help of Ag₃PO₄-coated MNs through a colourimetric method. Cancer progression can be assessed by monitoring NO levels, as it inhibits tumour growth. Poly (3,4-ethylenedioxythiophene) (PEDOT)-coated MNs functionalised with hemin molecules were used to monitor NO in colon cancer tissue. VEGF was detected by functionalised MNs using peptide aptamers. Hollow MNs were used to isolate exosomes from ISF, and the exosomes were later visualised with electron microscopes [25,26].

Analysing interstitial fluid components from dermal and subcutaneous tissues can help diagnose and prognose cancer. This identifies medicines, metabolites, biomarkers, and analytes. Cancer patients can avoid blood extractions and sharp needles with percutaneous interstitial fluid extraction. Compared to fast blood extraction, microneedles are convenient, efficient, secure, and economical for extracting this fluid, but their use in cancer diagnostics is still in its infancy due to the long waiting times, which can range from ten minutes to several hours. Only small sample volumes are available. For accurate and long-lasting cancer treatment, microneedles are ideal for administering chemotherapy or radiation directly to specified locations with minimal invasiveness. This strategy considerably improves patient comfort, especially over multiple therapy cycles. New research suggests microneedle patches can be used in combination therapies to boost treatment efficacy by synergising with other medications or therapies. Microneedles could replace hypodermic injections for cervical cancer immunisation. This technique controls local immunity more effectively at lower dosages, circumvents in vivo barriers, and may minimise systemic toxicity or immunological reactions. Microneedles have been studied for administering adjuvants, antigens, antitumoral gene therapies, and antibodies to expand delivery systems [27,28,29].

Microneedles combine minimally invasive methods with enhanced data collecting, making them a key digital health tool. Their small, precise structures administer drugs painlessly and efficiently, which is very useful for cancer patients who need daily therapy. Beyond drug administration, microneedles can be coupled with biosensors to continually monitor vital indicators from interstitial fluid and send real-time data to healthcare practitioners via digital platforms [30,31]. Microneedles are at the forefront of personalised medicine, using patient-specific data to adapt therapies and enhance outcomes. Digital health frameworks with microneedles solve remote-patient-monitoring and chronic-illness-management issues. Microneedles enable continuous, non-invasive monitoring to detect physiological changes that may indicate disease progression or adverse effects of treatment, allowing for prompt interventions. Advanced algorithms can combine and analyse microneedle-based data to better understand patient health trends over time. Microneedles will improve healthcare precision, accessibility, and efficacy, especially in cancer management, as digital health evolves [32].

Many clinical trials assessing MN array platforms in detecting biomarkers, diagnosis, and disease monitoring are ongoing, and new opportunities for future improvements in the medical management of cancer are proposed.

3.3. Artificial Intelligence—Using Data to Improve Cancer Care

As digital technology has been developing rapidly, a transition to the digital storage of data has been made. Moreover, with time, storage spaces expanded and became more complex, and advances in processing power made it feasible for artificial intelligence to be implemented in medical care.

AI is a revolutionary technology that aims to mimic, improve, or transcend human intellect by creating computers that can perform tasks that need human thought. Automation that can adapt to new circumstances, discover complicated patterns, and draw general inferences from large datasets can improve learning, reasoning, problem-solving, and decision-making. AI’s ability to make accurate interpretations, alone or with human help, is being used in numerous fields, including healthcare, where it could revolutionise diagnosis, treatment, and patient care. Machine learning (ML) is a fundamental topic of advanced AI that creates algorithms that learn from data. Algorithm accuracy and prediction power increase with data quantity and quality. ML models improve their outputs by finding subtle patterns and making exact predictions when they are exposed to additional datasets. ML is crucial in cancer, where large datasets from medical imaging, genetics, and patient records can be used to predict disease progression or modify treatments. Deep learning (DL) is a more advanced area of AI that uses neural networks to mimic the human brain. These networks use layers of interconnected “neurons”, or nodes, to examine raw data and gain insights. DL can process massive amounts of unstructured data, including photos, text, and audio, without feature extraction, making it powerful. DL models can autonomously recognise patterns and correlations in data that humans may miss, making them useful in medical imaging to detect minor irregularities that may indicate early cancer or other illnesses. In digital health platforms, AI, ML, and DL can improve clinical decision-making, workflows, and patient outcomes by providing more accurate, efficient, and personalised healthcare solutions [33].

AI, especially medical image processing, has transformed cancer diagnosis. This field of AI extracts clinically useful information from medical images to improve diagnosis and therapy. Medical image computing analyses complicated visual data using numerous methods to detect and track cancer. Image segmentation, which divides the image into organ and tissue segments, is a common method. Isolating malignancies from healthy tissue is crucial for accurate diagnosis and tailored treatment planning [34]. To simplify understanding, picture registration aligns several images from various times or modalities. This is crucial for following cancer progression or comparing CT and MRI scans to obtain a complete picture of the patient’s status. Clinicians can detect subtle tumour size, shape, and location changes by correctly aligning these images, resulting in faster and more accurate diagnosis. AI also improves picture acquisition, making it more efficient and personalised for cancer patients. For instance, AI systems can balance CT scan doses to maximise picture quality and minimise radiation exposure. This feature is useful for cancer recurrence monitoring patients needing frequent imaging. AI can reduce MRI scan times, which can be uncomfortable for patients. AI optimises scan processes to speed up and simplify imaging while maintaining excellent quality [35]. Convolutional neural networks (CNNs) are also changing MRI contrast agent management. For nephrotoxic chemotherapy patients, contrast chemicals must be carefully managed to avoid kidney injury. CNNs can process raw imaging data in real-time and precisely change contrast levels to provide diagnostic information without sacrificing patient safety. This enhances imaging quality and minimises contrast agent hazards, making cancer diagnosis safer and more efficient for susceptible patients [36].

Breast cancer screening uses mammography, prostate cancer screening uses MRI, and lung cancer screening uses low-dose CT scans. Early detection is key for patient outcomes and survival; hence, these imaging modalities are essential. Despite its broad use, AI in cancer screening is still in its infancy. AI has shown great promise in improving diagnosis accuracy, particularly in mammography, but its full potential in population-wide screening has yet to be achieved. Many studies have used AI to read mammograms to detect breast cancer early by spotting patterns that radiologists may miss. ML techniques in these AI systems can analyse mammographic pictures to detect microcalcifications and masses faster and more accurately than previous methods [37,38,39].

Larsen et al.’s population-based-screening study showed that AI can detect breast cancer through mammography. The study found affordable AI systems could improve screening approaches, especially in areas without professional radiologists. These AI-driven technologies can swiftly evaluate vast amounts of images to help radiologists make more accurate diagnoses. AI in the screening process may reduce healthcare workers’ burden, reduce human error, and detect more breast cancer cases at an earlier, more treatable stage [38].

Natural Language Processing (NLP) is another promising AI cancer treatment technology. NLP is an area of artificial intelligence that helps computers understand, interpret, and generate meaningful and usable human language. NLP can evaluate massive amounts of unstructured data in medical notes, EHRs, and patient feedback to improve clinical decision-making in cancer care. NLP is used in cancer to find patterns and trends in complex medical records that healthcare providers may miss. NLP algorithms can analyse narrative medical notes to extract patient history, symptoms, and treatment reactions to forecast the best treatments. This is especially useful when patients have extensive medical histories or several therapy routes, and picking the best one is crucial to their results [40].

A study conducted by Kehl et al. employed an NLP model to evaluate data from 2500 patients diagnosed with non-small cell lung cancer (NSCLC), which is the predominant form of lung cancer, representing around 85% of all lung cancer cases. A complete dataset of unstructured clinical notes was utilised in the study, encompassing complete recordings of patient contacts, oncologists’ observations, and documented events, such as symptom progression, treatment responses, and adverse effects. The NLP model examined these narrative data points to detect patterns and connections that may not be readily evident through conventional data analysis approaches. Significantly, the model accurately forecasted mortality in these patients by analysing the observed improvements and deteriorating events as reported by oncologists over a period of time. The shown predictive capacity of NLP underscores its potential to improve clinical decision-making in the oncology field by offering early indications of patients who are more likely to have unfavourable outcomes [41].

Integrating ML into the current digital cancer care systems and procedures will be fairly difficult. To optimise these models’ effectiveness and impact, ensuring they can be easily incorporated into decision support systems, clinical processes, and other healthcare services is crucial. Cooperation between data/ML engineers, medical professionals, patients, family caregivers, and other participants is needed to construct and carry out efficient solutions considering the particular requirements and limitations of cancer treatment.

3.4. Clinical Trials

Clinical trials are not a simple affair, with enormous resources required for enrolment, treatment, monitoring, and data acquisition and interpretation. One of the biggest hurdles in clinical trials, which strongly hinders both patient enrolment and the statistical value of the data observed, is patient access. It must be mentioned that the notion of ‘access’ is a two-sided issue, as it is composed of both patient and institutional recruitment barriers that are reflected in this study’s design. For example, it is well-known that most clinical studies are conducted in large, urban academic centres. One solution to this problem is decentralisation, enabling remote data sampling and collection from smaller local hospitals and clinics or even from the patient’s home, making it much simpler for health professionals, patients, and caregivers [42].

Fortunately, most of the technology for remotely caring for patients and conducting clinical trials was present for years, but simple legislative or plain lack of trust towards more technologically orientated approaches stunted its adoption. No one could have predicted that the incentive needed to expedite this measure would come from the following unfortunate events. Despite all the detrimental effects that the COVID-19 pandemic wrought upon the world of oncology, it has provided a much-needed technical boost [43].

The COVID-19 pandemic has posed a significant threat to non-viral clinical trials and research better to understand major global health emergencies, such as oncological diseases. The completion of many clinical trials under these difficult circumstances is mainly due to the simplicity, low prices, and ubiquitous nature of the new personal devices and the inspiring adaptability of researchers, patients, and regulators who immediately saw the potential. A significant feature of newer technologies is the remote assessment of patients, a practice encouraged by the FDA guidelines published in March 2020 [44]. These efforts have led study coordinators to include virtual check-ups in the form of telemedicine visits to analyse patients’ status. Today, remote surveillance is possible through home sensors (pulse oximeters, for example). Before the COVID-19 pandemic, the potential for using this remote sensor type was mentioned in previous FDA guidelines, but many trial coordinators were concerned that the benefits could never outweigh the risks and possible inequalities. Remote surveillance also helped trial monitors keep contact and evaluate progress in individual research sites when travelling was heavily restricted [45].

3.5. Limitations and Challenges

Using digitally focused approaches in managing cancer patients has significantly enhanced patient care. However, substantial technical and conceptual challenges must be addressed to fully optimise the potential of these technologies.

The intricate nature of data produced by these innovative technologies, such as wearable devices, smartphone applications, and telemedicine platforms, poses considerable difficulties in its interpretation. The data sources frequently generate substantial amounts of unstructured and diverse information, encompassing physiological measurements, behavioural data, and self-reported patient results. The difficulty resides not only in the large quantity but also in the data’s diversity and consistency. Ensuring precise data interpretation relies on the capacity to standardise measurements across various devices and platforms. Now, there is a dearth of widely acknowledged criteria for data gathering in digital health, resulting in discrepancies in the interpretation and application of data in clinical practice. Physiological measurements such as heart rate or oxygen saturation might exhibit considerable variation in accuracy across different devices, resulting in possible misinterpretation of a patient’s health [46,47,48].

Another notable constraint is the excessive dependence on self-reported data, which is susceptible to subjectivity and imprecision. Suboptimal reporting of symptoms by patients or misinterpretation of their own health data might result in inconsistencies in the information given to healthcare professionals. Furthermore, existing digital health techniques typically lack the capacity to adjust to individual patients’ specific requirements and preferences, leading to a standardised approach that may not be appropriate for all patients [49,50].

Both the design and functionality of numerous digital health devices pose significant challenges. A significant number of wearable gadgets, for instance, lack the explicit consideration of the unique requirements of cancer patients. These patients may encounter physical constraints, such as decreased movement or skin sensitivity, making using specific devices uncomfortable or unfeasible.

Battery longevity and data storage capacity are additional technical constraints that can restrict the efficiency of these devices. Requiring frequent recharging or data synchronisation might be burdensome for patients, especially those who are advanced in age or suffering from substantial weariness caused by disease. Furthermore, the robustness of these devices is a consideration, particularly for patients receiving intensive therapies that may need frequent hospitalisations or physical strain [51].

Furthermore, the security of the gathered data is a significant worry and a big possible constraint. Protected health information is highly sensitive, and any violation of confidentiality can result in serious repercussions for patients. An essential obstacle is guaranteeing the encryption and secure storage of data, both during its transmission and when it is not in use. Strong security measures are necessary to deter unwanted access to or manipulation of the data effectively. Nevertheless, engineering such security protocols can be intricate and expensive, especially for smaller healthcare providers or settings with limited resources [52].

Commercialising microneedles encounters many substantial obstacles, mostly stemming from technological, regulatory, and market-related impediments. Production of microneedles on a large scale while ensuring accuracy and quality is technically challenging, necessitating sophisticated and expensive manufacturing methodology. The regulatory authorisation procedures for microneedles are intricate due to their status as a recently developed technology, which necessitates thorough testing to guarantee both safety and effectiveness, especially considering their intrusive profile. Furthermore, achieving market acceptance is an additional challenge, as healthcare practitioners and patients may harbour doubts about embracing a novel technology that fundamentally deviates from conventional medication delivery approaches. Manufacturing costs add complexity to the process of commercialising microneedles, as their economic feasibility relies on their capacity to rival well-established, more affordable methodologies. Furthermore, it is crucial but difficult to negotiate the intricate intellectual property environment and guarantee fair and equal access to this technology. Notwithstanding their potential to revolutionise medicine administration and immunisation, these problems combined impede the broad use of microneedles [53,54,55].

4. Discussions

The integration of microneedle technology, wearable electronics, and AI signifies a substantial transformation in contemporary healthcare, providing innovative avenues for identifying, treating, and monitoring diseases. When incorporated into wearable devices, microneedles, renowned for their minimally invasive characteristics, become a viable instrument for drug delivery, biomarker detection, and patient monitoring. This approach can transform personalised medicine by offering patients immediate, accurate, and individualised insights. This paper underscores the requirement for ongoing innovation, the establishment of solid digital infrastructures, and the need to create a conducive atmosphere for the long-term incorporation of these advancements. In the post-COVID era, combining technical advancement and personalised healthcare can significantly optimise patient outcomes, enhance quality of life, and transform cancer management.

Our research focus in digital health is telemedicine and personal digital health tools, a rapidly changing subject. We also examine how digital health technologies transform patient care through remote monitoring, virtual consultations, and data collection. Telemedicine has dramatically improved healthcare availability, allowing patients to receive medical supervision, diagnosis, and treatment from home, reducing the need for in-person sessions. Consumer-oriented digital health technology like wearable gadgets and mobile health apps empower people to actively manage their health by providing rapid and precise health information. We have also highlighted the introduction of AI into digital health systems to improve the ability to analyse large amounts of health data, predict illness progression, and customise treatment techniques. AI-based telemedicine platforms can enhance diagnostic accuracy, patient care, and decision-making. Several other papers have discussed this topic, as well. Ji et al. concentrate on wearable sweat biosensors designed to non-invasively monitor biomarkers in sweat, providing a convenient and continuous means of tracking an individual’s health status [56]. These sensors can detect analytes, such as electrolytes, metabolites, and proteins, offering real-time insights into hydration levels, stress, and overall metabolic health. This approach aligns with the broader theme of personalised health discussed in our paper, where continuous and remote monitoring is critical for personalised care. However, while Ji et al. focus on using sweat as a biomarker-rich fluid, our work explores a broader range of digital health tools, including telemedicine platforms and wearable devices that may or may not be focused on biomarker analysis [56]. Likewise, Taha et al. and Muller et al. had a similar analysis of biosensors but with a significant focus on monitoring SARS-CoV-2 patients [57,58]. However, we chose a more encompassing approach without dwelling as much into technical details as the previous authors while building a more nuanced and diverse theme that integrates these biosensors into the more prominent theme of telemedicine.

Our study emphasises the crucial function of microneedles in digital health, namely in the painless administration of medication and the immediate identification of biomarkers. Microneedle technology provides a very non-invasive substitute for conventional needles and may be seamlessly included in wearable devices, allowing for uninterrupted monitoring and therapy. A detailed overview of functional microneedles combined with wearable electronics is presented by other authors, such as Zhang et al. or Ganeson et al., with a focus on their potential for a wide range of applications, including continuous glucose monitoring, medication delivery, and real-time health tracking [59,60]. While our work emphasises the patient-centric benefits of microneedles, Zhang et al. delve deeper into the engineering aspects, providing insights into how microneedles can be optimised for broader and more sophisticated healthcare applications [59] and Ganeson et al. highlights the role of microneedles in cancer treatment [60]. A further dimension to this debate is introduced by a recent study conducted by Wang et al. [61]. Soft robotics, which possess intrinsic flexibility and biocompatibility, when integrated with microneedles, provide significant benefits. These devices can conform to the geometric features of the body, so offering a more ergonomic and flexible interface for the administration of drugs or biosensing. The analysis supports our results, indicating that incorporating microneedles into soft robotic systems can improve the accuracy and efficiency of wearable health devices, especially in administering medications or managing health problems [61]. When comparing our results with previous research, we offer a more nuanced and holistic comprehension of how these technologies might enhance one another in practical situations.

AI integration throughout patient care stages has improved cancer diagnosis and treatment [62]. AI has benefited healthcare through digital data storage and exponential computing power expansion. ML and DL are transforming cancer care by analysing vast datasets, discovering complicated patterns, and improving diagnosis accuracy. These tools can detect minor differences in medical pictures, forecast patient outcomes, and recommend individualised treatment strategies based on patient data [63].

To comprehend AI’s involvement in cancer care, we looked at how these advanced technologies fit into the healthcare system. We analysed AI’s ability to process and analyse large datasets to increase diagnosis accuracy across multiple jobs. We also investigated how AI systems can improve medical imaging picture interpretation, which has shown promise in early cancer detection. We also examined how AI and ML affect clinical trials. These technologies could improve clinical trial enrolment, monitoring, and patient access to investigational medicines [42,43,44]. AI can find suitable patients faster by searching EHRs and connecting patients to trials based on their medical histories and genetic profiles [40]. The trial process is accelerated, and the patient group is more diverse and representative, addressing longstanding clinical research inequity [45].

Our research highlights AI’s potential to universalise cutting-edge cancer treatments and alleviate healthcare disparities. Integrating AI into cancer care from diagnosis to treatment and beyond shows how these technologies can simplify processes, enhance results, and create fairer healthcare systems.

5. Conclusions

Digital cancer patient management technologies could transform oncology care, especially after the COVID-19 epidemic. Telemedicine, wearable tech, and AI are changing cancer treatment and monitoring. Personalised care and constant monitoring improve diagnosis, treatment, and patient outcomes.

Microneedle technology simplifies drug administration and biomarker detection. Together with AI, these technologies improve cancer treatment by making more accurate and timely clinical judgments. Technical, legislative, and ethical restrictions must be addressed, and equal access to advanced instruments must be ensured to use these technologies appropriately.

This report underlines the need for a holistic digital cancer research approach. Understanding a healthcare system’s parts and interconnections helps explain patient care. Studying these synergies can improve cancer treatment and produce more effective, accessible, and patient-focused healthcare solutions.