Abstract

Healthcare is increasingly shifting from episodic, reactive care towards continuous, preventive and personalised monitoring. This paper reviews the role of wearable technologies in supporting this transition, with particular attention to continuous health monitoring and early disease detection. It examines consumer- and medical-grade wearables, the physiological and behavioural data they collect, and their potential benefits for remote monitoring, personalised care and patient engagement. Evidence from cardiovascular, neurological and musculoskeletal applications suggests that wearables are already useful for tracking symptoms, recovery and changes in physiological function outside clinical settings. However, their ability to detect disease before conventional diagnosis remains less established. Important limitations include measurement accuracy, clinical validation, adherence, privacy and unequal performance across populations. Integration with artificial intelligence, machine learning and multimodal sensing may improve pattern recognition and predictive monitoring, although unreliable or biased data can reduce clinical value. Overall, wearable technologies show considerable potential to strengthen continuous and personalised healthcare, but wider clinical adoption will depend on stronger validation, secure integration and appropriate use as decision-support tools rather than replacements for professional judgement.

1. Introduction

1.1 The Changing Healthcare Model

The contemporary healthcare landscape is undergoing a fundamental paradigm shift, moving away from a traditionally reactive and episodic model towards one that is preventive, personalised and continuously engaged with the patient’s daily life. For decades, healthcare delivery has been predicated on infrequent clinical encounters, where a snapshot of physiological parameters is captured and interpreted in isolation. This approach, while valuable for diagnosing acute conditions, is inherently ill-suited to detect the subtle, progressive or intermittent changes that often precede chronic disease or signal a decline in wellness. The measurements taken during a brief consultation are merely a point in time, potentially missing clinically significant fluctuations that occur during the routines of work, rest and sleep, and failing to account for the dynamic interplay of lifestyle, environment and biology (Topol, 2019).

The inherent limitation of periodic clinical measurements lies in their inability to capture the full spectrum of an individual’s health status as it unfolds in real-world settings. A single blood pressure reading or a momentary glucose level provides a sparse dataset, offering little insight into trends, variability or the body’s response to daily stressors and activities. Consequently, a reliance on such infrequent data points can lead to delayed interventions, misdiagnosis or a failure to recognise the early, sub-clinical signs of disease. This episodic model is fundamentally reactive, often waiting for symptoms to manifest before action is taken rather than pre-empting pathology. Therefore, there is a compelling need for a more granular and continuous stream of health data that can paint a holistic picture of an individual’s physiological state over time, enabling the identification of deviations from their unique baseline and facilitating timely, personalised interventions (Smuck et al., 2021).

This growing demand for continuous health data creates a pivotal role for wearable technologies. These devices, evolving from simple fitness trackers, offer the unprecedented capability to monitor physiological signals seamlessly and non-invasively throughout the day. Wearable technologies are likely to move beyond monitoring a small number of measurements and towards collecting several types of physiological and biochemical data simultaneously. Kulkarni et al. (2024) identify developments such as multiplexed biosensing, microfluidic sampling and flexible wearable sensors as important directions for continuous and minimally invasive health monitoring. These advances could allow future devices to monitor a wider range of biomarkers and provide more detailed information about an individual’s health. By bridging the gap between the clinic and daily life, wearables hold the potential to transform healthcare from a system that treats illness to one that actively cultivates and preserves wellbeing, making the vision of truly personalised and preventive medicine an attainable reality.

1.2 Wearable Technologies in Healthcare

Wearable technologies are defined as devices commonly worn as accessories that can collect data about the wearer (Serhat et al., 2018). They are most easily defined as two main categories: medical-grade and consumer-grade (Edelmann, 2025). Consumer grade tech predominantly comes in the form of smartwatches, rings or wrist-bands. While they are marketed for individual use, they both enable users to access personal data easily and allow for mass collection of data for public health studies. Consumer grade tech can assess an ever-growing number of variables. Accelerometry evaluates acceleration forces mainly in order to measure exercise and body position. Photoplethysmography (PPG) detects small variations in blood volume using infra-red in order to gauge, among others, heart-rate, respiratory rate and blood pressure. Finally, electrocardiography (ECG) sensors provide information relating to heart rate and heart rhythm in order to detect abnormalities (Vijayan et al., 2021). These are all indicators of a multitude of diseases and disorders, from simply getting bad sleep to a seizure warning.

On the other hand, a wearable can only qualify as medical grade if it can provide data with “clinical accuracy, regulatory compliance and real-world reliability” (Seitz, 2025). The data is often used by medical professionals to support decision making and must be able to provide consistently accurate results through continuous use in demanding environments (Stuart et al., 2024). This is why they require rigorous government testing and are often aimed at a specific disease (Devine, Schwartz & Hursh, 2022). They can be used to treat or detect a number of medical cases: in cardiovascular disease, through devices with ECG and arrhythmia detection capabilities, to help prevent strokes; in respiratory conditions, measuring oxygen saturation (SpO₂), respiratory rate and airflow; and in gastrointestinal conditions by measuring digestion and gut motility.

1.3 Benefits and Opportunities of Wearable Technology

Wearable technology creates opportunities for improved healthcare through continuous, real-time monitoring, although its value depends on how effectively the data collected can be interpreted and integrated into clinical care. Unlike periodic measurements obtained during clinical visits, wearable technologies collect data continuously, which generates a more in-depth picture of a patient’s health over time (Jafleh et al., 2024). This constant provision of data, in place of snapshots, enables a range of benefits discussed in this section; earlier detection, remote monitoring and personalised care all depend on a steady stream of data rather than isolated interpretations weeks or months apart.

Earlier identification of abnormalities and remote patient monitoring are an outcome of the continuous information gathered from wearable technology. In patients with chronic obstructive pulmonary disease (COPD), Hawthorne et al. (2022) recorded significant changes in heart rate and respiratory rate up to three days before exacerbations, suggesting that continuous monitoring may provide earlier indicators of physiological deterioration. However, as the study was proof-of-concept, further research in larger and more diverse populations is needed to establish whether these findings can be generalised to routine clinical practice. The value of this finding depends on whether healthcare systems can act on such early signals quickly enough during routine care. This information also enables remote patient monitoring, which can support patient engagement and reduce reliance on in-person visits. Mehta et al. (2020), in a randomised trial of 242 patients recovering from hip or knee arthroplasty, found significantly fewer rehospitalisations among those receiving care with help of wearables combined with remote goal-setting and clinical contact, compared to normal care without wearable technology.

Patient engagement and improved disease management are another benefit of wearables. Wearables can support better long-term management of chronic conditions by keeping patients actively involved in their own care. Kamei et al. (2022), in a systematic review of wearable-supported chronic disease management, found improved adherence and outcomes of COPD, diabetes and cardiac disease when wearable use was paired with structured support such as feedback and goal-setting. Together with Mehta et al. (2020), this suggests wearables can improve how chronic conditions are managed day to day, but only if clinical guidance is paired with this information, rather than left to function on its own. 

The data provided by wearables can also help with more personalised care. Babu et al. (2024) described how wearable-based glucose monitoring can reveal individual “glucotypes”, highly personal patterns that could help clinicians design more specific interventions based on a patient’s own physiological needs and norms rather than applying the same recommendations to everyone. This illustrates a broader advantage of continuous monitoring, as longitudinal wearable data allows changes to be interpreted relative to an individual’s typical physiological patterns rather than solely against population-level thresholds. This may support more personalised clinical decisions as an individual’s physiological patterns change over time. However, the usefulness of this approach depends on the accuracy and consistency of wearable measurements and on these individual patterns being interpreted alongside appropriate clinical information.

Taken together, the evidence indicates that wearable technologies can provide meaningful benefits when built on a foundation of continuous data and paired with clinical integration.

1.4 Challenges and Limitations of Wearable Technology

The clinical potential of wearable technologies is limited by trade-offs between measurement accuracy and consumer requirements such as battery life, device size and usability, often dismissing excellence for consumer sustenance (Roos et al., 2023). Therefore, a patient’s data often is not as reliable. Additionally, the limited validation of commercially available devices raises concerns about whether measurements generated by some wearables are sufficiently reliable for health-related decision-making. To illustrate, Giurgiu et al. (2025) asserted that 193 wearables were included only once in a validation process out of 396.

Through continuous monitoring, wearable devices collect a great deal of sensitive information, increasing the consequences of unauthorised access and the potential for data to be divulged or traced (Mone & Fayazullaeva, 2023). Silva-Trujillo et al. (2023) argued that while there are numerous ways to reduce these threats, the ceaseless advancement in wearables also raises some obstacles to countermeasuring these liabilities. This introduces distrust in consumers and, without fundamental safety standards, could lead to the public’s rejection of these devices.

Another major challenge for wearable sensors comes down to the patient’s diversity or constitution. Some studies suggest that darker skin colour absorbs greater amounts of the green LED lights used by wearable sensors and therefore limits their penetration into the skin and consequently results in a less adequate signal (Koerber et al., 2023). However, Bent et al. (2020) reached the conclusion that there are no significant statistical differences in heart rate or heart rate variability (HRV) accuracy across skin tones. Hence, data remains inconclusive, and further research is merited. This is while excluding body size limitations. For instance, body fat increases skin thickness and significantly alters blood flow and oxygen saturation. This influences the optical qualities of the dermis and the range at which light traverses through the skin, which impacts the scope and accuracy of the sensor (Fine et al., 2021). If optical sensors systematically perform less accurately for particular populations, wearable technologies could potentially reproduce or widen existing inequalities when used for continuous monitoring or clinical decision-making.

Continuous monitoring depends on continuous or regular device use; therefore, poor adherence may create incomplete datasets that reduce the reliability of conclusions about a patient’s health. Fowe et al. (2023) suggest that using wearables with adherence may be challenging for older adults, particularly when faced with fatigue or a lack of motivation. There is a probability that users might hesitate to acquire wearables due to their technical demands or obtrusiveness, especially the elderly.

1.5 Integration of Wearable Technologies with Other Technologies

Wearable devices increasingly function as data-generating components within a wider digital healthcare ecosystem rather than as independent technologies. Physiological information collected continuously by wearables can be transmitted to smartphones, cloud platforms and clinical systems, allowing remote monitoring and potentially supporting treatment decisions (Jafleh et al., 2024). However, integration is challenging because devices and healthcare platforms may use incompatible data formats and standards. Abedian et al. (2025) demonstrate that wearable data can be integrated using the Fast Healthcare Interoperability Resources (FHIR) standard, although technical and regulatory barriers remain. This matters clinically because continuous monitoring has limited value if the data cannot be transferred into systems where clinicians can interpret and use it.

Artificial intelligence (AI) and machine learning (ML) are especially important because continuous monitoring produces quantities of data that would be difficult to interpret manually. Shajari et al. (2023) explain that AI-enabled wearables can support real-time data acquisition and processing, while Olyanasab and Annabestani (2024) show how ML can identify physiological patterns linked to prediction, early detection and personalised healthcare. Taken together, these studies suggest that the main value of combining AI with wearables lies in converting continuous measurements into clinically meaningful patterns rather than simply collecting more data.

Jafleh et al. (2024) provide an example of this potential through a machine-learning system that used wearable heart-rate data to predict thyrotoxicosis, achieving 86.14% sensitivity and 85.92% specificity. Although promising, these figures also indicate the possibility of false-positive and false-negative predictions. Such systems may therefore be more appropriate for supporting clinical assessment than independently determining diagnosis.

Integration can also amplify existing limitations. Inaccurate or motion-affected sensor measurements may become inputs for predictive algorithms, meaning that errors at the sensing stage can influence later AI outputs (Jafleh et al., 2024; Shajari et al., 2023). Privacy concerns also increase when sensitive information moves through several connected systems, such as a wearable, smartphone, cloud platform, AI model and healthcare provider. In addition, complex AI systems may be difficult to interpret, while unrepresentative training data may reduce reliability across different populations (Hasanzadeh et al., 2025).

Overall, integrating wearables with AI, cloud computing and clinical systems has considerable potential for predictive and personalised healthcare. However, clinical benefit depends on accurate and representative data, interoperability, transparency and secure data handling. Technological integration should therefore be viewed as a means of improving clinical decision support, rather than evidence that wearable systems can already replace established diagnostic methods.

2. Wearable Technologies for Monitoring and Detecting Various Health Conditions

2.1 Wearable Technologies for Monitoring and Detecting Cardiovascular Diseases

Wearable technologies may address limitations of episodic cardiovascular assessment by continuously collecting physiological data outside clinical environments. Williams et al. (2023) highlight the potential of wearable technologies to provide clinicians with longitudinal cardiovascular information that may otherwise be unavailable during conventional assessment. To illustrate, a study assessed in 2019 used smartwatches to detect atrial fibrillation, and they observed that more than 84% of irregular pulse notifications were concordant with atrial fibrillation (Nazir et al., 2025). Physicians need a context of symptoms in order to prevent, predict, diagnose and manage cardiovascular diseases, which is why consistent monitoring devices enhance care and treatment.

The connection between a high resting heart rate and adverse diseases is well recognised (Jensen, 2019). Wearables often use photoplethysmography sensors to measure the visual dimensions of changes in blood volume circulation, giving us a calculated heart rate by shining a light on the skin and gathering the reflected wave of light with a photodetector (Hughes et al., 2023). It provides a non-obtrusive way of monitoring without interfering with a patient’s daily activities, while also offering immediate arrhythmia detection, regardless of its asymptomatic or intermittent nature (Santala et al., 2021). 

Hypertension holds the highest rank for preventable causes of death worldwide (Etten, 2025). Nonetheless, over the last decade, wearables have become significantly more accessible to the public with the intent of providing validated measurements of blood pressure from the wrist (Cohen et al., 2026). However, reaching that standard has proven difficult, and further regulation is required. The American Heart Association (AHA) (2025) stated that cuffless devices measuring blood pressure, including smartwatches, rings, patches and fingertip monitors, show great potential as alternatives to conventional arm-cuff monitors, but they are not yet proven to be effective, to accurately diagnose high blood pressure or to guide treatment decisions. If these issues persist, using these devices to guide healthcare may potentially foster inappropriate treatment and could expose patients to harm.

Due to their unfortunate implications, cardiovascular diseases require the progression of effective solutions that enable early diagnosis and anticipate their manifestation. Moshawrab et al. (2023) claim that AI will shortly transform cardiovascular health, as it has the ability to outshine experts in detecting and predicting cardiovascular diseases. As a result, smart wearables that integrate AI and ICT are expected to be efficacious in cardiovascular disease detection and prediction (Moshawrab et al., 2023). These claims must be made with caution since the future is unprecedented. Abedi et al. (2025) claim that the development and validation of solutions for continual community-based deployment, participant compliance, hardware, network restrictions and AI model optimisation must be harnessed through interdisciplinary research to reach the full potential of AI driven wearables.

Wearable technology is transforming cardiovascular care by taking subjective patient reminiscence and turning it into ongoing, objective records on heart condition, physical activity and lifestyle behaviours.

2.2 Wearable Technologies for Monitoring and Detecting Neurological Disorders

Continuous monitoring is essential in many neurological diseases. A significant challenge is the limited accessibility of routine detection methods, which require professional equipment and personnel. Examinations are affected by a multitude of factors including examiner competence, the examinee’s mental and physical capacity, as well as displayed symptoms on the day of the exam (Cai et al., 2025). Consequently, the results of such an exam may or may not represent the overall condition of the patient on a regular day, or the symptoms which fluctuate over time – which is something that is able to be monitored with wearable technology. Additionally, daily information can help medical professionals accurately determine whether a new treatment is working by tracking sleep, or whether a patient is adhering to a new plan like increased exercise (Minen & Stieglitz, 2021). 

Parkinson’s disease (PD) patients require frequent treatment adjustments as the disease advances (Ma et al., 2025) which can be difficult if medical professionals are unavailable, but can prove more accessible with the help of wearables. One example is a non-invasive vibrotactile glove that uses implanted mechanical triggers to stimulate PD patients’ fingertips and reduce motor symptoms, including tremors and gait (Bougea, 2025). In other applications, epileptic seizures, motor fluctuations in PD or transient episodes of gait instability may occur infrequently or at specific times of day, making their observation in a clinic setting largely a matter of chance. Without continuous data, clinicians are often forced to rely on patient-reported diaries, which are subjective, prone to recall bias and frequently underestimate symptom frequency (Regalia et al., 2019). Wearable devices equipped with inertial sensors such as accelerometers and gyroscopes can objectively quantify tremors, bradykinesia and postural instability in real-time, while wearable EEG systems offer the potential for long-term seizure detection outside the hospital environment (Stangl et al., 2023). This continuous stream of data not only facilitates the early detection of neurological deterioration but also enables clinicians to make timely, evidence-based adjustments to pharmacotherapy, potentially reducing hospitalisations and improving quality of life.

However, the translation of these technological capabilities into reliable clinical tools is fraught with challenges. The primary limitation of continuous monitoring in neurology is the high rate of false alarms, which can desensitise patients and caregivers to genuine alerts or lead to unnecessary anxiety and healthcare utilisation. Movement artefacts, sensor displacement and the inherent variability of physiological signals across individuals can all confound interpretation, and algorithms trained on general populations may perform poorly when applied to patients with atypical symptom presentations (Jeppesen et al., 2020). Furthermore, individual variability in baseline motor function, medication response and daily activity patterns means that a single threshold for abnormality is insufficient; personalised baselines and machine learning models are required to distinguish pathological events from normal variations in behaviour. Despite these limitations, the potential of wearables to transform neurological care remains profound, offering an unprecedented window into the lived experience of patients between clinic visits and providing the granular data necessary for truly personalised treatment strategies.

2.3 Wearable Technologies for Monitoring and Detecting Musculoskeletal Conditions

Wearable technologies offer particular opportunities in musculoskeletal healthcare because movement and rehabilitation progress can be monitored continuously outside conventional clinical assessments. Around 1.71 billion people worldwide suffer from musculoskeletal conditions, with the highest rate among other types of disorders that contribute to the warrant for rehabilitation services (Cieza et al., 2020).

By continuously monitoring body movements and providing real-time feedback, wearable sensors can offer users practical insights for reducing movement risks. Different wearable sensor technologies, such as inertial measurement units (IMUs), electromyography sensors (EMG) and pressure sensors, offer patients ongoing monitoring and customised adjustments (Alenjareghi et al., 2026). For instance, footwear designed for gait training includes force-based sensors that calculate the heel-strike and heel-off phases of gait, and through auditory or visual biofeedback, the user can improve gait patterns (Porciuncula et al., 2018). During recovery, the employment of this data aids the implementation of more affordable or personalised therapy for patients in their home environment, facilitating a more comprehensive rehabilitation process (Zadech et al., 2023). Feedback on joint movement information is crucial for alterations and progress in the treatment process (Wei & Wu, 2023). However, it should not replace other clinical measures. For example, elbow and shoulder clinicians assure wearables supply distinct data on functional recovery following total shoulder arthroplasty outside of the clinic and are useful primarily when deployed as an auxiliary metric when evaluating postoperative recovery (Edwards et al., 2020, cited in Haddas, 2023).

Beyond rehabilitation, wearable sensors also show promise for injury detection and prevention. Seifi et al. (2026), in a systematic review of wearable sensors in athletes, found evidence that biomechanical data such as tibial shock and ground reaction force could support injury risk assessment, suggesting wearables may help identify increased risks before an injury develops rather than only after it occurs. However, this potential should be interpreted cautiously. Preatoni et al. (2022) note that even though there is growing interest in wearable technology for injury prevention, there remains limited research directly linking specific data gathered by the wearables to actual injury occurrence. This means current evidence supports wearables more strongly for monitoring movement and fatigue than for actually predicting injury in advance. Consequently, detecting an abnormal biomechanical pattern should not necessarily be interpreted as detecting an impending injury, as similar changes may result from fatigue, discomfort or other non-pathological factors.

This same distinction applies to recovery. Iovanel et al. (2023) found that wearable-collected step count and range-of-motion data could predict standard post-operative outcomes following joint replacement, helping clinicians identify patients falling behind expected recovery milestones. This however monitors deviation from an expected pattern rather than detecting a new condition.

Overall, wearables are well supported by evidence for monitoring movement and guiding clinical recovery, but their ability to genuinely determine new musculoskeletal disease remains far less established, and such claims should be operated cautiously.

2.4 Wearable Technologies for Monitoring and Detecting Mental Health Conditions

Wearable technologies can support mental-health monitoring by continuously collecting physiological and behavioural data linked to conditions such as anxiety, depression and stress. Common measurements include heart rate, heart-rate variability, sleep, physical activity and skin conductance. Hickey et al. (2021) found that HRV is frequently used in research on stress and anxiety, while Jafleh et al. (2024) also identify HRV, blood pressure, skin conductance and brain activity as useful signals for wearable monitoring.

Continuous monitoring may be particularly useful because it allows changes to be observed over longer periods rather than only during clinical appointments. Ahmed et al. (2023) found that wearable devices are increasingly being studied for monitoring anxiety and depression, particularly wrist-worn devices. This could help identify changes in sleep, activity or physiological responses that may indicate worsening mental health. However, these signals are not unique to mental-health conditions, meaning that wearable data must be interpreted carefully. This limitation is particularly important when considering the apparently high predictive performance reported by some studies.

Shen et al. (2025), in a scoping review of 42 studies using wearables and smartphone sensing for mental-health monitoring, found that even if some of the machine-learning models reported high accuracy, such as one of the studies included in their review reporting 92% or more accuracy in detecting anxiety, most studies relied on small samples, limiting the generalisability of the findings, and short periods of monitoring, and rarely tested whether the findings can be generalised beyond the sample. This means that the impressive 92% accuracy from this individual study may not reflect how reliable these signals can be applied more broadly. Physiological signals associated with mental-health conditions may also be influenced by physical health, environmental conditions and everyday behaviour. Consequently, identifying an abnormal physiological pattern does not necessarily establish that the underlying cause is psychological, so specificity remains a genuine limitation.

This uncertainty is compounded by ethical concerns as errors in wearable interpretation may have greater consequences when algorithms attempt to infer sensitive psychological states from behavioural and physiological data. Capulli et al. (2025) identified patient safety, autonomy, justice and personal-data protection as important ethical concerns surrounding health-monitoring wearable devices, particularly where the risks and benefits of their use remain uncertain. For data as sensitive as mental-health indicators, this raises real risks around misuse and decisions being made about a person based on incomplete or misread signals. These concerns become particularly important when personal health data are shared with third parties or used for secondary purposes. Baines et al. (2024) found that privacy, security and data-management concerns were major barriers to sharing personal health data, while transparency and individual control over what data are shared, with whom, when and for how long were important considerations for consent. Therefore, when wearable data is used to make inferences about an individual’s mental health, both the possibility of inaccurate interpretation and the handling of sensitive personal data need to be considered.

Overall, wearables offer a promising, non-invasive approach to monitor mental health continuously, and the range of physiological signals identified across studies shows genuine research interest in this area. However, given the current limitations around specificity, small-scale validation and unresolved questions about data privacy and consent, wearable-derived signals should act as indicators rather than a standalone diagnostic tool. Their value is therefore likely dependent on being interpreted alongside clinical judgement, rather than being relied upon as a standalone method of identifying mental-health conditions.

3. The Future of Wearable Technologies

The future of wearable health technologies is likely to involve a shift from monitoring isolated physiological measurements towards combining multiple biochemical and biophysical signals. Current wearable biosensors can already provide continuous measurements of biomarkers and physiological variables, while developments in multiplexed sensing and microfluidic sampling may allow several indicators to be measured simultaneously (Kim et al., 2019; Kulkarni et al., 2024). Multimodal wearables extend this approach by combining different sensing methods within a single device. Mahato et al. (2024) argue that this could address a major weakness of single-parameter monitoring, since individual physiological signals are often non-specific and may not provide a complete assessment of health. Consequently, the significance of multimodal sensing lies not simply in collecting more data, but in potentially providing a more comprehensive basis for recognising abnormal patterns.

Artificial intelligence may further increase the value of these systems by analysing multiple continuous data streams and identifying combinations of changes that could indicate health deterioration. This creates the possibility of moving from retrospective monitoring towards earlier and more predictive healthcare. However, current evidence does not establish that increasing technological sophistication automatically produces better clinical outcomes. A 2025 scoping review found that only 12 of 80 studies used wearable data to diagnose new disease, while the majority focused on monitoring existing conditions; the authors concluded that evidence for the clinical effectiveness of wearables remains limited and highly variable (Lodewyk et al., 2025). This suggests that early detection remains less established than disease monitoring.

Several barriers must therefore be addressed before more advanced wearable systems can be adopted routinely. Even commercially successful wearable biosensors continue to face problems involving accuracy, reliability and autonomy, while newer systems must also overcome issues such as signal drift, calibration, user variability and clinical validation. Multimodal sensing may reduce the limitations of relying on a single indicator, but combining additional sensors does not remove errors if the underlying measurements remain inaccurate. Wider adoption will also depend on interoperability with clinical systems, secure handling of personal data and evidence that predictions are reliable across different populations.

Overall, current evidence supports considerable potential rather than inevitable transformation. Future wearables are more likely to augment clinical decision-making by providing increasingly detailed longitudinal information than to replace healthcare professionals. Their contribution to early disease detection will depend not only on advances in sensing and AI, but on whether these technologies achieve sufficient accuracy, validation, interoperability and clinical usefulness for routine healthcare.

4. Conclusion

Wearable technologies have considerable potential to transform how healthcare is delivered by enabling more continuous, preventive and personalised approaches to patient care. By collecting physiological and behavioural data outside clinical settings at all times, wearables can provide a more in-depth picture of an individual’s health over time. Across cardiovascular, neurological and musculoskeletal conditions, these technologies have demonstrated value in monitoring symptoms, identifying physiological changes, supporting rehabilitation and enabling remote patient management. Their ability to gather data during everyday life is particularly important for conditions characterised by intermittent symptoms or changes that may not be captured during a clinical appointment.

However, the availability of continuous data does not always result in reliable diagnosis or improved clinical outcomes. Measurement inaccuracies, insufficient clinical validation, privacy concerns, patient adherence and differences in sensor performance across populations remain significant limitations. Therefore, wearable-generated information should generally complement established clinical assessments rather than replace professional judgement. This is especially important where inaccurate measurements or false alerts could result in inappropriate treatment decisions.

The integration of wearable technologies with artificial intelligence, machine learning and healthcare information systems may further increase their clinical usefulness. These technologies can assist in interpreting large quantities of continuously collected data and identifying patterns that may otherwise be difficult to recognise. Nevertheless, their effectiveness remains dependent on the quality and representativeness of the underlying data.

Overall, wearable technologies provide an important opportunity to make healthcare more continuous, accessible and responsive to individual patients. Their future clinical value will depend not simply on collecting greater quantities of health data, but on ensuring that this information is accurate, secure, clinically validated and meaningfully integrated into healthcare decision-making.

Abedi, A., Verma, A., Jain, D., Kaetheeswaran, J., Chui, C., Lankarany, M. and Khan, S.S. (2025) ‘AI-driven real-time monitoring of cardiovascular conditions with wearable devices: Scoping review’, JMIR mHealth and uHealth, 13, e73846.

Abedian, S., Yesakov, E., Ostrovskiy, S. and Hussein, R. (2025) ‘Streamlining wearable data integration for EHDS: a case study on advancing healthcare interoperability using Garmin devices and FHIR’, Frontiers in Digital Health, 7, 1636775.

Ahmed, A., Aziz, S., Alzubaidi, M., Schneider, J., Irshaidat, S., Abu Serhan, H., Abd-Alrazaq, A.A., Solaiman, B. and Househ, M. (2023) ‘Wearable devices for anxiety & depression: A scoping review’, Computer Methods and Programs in Biomedicine Update, 3, 100095.

Alenjareghi, M.J., Sekkay, F., Dadouchi, C. and Keivanpour, S. (2026) ‘Wearable sensors in Industry 4.0: Preventing work-related musculoskeletal disorders’, Sensors International, 7, 100343.

American Heart Association (2025) ‘Cuffless blood pressure technologies in wearable devices show promise to transform care’, American Heart Association Newsroom [online]. <https://newsroom.heart.org/news/cuffless-blood-pressure-technologies-in-wearable-devices-show-promise-to-transform-care>

Babu, M., Lautman, Z., Lin, X., Sobota, M.H.B. and Snyder, M.P. (2024) ‘Wearable devices: Implications for precision medicine and the future of health care’, Annual Review of Medicine, 75, pp. 401-415.

Baines, R., Stevens, S., Austin, D., Anil, K., Bradwell, H., Cooper, L., Maramba, I.D., Chatterjee, A. and Leigh, S. (2024). Patient and Public Willingness to Share Personal Health Data for Third-Party or Secondary Uses: Systematic Review. Journal of Medical Internet Research, 26(1), e50421.

Bent, B., Goldstein, B.A., Kibbe, W.A. and Dunn, J.P. (2020) ‘Investigating sources of inaccuracy in wearable optical heart rate sensors’, npj Digital Medicine, 3, 18.

Bougea, A. (2025). Application of Wearable Sensors in Parkinson’s Disease: State of the Art. Journal of Sensor and Actuator Networks, 14(2), 23.

Burmaoglu, S., Trajkovik, V., Tutukalo, T.L., Yalcin, H. and Caulfield, B. (2018). ‘Chapter 14 – Evolution Map of Wearable Technology Patents for Healthcare Field’, in (ed. Tong, R.K.-Y.) Wearable Technology in Medicine and Health Care (Academic Press: London), pp. 275-290.

Cai, H., Hu, J., Zhao, C. and Lin, J. (2025) ‘Wearable devices in neurological disorders: a narrative review of status quo and perspectives’, Annals of Translational Medicine, 13(4), 46.

Capulli, E., Druda, Y., Palmese, F., Butt, A.H., Domenicali, M., Macchiarelli, A.G., Silvani, A., Bedogni, G. and Ingravallo, F. (2025). Ethical and Legal Implications of Health Monitoring Wearable Devices: A Scoping Review. Social Science & Medicine, 370, 117685.

Cieza, A., Causey, K., Kamenov, K., Hanson, S.W., Chatterji, S. and Vos, T. (2020) ‘Global estimates of the need for rehabilitation based on the Global Burden of Disease study 2019: a systematic analysis for the Global Burden of Disease Study 2019’, The Lancet, 396(10267), pp. 2006–2017.

Cohen, J.B., Byfield, R.L., Hardy, S.T., Juraschek, S.P., Houston Miller, N., Mukkamala, R., Picone, D.S., Thiele, R.H., Yang, E. and Brady, T.M. (2026) ‘Cuffless devices for the measurement of blood pressure: A scientific statement from the American Heart Association’, Hypertension, 83(3), pp. 876–886.

De Angel, V., Lewis, S., White, K. et al. (2022) ‘Digital health tools for the passive monitoring of depression: a systematic review of methods’, npj Digital Medicine, 5, 3.

Devine, J.K., Schwartz, L.P. and Hursh, S.R. (2022) ‘Technical, regulatory, economic, and trust issues preventing successful integration of sensors into the mainstream consumer wearables market’, Sensors, 22(7), 2731.

Edelmann, S. (2025). Wearable technology in healthcare: How recent advances are transforming patient care. Roche Diagnostics [online]. <https://diagnostics.roche.com/global/en/healthcare-transformers/article/wearable-technology-in-healthcare.html>

Etten, E.S. (2025) World Hypertension Day – 17 May 2025, European Stroke Organisation [online]. <https://eso-stroke.org/blog-world-hypertension-day-17-may-2025/>

Fine, J., Branan, K.L., Rodriguez, A.J., Boonya-Ananta, T., Ajmal, A., Ramella-Roman, J.C., McShane, M.J. and Coté, G.L. (2021) ‘Sources of inaccuracy in photoplethysmography for continuous cardiovascular monitoring’, Biosensors, 11(4), 126.

Fowe, I.E., Sanders, E.C. and Boot, W.R. (2023) ‘Understanding barriers to the collection of mobile and wearable device data to monitor health and cognition in older adults: A scoping review’, AMIA Joint Summits on Translational Science Proceedings, 2023, pp. 186-195.

Giurgiu, M. et al. (2025) ‘The wearable landscape: Issues pertaining to the validation of the measurement of 24-h physical activity, sedentary, and sleep behavior assessment’, Journal of Sport and Health Science, 14, 101006.

Haddas, R. (2023) ‘Assessing disability and function in patients with musculoskeletal disorders utilizing wearable medical technology: Opportunities and challenges’, Journal of Back and Musculoskeletal Rehabilitation, 36(4), pp. 779–782.

Hasanzadeh, F., Josephson, C.B., Waters, G., Adedinsewo, D., Azizi, Z. and White, J.A. (2025) ‘Bias recognition and mitigation strategies in artificial intelligence healthcare applications’, npj Digital Medicine, 8, 154.

Hawthorne, G., Richardson, M., Greening, N.J., Esliger, D., Briggs-Price, S., Chaplin, E.J., Clinch, L., Steiner, M.C., Singh, S.J. and Orme, M.W. (2022) ‘A proof of concept for continuous, non-invasive, free-living vital signs monitoring to predict readmission following an acute exacerbation of COPD: a prospective cohort study’, Respiratory Research, 23, 102.

Hickey, B.A., Chalmers, T., Newton, P., Lin, C.-T., Sibbritt, D., McLachlan, C.S., Clifton-Bligh, R., Morley, J. and Lal, S. (2021) ‘Smart devices and wearable technologies to detect and monitor mental health conditions and stress: a systematic review’, Sensors, 21(10), 3461.

Hughes, A., Shandhi, M.M.H., Master, H., Dunn, J. and Brittain, E. (2023) ‘Wearable devices in cardiovascular medicine’, Circulation Research, 132(5), pp. 652-670.

Iovanel, G., Ayers, D. and Zheng, H. (2023) ‘The role of wearable technology in measuring and supporting patient outcomes following total joint replacement: Review of the literature’, JMIR Perioperative Medicine, 6, e39396.

Jafleh, E.A., Alnaqbi, F.A., Almaeeni, H.A., Faqeeh, S., Alzaabi, M.A. and Al Zaman, K. (2024) ‘The role of wearable devices in chronic disease monitoring and patient care: a comprehensive review’, Cureus, 16(9), e68921.

Jamieson, A., Chico, T.J.A., Jones, S., Chaturvedi, N., Hughes, A.D. and Orini, M. (2025) ‘A guide to consumer-grade wearables in cardiovascular clinical care and population health for non-experts’, npj Cardiovascular Health, 2(1), 44.

Jensen, M.T. (2019) ‘Resting heart rate and relation to disease and longevity: Past, present and future’, Scandinavian Journal of Clinical and Laboratory Investigation, 79(1–2), pp. 108–116.

Jeppesen, J., Fuglsang-Frederiksen, A., Johansen, P., Christensen, J., Wüstenhagen, S., Tankisi, H., Qerama, E. and Beniczky, S. (2020) ‘Seizure detection using heart rate variability: A prospective validation study’, Epilepsia, 61(Suppl. 1), S41–S46.

Kamei, T., Kanamori, T., Yamamoto, Y. and Edirippulige, S. (2022) ‘The use of wearable devices in chronic disease management to enhance adherence and improve telehealth outcomes: A systematic review and meta-analysis’, Journal of Telemedicine and Telecare, 28(5), pp. 342-359.

Kim, J., Campbell, A.S., de Avila, B.E.F. and Wang, J. (2019) ‘Wearable biosensors for healthcare monitoring’, Nature Biotechnology, 37, pp. 389-406.

Koerber, D., Khan, S., Shamsheri, T., Kirubarajan, A. and Mehta, S. (2023) ‘Accuracy of heart rate measurement with wrist-worn wearable devices in various skin tones: A systematic review’, Journal of Racial and Ethnic Health Disparities, 10(6), pp. 2676-2684.

Kulkarni, M.B., Rajagopal, S., Prieto-Simon, B. and Pogue, B.W. (2024) ‘Recent advances in smart wearable sensors for continuous human health monitoring’, Talanta, 272, 125817.

Li, R.T., Kling, S.R., Salata, M.J., Cupp, S.A., Sheehan, J. and Voos, J.E. (2016) ‘Wearable performance devices in sports medicine’, Sports Health, 8(1), pp. 74-78.

Lodewyk, K., Wiebe, M., Dennett, L., Larsson, J., Greenshaw, A. and Hayward, J. (2025) ‘Wearables research for continuous monitoring of patient outcomes: A scoping review’, PLOS Digital Health, 4(5), e0000860.

Mahato, K., Saha, T., Ding, S., Sandhu, S.S., Chang, A.-Y. and Wang, J. (2024) ‘Hybrid multimodal wearable sensors for comprehensive health monitoring’, Nature Electronics, 7, pp. 735-750.

Ma, Y., Zhang, Y., Li, R., Cheng, W. and Wu, F. (2025) The experience and perception of wearable devices in Parkinson’s disease patients: a systematic review and meta-synthesis of qualitative studies. J Neurol., 272(5), 350.

Mehta, S.J., Hume, E., Troxel, A.B., Reitz, C., Norton, L., Lacko, H., McDonald, C., Freeman, J., Marcus, N., Volpp, K.G. and Asch, D.A. (2020) ‘Effect of remote monitoring on discharge to home, return to activity, and rehospitalization after hip and knee arthroplasty’, JAMA Network Open, 3(12), e2028328.

Minen, M.T. and Stieglitz, E.J. (2021) ‘Wearables for neurologic conditions: considerations for our patients and research limitations’, Neurology Clinical Practice, 11(4), e537-e543.

Mone, V. and Fayazullaeva, S. (2023) ‘Health data on the go: Navigating privacy concerns with wearable technologies’, Legal Information Management, 23(3), pp. 179-188.

Moshawrab, M., Adda, M., Bouzouane, A., Ibrahim, H. and Raad, A. (2023) ‘Smart wearables for the detection of cardiovascular diseases: A systematic literature review’, Sensors, 23(2), 828.

Nazir, A., Nazir, A., Jamal, M.S.W., Sadiq, S.R., Aman, S., Mustapha, M.J., Lawal, S.O., AbdulKareem, M.O. and Bamigbola, M.F. (2025) ‘Wearable technology and its potential role in cardiovascular health monitoring and disease management’, Health Science Reports, 8(11), e71486.

Olyanasab, A. and Annabestani, M. (2024) ‘Leveraging machine learning for personalized wearable biomedical devices: a review’, Journal of Personalized Medicine, 14(2), 203.

Porciuncula, F., Roto, A.V., Kumar, D., Davis, I., Roy, S., Walsh, C.J. and Awad, L.N. (2018) ‘Wearable movement sensors for rehabilitation: A focused review of technological and clinical advances’, PM&R, 10(9 Suppl. 2), S220-S232.

Preatoni, E., Bergamini, E., Fantozzi, S., Giraud, L.I., Orejel Bustos, A.S., Vannozzi, G. and Camomilla, V. (2022) ‘The use of wearable sensors for preventing, assessing, and informing recovery from sport-related musculoskeletal injuries: A systematic scoping review’, Sensors, 22(9), 3225.

Regalia, G., Onorati, F., Lai, M., Caborni, C. and Picard, R.W. (2019) ‘Multimodal wrist-worn devices for seizure detection: advancing epilepsy care beyond the clinic’, Epilepsy & Behavior, 98, pp. 295-302.

Roos, L.G. and Slavich, G.M. (2023) ‘Wearable technologies for health research: Opportunities, limitations, and practical and conceptual considerations’, Brain, Behavior, and Immunity, 113, pp. 444-452.

Santala, O.E., Halonen, J., Martikainen, S., Jäntti, H., Rissanen, T.T., Tarvainen, M.P., Laitinen, T.P., Laitinen, T.M., Väliaho, E.-S., Hartikainen, J.E.K., Martikainen, T.J. and Lipponen, J.A. (2021) ‘Automatic mobile health arrhythmia monitoring for the detection of atrial fibrillation: Prospective feasibility, accuracy, and user experience study’, JMIR mHealth and uHealth, 9(10), e29933.

Seifi, V., Tavana, M.M., Soltani, S., Asgari, A.M. and Khavari Ardestani, D. (2026) ‘Clinical applications of wearable sensor-based gait analysis in athletes: A systematic review for injury prevention and rehabilitation’, BMC Sports Science, Medicine and Rehabilitation, 18, 105.

Seitz, S. (2025). Medical-grade wearables: A developer’s guide to clinically validated devices. Medium [online]. <https://medium.com/@sequenex/medical-grade-wearables-a-developers-guide-to-clinically-validated-devices-e0365ce4765c>

Shajari, S., Kuruvinashetti, K., Komeili, A. and Sundararaj, U. (2023) ‘The emergence of AI-based wearable sensors for digital health technology: a review’, Sensors, 23(23), 9498.

Shen, S., Qi, W., Zeng, J., Li, S., Liu, X., Zhu, X., Dong, C., Wang, B., Shi, Y., Yao, J., Wang, B., Lou, X., Gu, S., Li, P., Wang, J., Jiang, G. and Cao, S. (2025). Passive Sensing for Mental Health Monitoring: A Scoping Review of Machine Learning with Wearables and Smartphones. Journal of Medical Internet Research, 27, e77066.

Silva-Trujillo, A.G., Jacobo, M.G.G., Pablo, L.R. and Javier, L.G.V. (2023) ‘Cybersecurity analysis of wearable devices: Smartwatches passive attack’, Sensors, 23(12), 5438.

Smuck, M., Odonkor, C.A., Wilt, J.K., Schmidt, N. and Swiernik, M.A. (2021) ‘The emerging clinical role of wearables: factors for successful implementation in healthcare’, npj Digital Medicine, 4, 45.

Stangl, M., Maoz, S.L. and Suthana, N. (2023) ‘Mobile cognition: imaging the human brain in naturalistic environments’, Nature Reviews Neuroscience, 24(1), pp. 28-41.

Stuart, S., de Kok, M., O’Searcoid, B., et al. (2024). ‘Critical Design Considerations for Longer-Term Wear and Comfort of On-Body Medical Devices’, Bioengineering (Basel), 11(11), 1058.

Topol, E.J. (2019) ‘High-performance medicine: the convergence of human and artificial intelligence’, Nature Medicine, 25(1), pp. 44-56.

Vijayan, V., Connolly, J.P., Condell, J., McKelvey, N. and Gardiner, P. (2021) ‘Review of wearable devices and data collection considerations for connected health’, Sensors, 21(16), 5589.

Wei, S. and Wu, Z. (2023) ‘The application of wearable sensors and machine learning algorithms in rehabilitation training: A systematic review’, Sensors, 23(18), 7667.

Williams, G.J. et al. (2023) ‘Wearable technology and the cardiovascular system: the future of patient assessment’, The Lancet Digital Health, 5(7), e467-e476.

Yoon, H. and Choi, S.H. (2023) ‘Technologies for sleep monitoring at home: wearables and nearables’, Biomedical Engineering Letters, 13(3), pp. 313-327.

Zadech, S.M., MacDermid, J., Johnson, J., Birmingham, T.B. and Shafiee, E. (2023) ‘Applications of wearable sensors in upper extremity MSK conditions: A scoping review’, Journal of Neuroengineering and Rehabilitation, 20(1), 158.