Abstract

Modern healthcare is progressing from occasional in-person doctor visits towards more continuous and preventive care. Traditional checkups can miss fluctuations in patient health between visits. Wearable devices provide a solution to this, continuously monitoring patient health. Wearable technology typically falls into two categories: accessible wearables that monitor consumers’ health, and medical wearables designed for patient diagnosis and treatment. To understand the overall impact of wearables, it is crucial to consider both their limitations and benefits.

In respiratory care and oncology, continuous monitoring of respiratory rate, gait and fatigue provides more actionable data than subjective patient surveys. In diabetes and dermatology, devices are evolving into closed-loop systems, such as automated insulin delivery and therapeutic OLED patches for wound healing, that would directly administer interventions. However, significant barriers hinder widespread adoption. Clinically, unorganised, continuous data risks causing physician cognitive overload, while legacy electronic health record (EHR) systems lack the interoperability and cloud security needed for big data integration. Technically, issues with artificial intelligence (AI) model drift, sensor inaccuracies, high costs, privacy concerns and physical discomfort limit both patient adherence and diagnostic reliability.

Ultimately, medical wearables reach their full potential not through simple passive monitoring, but when deployed as continuous, proactive therapeutic platforms integrated directly into established clinical workflows. Realising this vision requires distinguishing commercially proven capabilities – for example, optical heart rate and ECG – from newer concepts, such as non-invasive glucose sensing, to ensure clinical utility.

1. Introduction

1.1 Wearable Technologies in Healthcare

Wearable technologies are devices worn by patients that collect and interpret data about the body and are often used to help treat diseases (Iqbal et al., 2016). Wearables can be separated into two major categories: consumer wearables and medical wearables. Doherty et al. (2024) define consumer wearable devices as any wearable device available for public purchase. Meanwhile, Devine, Schwartz and Hursh (2022) define medical wearables as “devices intended for the purpose of diagnosis, prevention, monitoring, treatment, prediction, or alleviation of a specific disease or disease state.” These two definitions illustrate the main trade-offs between the two types of wearables: consumer wearable devices can monitor large populations due to their accessibility; in contrast, medical wearable devices have specific clinical use cases due to their greater specialisation. 

Consumer wearables include smartwatches, fitness trackers and smart rings (Doherty et al., 2024). Since medical approval is not required for consumer wearables, they can be used by a larger section of the population than medical wearables. These devices use built-in sensors to track a variety of general biometric data, such as location, movement, heart and respiratory rates, blood oxygen levels, blood pressure and temperature. Still, they do not use invasive sensing techniques that penetrate the skin (Jamieson et al., 2025). They can then track, store and send this data to medical professionals in real time (George et al., 2023). These factors make consumer wearable devices attractive for conducting longitudinal monitoring. Still, the clinical viability of consumer wearable studies depends on their accuracy across parameters, which can vary from around a 3% margin of error for heart rate to 29-80% for physical activity (Doherty et al., 2024).

Medical wearables include patches, chest straps and smart clothing that monitor vital signs, as well as more specialised devices, such as an exoskeleton for gait analysis or a system of accelerometers distributed around the body to detect movement that could indicate diseases or seizures (Iqbal et al., 2016). Medical wearables can also incorporate sensing methods unavailable in consumer wearables, enabling them to monitor more specialised physiological parameters. For example, continuous glucose monitors can measure interstitial glucose levels continuously, which can then be interpreted with integrated artificial intelligence (AI) systems that predict high and low blood sugar levels early (Fraser et al., 2025). Many medical wearables, such as continuous glucose monitors, are also prescription-only, limiting access to them (Xu et al., 2022). These factors highlight the main use of medical wearables: as specialised tools used for specific applications.

Overall, consumer and medical wearables have distinct uses in medicine: consumer wearables serve as more general monitoring devices, potentially useful for long-term studies; in contrast, medical wearables are specialised tools with specific use cases. The value each wearable provides, therefore, is not based on the accessibility or variety of sensors a device holds, but the accuracy of its measurements and whether the wider medical field validates them.

1.2 Benefits and Opportunities of Wearable Technologies

Wearable technologies in healthcare enable continuous patient monitoring, which in turn allows better management of chronic diseases. Examples include: wearable glucose monitors that generate real-time alarms when harmful blood glucose variations occur, lowering the risks of hospitalisation and the long-term consequences of diabetes like renal failure; wearable ECG devices that provide early warnings for abnormal cardiac electrical activity, allowing doctors to spot and treat cardiovascular diseases quickly; and portable oxygen saturation monitors that enable early detection of lung diseases in patients with conditions such as asthma (Qadrie et al., 2025). This continuous stream of real-time data enables the detection of certain anomalies, providing early warning before irreversible organ damage occurs. Immediate, automatic alerts can enable caretakers to take action promptly, such as timely dose adjustments, while simultaneously providing doctors with long-term data trends to tailor the management of chronic diseases.

Another applicable benefit of wearable technologies is allowing remote patient monitoring. According to Liao et al. (2019), wearable and mobile technology can enable cost-effective and scalable opportunities for remote, and often real-time, monitoring of patients during critical periods of cancer care. When patients undergo intensive chemotherapy treatments, they experience most of their care at home, away from the clinical setting, so they are responsible for making complex decisions on when to contact their healthcare team when side effects escalate. Liao et al. (2019) report evidence from randomised trials indicating that remote symptom monitoring of patients undergoing chemotherapy, when combined with clinical support, was associated with fewer treatment interruptions and improved survival. This suggests that the clinical benefit of continuous monitoring depends not only on data collection but also on whether healthcare systems can interpret the data and respond appropriately. Care providers need to provide appropriate support when symptoms worsen for the benefits of wearable devices to take effect. 

However, questions have been raised about how to interpret the large volume of data generated by continuous monitoring, and strategies are needed to manage and integrate this data into electronic health records (Liao et al., 2019).

The potential contribution of wearables extends beyond monitoring; some technologies also support therapeutic delivery. Healthcare wearable devices enhance disease management and personalised care by providing continuous biosensing and automated therapeutic interventions for specific conditions. Rather than relying on periodic hospital visits, some specialised devices act preemptively; for instance, thoracic impedance patches track fluid retention to alert clinicians “days before heart failure symptoms such as shortness of breath are noted by the patient” (Iqbal et al., 2021). Additionally, these devices improve disease management by preventing treatment complications, as “the noninvasive nature of wearable devices has made therapeutic procedures simple and has decreased the risk of infection, which was previously related to blood” (Iqbal et al., 2021). Finally, wearables go beyond monitoring by enabling targeted therapeutic interventions, as “these HWDs can be used for the delivery of drugs in a more controlled and efficient manner in comparison to traditional drug delivery systems”(Iqbal et al., 2021). Healthcare providers also have access to more precise and frequent data to better inform study designs and understand the clinical benefits of therapies.

Taken together, these applications demonstrate the potential of wearable technologies to support earlier intervention, remote monitoring and more personalised disease management. However, their clinical benefits depend on data accuracy and effective integration with healthcare services.

1.3 Challenges and Limitations of Wearable Technologies

Although wearable technologies show significant promise for continuous physical monitoring, remote patient care and other applications, several limitations challenge the benefits highlighted in Section 1.2. A key limitation is the accuracy, reliability and clinical validity of the data collected by wearable technology. Wearable technology intended for consumer use can vary in accuracy and reliability. This raises concerns about the reliability of the data and its appropriateness for clinical decision-making (GAO, 2026). Errors in patient data can lead to false positives or false negatives, which may adversely affect a patient’s treatment. Another limitation regarding data accuracy is AI false positives and false negatives, as well as model drift. This is when the accuracy of AI models degrades over time. If these data errors go unnoticed for a significant period, their effects may be seen in patient health (GAO, 2026).

Moreover, continuous monitoring captures vast amounts of data. This presents a severe data overload issue, which constrains clinical workflow integration. Large volumes of unfiltered, unorganised data can create clinical friction for clinicians. This may ultimately be a limitation if healthcare systems cannot efficiently filter clinically meaningful signals from large volumes of routine data. Wearable devices can collect millions of data points over a set period, which can overwhelm the clinician, as this has to be evaluated before it can be taken into account in clinical decision-making (GAO, 2026). Due to the mass collection of data, the overwhelming of clinicians can weaken or strain the clinical process by adding stress during decision-making, hindering workflow integration. Moreover, this excessive data can make it harder for doctors to spot issues in real time.

Additionally, long-term continuous tracking depends on device utility and patient adherence, which can become limiting factors due to factors like physical comfort, ease of use and patients’ perceived usefulness of the technology. These factors can be what limits patients’ adherence to the device (Jafleh et al., 2024). Furthermore, a lack of user adherence or engagement can significantly decrease the effectiveness of these devices (Jafleh et al., 2024). Consequently, the continuous monitoring benefit identified in Section 1.2 depends on sustained patient adherence; inconsistent use may create gaps in longitudinal data and reduce the reliability of subsequent clinical interpretation. If patients are not using the device, data cannot be collected to evaluate their treatment plan. This is why patient adherence is so crucial and also why it is a critical limitation. 

Finally, additional concerns regarding price and data privacy also arise with the rapid development of wearable technology. As wearables continue to develop, the technology behind them remains expensive, creating a financial barrier for many people (Jafleh et al., 2024). High device costs may limit access among lower-income populations, potentially creating inequalities in who benefits from emerging forms of continuous health monitoring. In healthcare, there is a gap between higher- and lower-income populations, keeping the underprivileged without access to advanced technology. Moreover, privacy has also been shown to be a major limitation in wearable technology. Capturing large amounts of sensitive patient data makes patients vulnerable to data breaches and to uncertainty about the security of their data. Continuous tracking captures highly detailed data like psychological signals, daily routines, behaviour and location. This is a crucial limitation to overcome by gaining users’ trust; otherwise, patients will be concerned about the collection of their data (Jafleh et al., 2024).

1.4 Integration of Wearable Technologies with Other Technologies

The integration of wearable technologies with broader digital healthcare infrastructures, such as the Internt of Medical Things (IoMT), can extend their clinical value by enabling the transmission, storage and analysis of collected data across connected systems (Nui et al., 2023). Additionally, one of the most prevalent yet controversial technologies integrated with wearable devices has been artificial intelligence and machine learning (ML) (Radanliev, 2025). The role of wearable technologies in the IoMT is to collect data for processing and analysis (Nui et al., 2023), while integrated AI and ML can continuously process data to derive clinically useful information for inferring events, states and risk estimates (Kim et al., 2026). For example, there are increasing reports of wearable sweat-monitoring devices continuously collecting data on sweat biomarkers and sodium levels (Wang et al., 2022); AI would then be a useful tool for processing this data and determining the user’s hydration level (Kim et al., 2026). Additionally, the integration of wearable technology into the IoMT, along with cloud computing, has enabled high reliability, effective resource sharing, and cost-effectiveness (Nui et al., 2023). 

Nevertheless, the integration of wearable technologies with the IoMT, AI and ML has posed many challenges. For example, data volumes have become too large, requiring more advanced technology to store and process this big data (Nui et al., 2023). These issues with continuous data collection could lead to interoperability problems across different connected systems, since it is unlikely that every medical technology is designed to store the volume of data generated by continuous monitoring. In addition, cloud storage for big data has issues connecting to and effectively interoperating with the entire vast range of technologies used in medicine (Nui et al., 2023). These issues tie into the challenges electronic health records face, as they also struggle with patient privacy, system interoperability and the volume of patient data to process (Dinh-Le et al., 2019). Additionally, AI and ML both raise issues such as privacy concerns, invasive targeted advertising, algorithmic bias and increased insurance premiums based on health data (Radanliev, 2025). Moreover, ML-integrated wearable technologies face the challenge of fitting complex programs onto wearable devices due to limited data storage and computing capabilities (Xiao et al., 2024).

Therefore, the clinical value of integrating wearables with AI, ML, the IoMT and cloud-based healthcare systems depends not simply on connecting more technologies, but on effectively integrating complex programs and on whether wearable-generated data can be accurately interpreted, securely transmitted and effectively incorporated into clinical decision-making.

2. Wearable Technologies for Monitoring and Detecting Various Afflictions

2.1 Wearable Technologies for Monitoring and Detecting Respiratory Diseases

Wearable technologies serve as an important resource for respiratory health. The continuous monitoring of multiple respiratory health measurements enables wearable technologies to detect and potentially predict exacerbations in chronic respiratory diseases such as chronic obstructive pulmonary disease (COPD), asthma and many others (Armstrong, 2026).

Examples of the many capabilities of wearable technologies for respiratory health include the monitoring of respiratory rate and oxygen saturation (Patel et al., 2021). Hawthorne et al. (2022), after reviewing many clinicians’ and patients’ reviews, reported confidence in the ability of wearable technologies to track oxygen saturation via pulse oximetry; however, it was found that pulse oximetry has limitations, as complete, continuous monitoring of oxygen saturation is not yet feasible due to the presence of invasive issues. In contrast, wearable technologies have proven effective at continuously monitoring respiratory rate (Armstrong, 2026).

One method used to measure respiratory rate with wearable technologies is the integration of small fiber Bragg grating (FBG) sensors (Hussain et al., 2023). Rajeh and Hurst (2016) concluded that monitoring respiratory rate led to a statistically significant change in the exacerbation detection rate among patients with COPD. The benefits of monitoring respiratory rate demonstrate the potential of wearable technologies for continuous patient monitoring and for preventing COPD exacerbations.

Studies validating wearable sensors – such as inertial measurement units (IMUs), acoustic sensors and photoplethysmography (PPG) – show high correlation with medical-grade reference equipment during rest or controlled protocols (Abdulsadig et al., 2024; Eisenkraft et al., 2023). For example, devices that measure acoustic signals achieve a root-mean-square deviation of within three breaths per minute of clinical standards (Abdulsadig et al., 2024). However, physical activity introduces substantial motion artifacts, sensor displacement and noise, severely degrading signal quality and diagnostic accuracy (Hussain et al., 2023; Vitazkova et al., 2024).

Respiratory rate is widely recognised as one of the earliest and most sensitive vital signs for predicting acute clinical deterioration, often changing hours before changes in heart rate or blood pressure manifest (Vitazkova et al., 2024). When integrated into longitudinal algorithms, wearables enable continuous baseline tracking that can detect early deviations, such as respiratory tract infections, asthma attacks or COPD flare-ups.

While current wearables cannot independently replace formal clinical diagnostics, they offer significant potential as screening tools for high-risk patients, prompting timely medical consultations and enabling early intervention before severe decompensation occurs (Abdulsadig et al., 2024).

However, challenges exist regarding the reliability and comfort of these respiratory sensors. Sensors are divided into two types: low- and high-frequency sensors, each with distinct strengths and weaknesses. Low-frequency sensors provide direct measurements of respiratory movements but face challenges related to hysteresis, electrode-to-skin contact, motion artifacts and environmental interference (Hussian et al., 2023). On the other hand, high-frequency sensors offer wireless, contactless operation with good communication capabilities, but they face challenges with power consumption, data transmission and design complexity (Hussian et al., 2023). Therefore, more research is needed to identify materials with sufficient flexibility and biocompatibility to ensure long-term operation without causing user discomfort. 

2.2 Wearable Technologies for Monitoring and Detecting Diabetes and Metabolic Conditions

Wearable technologies can contribute greatly to the monitoring and management of diabetes, with further promising applications in its diagnosis and prevention. A variety of wearable technologies can be used to treat diabetes and track data such as heart rate and sleep quality (Schwartz et al., 2018). Continuous glucose monitoring (CGM) systems and insulin pumps work together, with sophisticated algorithms that detect low blood sugar levels and halt insulin delivery (Schwartz et al., 2018).

Wearable devices for diabetes management primarily fall into four categories: blood glucose monitoring, therapeutic interventions, exercise interventions and comprehensive management systems (Talaiti et al., 2026). A study by Talaiti et al. (2026) concluded that “wearable devices may benefit glycemic control, exercise management and foot ulcer prevention in diabetic patients, but evidence for preventing diabetic ketoacidosis and improving psychological outcomes remains limited”. This evidence suggests that wearable technologies may be more beneficial for continuous care to prevent diabetic exacerbations than for treating them in the moment. A study by Laffi et al. (2025) further noted that the impact of the wearable technology comes as much from effective implementation, clear goal-setting and seamless integration into the existing solutions of the patient as the technology’s “clinical impact depends on how they are embedded within structured interventions rather than on device sophistication”. This highlights that medical professionals may be more important than ever in ensuring patients use all available tools in the most impactful way possible. 

Wearable technologies show promise in detecting potential cases of diabetes. A study by Yin et al. (2021) combined data from participants collected via wearables such as smartwatches and cell phones, along with a neural network, to diagnose diabetes with 96.3% accuracy. However, the neural network was evaluated on data from the same 52 people it was trained on, meaning these results may differ in a real-world implementation, and a single study is not sufficient evidence to conclude the neural network’s true effectiveness. Despite this, 96.3% accuracy demonstrates the potential to combine wearable technology data with machine learning for diabetes detection. Moreover, because this approach uses obtainable data from widely available connected devices, it may enable more accessible screening. 

Wearable technologies can support healthy behaviours associated with lower risks of type 2 diabetes. A study by Zahedani et al. (2023) of over 1000 participants, including type two diabetics, prediabetics and healthy individuals, utilised a continuous glucose monitor, a food log and a heart rate monitor all fed into an AI program, which would produce actionable goals and activities, like suggesting a specific meal, for the patient. That program resulted in several behavioural changes, including increased intake of healthier foods, weight loss and increased physical activity, though the last was limited to non-diabetics. Lifestyle changes like these have been shown to reduce the risk of getting type 2 diabetes. Therefore, by promoting behaviours that support metabolic health, wearable device-supported programs may help prevent type 2 diabetes. However, while these devices have the potential to benefit people greatly, they can be uncomfortable to wear. They may impose a maintenance burden that reduces adherence to wearable-supported programs, limiting their effectiveness (Schwartz et al., 2018). Additionally, because the intervention combined multiple technologies with AI-generated behavioural recommendations, the findings may not demonstrate that wearable monitoring alone caused these improvements. 

Overall, wearable devices have the potential to be highly useful in diabetes and metabolic health. They have shown effectiveness in treating diabetes, while other studies suggest potential applications in metabolic health, such as automated diabetes screening and promoting behaviours that support good metabolic health. However, these cases should be examined with greater scrutiny.

2.3 Wearable Technologies for Monitoring and Detecting Cancer

Wearable technologies have a variety of uses in cancer care. Step trackers monitor patients’ exercise and have been associated with improved quality of life, mental health and treatment outcomes among cancer patients by increasing physical activity (Singh et al., 2022). Furthermore, wearables are useful for data collection and patient monitoring, with fitness trackers measuring heart rate and sensor systems monitoring gait (Chow et al., 2024). Heart rate monitoring was shown to be useful for detecting fatigue in elderly patients with urothelial carcinoma (Sugiyama et al., 2020). This can potentially be used to help caretakers by warning about complications associated with cancer treatment. However, this detection method was accurate only for fatigue in the study, as heart rate showed no correlation with nausea or constipation (ibid.), highlighting the current limitations of wearable technology in monitoring cancer treatment complications.

Meanwhile, a wearable system of gyroscopes and accelerometers was used to monitor gait in a study meant to test whole-body electromyostimulation’s effectiveness in improving gait and muscle mass for cancer patients, parameters which, from a combination of inflammation from advanced cancer and side effects of treatment, are deteriorating in cancer patients (Schink et al., 2019). The wearable technology helped confirm that the electromyostimulation was effective, and the data gathered was shown to be more accurate than previous testing methods that relied on subjective surveys (ibid.). This demonstrates the utility of wearable technology in longitudinal studies for testing and validating novel therapies to improve the lives of cancer patients. These examples show how wearable technology is already benefiting cancer care, from promoting healthy habits to monitoring and collecting patient data to testing treatments and therapies, keeping doctors more informed about the diseases they seek to treat.

Experimental wearable devices show potential for the early diagnosis and treatment of cancer. For example, microneedles can be modified to perform colorimetry to monitor areas for chemical markers suggesting potential melanoma, though these biomarkers are not equivalent to a clinical cancer diagnosis (Hua et al., 2025). If validated with further clinical testing for longitudinal use, these wearables have the potential to provide cancer monitoring outside a traditional clinical setting. However, current microneedle technology cannot provide real-time data, meaning that full point-of-care testing remains out of reach (Leanpolchareanchai & Nuchtavorn, 2023). This limitation may hamper early detection, as it relies on the rapid identification and communication of clinically important changes. Therefore, while microneedle biomarker detection shows promise, the current state of the technology cannot replace traditional cancer diagnostic pathways. New developments in microneedle technology suggest that they can be used in cancer treatment. Microneedle patches can inject drugs near melanoma tumours, reducing collateral damage compared with intravenous injections, while wearable photosensitisers use light to produce reactive oxygen species at the tumour site (Hua et al., 2025). Both of these examples also use self-sustaining wearable electronics, which may further enhance the mobility of these wearables. Overall, though their use is limited today, wearable technologies are already improving oncology care, and advances in wearables are expected to continue to revolutionise the field.

2.4 Wearable Technologies for Monitoring and Detecting Dermatological and Skin Conditions

Traditional dermatology can only provide periodic assessments and data, whereas wearable technology in dermatology can provide continuous data on skin health when users are at home. Skin-based wearables can measure key features such as skin hydration, scratching and UV exposure using motion sensors and other methods, providing real-time data to assist in in-person assessments (Kololichalil & Gaurav, 2026). Additionally, wound healing and UV exposure can be monitored using wearable devices (Kololichalil & Gaurav, 2026). It is important to distinguish between devices that assess signs of disease and those that monitor factors associated with disease risk. Direct assessment technology can provide information about physical and biological changes in the skin. At the same time, indirect devices monitor and measure factors such as UV radiation and skin hydration, assessing conditions that may be related to changes in skin health (Kololichalil & Gaurav, 2026).

Although consumer interest in wearable skin monitors is growing, significant barriers hinder their integration into clinical practice. Primary concerns include severe variations in hardware and software reliability, data privacy risks and a complete absence of standardised medical interpretation protocols.(Fraiser et al., 2021). Furthermore, issues such as high user variability and usability barriers among elderly users need to be considered. Therefore, further action is required to bridge the gap between current device limitations and clinical standardisation of wearable devices in dermatology.

Wearable medical technology has the greatest clinical impact when deployed for proactive flare management and continuous home-based interventions rather than for static diagnostic screening. While initial diagnostic screening remains constrained by sensor specificity and higher false-positive rates in unmonitored settings, ongoing continuous tracking captures abnormal signs in real time. Timely, targeted therapeutic actions can be taken before a dermatological condition escalates. Consider a novel body-attached wearable OLED medical device for cutaneous wound healing that provides effective, non-invasive treatment (Park et al. 2024). This OLED technology provides uniform light irradiation, which promotes wound healing without compromising patient comfort. This is an example of how wearable devices can significantly enhance patient care and revolutionise light-based therapies in dermatology. 

By integrating lightweight, skin-conformal therapeutics directly into daily routines, such bioelectronic platforms eliminate the physical constraints, thermal risks and spatial non-uniformity associated with conventional clinic-bound light therapies. This demonstrates that wearables do not merely act as passive monitors but also provide treatment delivery systems that enable immediate therapeutic response. Consequently, the integration of targeted therapeutic wearables such as OLED patches shifts dermatological care from reactive, episodic clinical visits to a proactive, continuous and patient-centric management model.

3. The Future of Wearable Technologies

Recent literature points to three main trends in modern wearable technology: AI-powered predictive monitoring, soft skin-interfaced bioelectronics and multimodal sensing that combines physical data with biochemical data. Single-modality wearables provide limited information, whereas multimodal or hybrid systems combine different signals that may support earlier risk protection and yield better, more personalised and clinically valuable health assessments (Kim, Ding & Wang 2026; Ray et al., 2019).

There is still significant uncertainty about how much autonomy or independence AI should have in clinical decision-making. Research emphasises the importance of human oversight of AI due to concerns about interpretation, patient safety and related issues. However, AI research is increasingly focused on rapid, automated analysis for integration into clinical workflows (Patel, 2026; Topol, 2019). This suggests that in the near future, AI will be more likely to be used as a monitored tool rather than as something completely autonomous in clinical decision-making. 

There is also a clear disparity between what wearable technology can currently do and what future research predicts it will be able to do. Wearable ECG, PPG, pulse oximetry and continuous glucose monitors already have clinical applications, although their effectiveness can vary across conditions (Dunn Runge & Snyder 2018; Lodewyk et al., 2025). In contrast, technologies like non-invasive glucose monitoring and more autonomous treatments remain in the early stages of development. In 2024, the FDA warned that no smartwatch or ring had been authorised to measure blood glucose levels without skin penetration (FDA, 2024). This shows the gap between commercial claims and real-world application, as evidenced by the approval barrier.

For wearables to shift from wellness trackers to broader clinical use, several barriers must be addressed. Frameworks such as the HL7 FHIR (Fast Healthcare Interoperability Resources) specification can help integrate data into electronic health records (HL7 International, 2023). Regulation also must allow controlled updates to machine learning systems while maintaining user safety. The guidance from the FDA, Health Canada and the MHRA provides an example of how planned changes to AI in clinical settings can be safely managed. Widespread adoption of wearable technology will also need sufficient cybersecurity, clinical workflow integration and funding.

Ultimately, wearables are likely to support a shift from reactive, occasional healthcare to constant, preventive healthcare. However, predictions of fully autonomous diagnostic platforms in the near future are beyond what research shows, constantly supporting the human oversight model of clinical implementation. In the near future, wearable technology is more likely to become high-quality tools that are used within clinical spaces rather than replacing entire systems. Wearables with human oversight can help identify and prevent health issues earlier than without it.

4. Conclusion

Wearable technology has transformed medicine in various ways and has the potential to benefit more in the future. Examples include advances in detecting and monitoring respiratory diseases, diabetes and metabolic conditions, cancer and dermatological conditions. As healthcare moves from reactive treatment to proactive preventive care, wearable technology enables continuous monitoring of relevant biomarkers. The wide range of relevant biomarkers tracked by wearable technologies includes respiratory rate, oxygen saturation, heart rate, sleep quality, glucose levels, gait, skin hydration and UV exposure. From general-use consumer-based wearable technology to more specialised medical devices, this technology has found its way into many fields of medicine. 

In pulmonology, wearable technologies are already demonstrating the ability to monitor and possibly prevent exacerbations in conditions such as asthma and COPD. In endocrinology, wearable technologies have already shown effectiveness in treating diabetes and applications in metabolic health. In oncology, wearable technologies have shown potential for early cancer detection and proactive treatment. In dermatology, wearable technology has shown benefits in proactive flare management and continuous home-based interventions. Wearable technology also shows promise for integrating with other technologies, including AI and machine learning, to enable early disease detection. 

However, wearable technology faces a variety of challenges that prevent it from reaching its full potential. These challenges include data privacy concerns, low sensor accuracy, low patient adherence due to discomfort, lack of data storage infrastructure and interoperability issues. Despite these drawbacks, wearable technologies have a bright future in medicine, expanding access to medical care and improving the effectiveness of medical treatment.

Abdulsadig, R.S., Devani, N., Singh, S., Patel, Z., Pramono, R.X.A.P., Mandal, S. and Rodriguez-Villegas, E. (2024) ‘Clinical validation of respiratory rate estimation using acoustic signals from a wearable device’, Journal of Clinical Medicine, 13(23), 7199.

Al Rajeh, A.M. and Hurst, J.R. (2016) ‘Monitoring of physiological parameters to predict exacerbations of chronic obstructive pulmonary disease (COPD): A systematic review’, Journal of Clinical Medicine, 5(12), 108.

Armstrong, M. (2026) ‘Modernisation of chronic respiratory disease management: The integration of wearable technology’, Chronic Respiratory Disease, 23, pp. 1–14.

Center for Devices and Radiological Health (2024) Do not use smartwatches or smart rings to measure blood glucose levels: FDA safety communication. U.S. Food and Drug Administration. <https://www.fda.gov/medical-devices/safety-communications/do-not-use-smartwatches-or-smart-rings-measure-blood-glucose-levels-fda-safety-communication>

Chow, R., Drkulec, H., Im, J.H.B., Tsai, J., Nafees, A., Kumar, S., Hou, T., Fazelzad, R., Leighl, N.B., Krzyzanowska, M., Wong, P. and Raman, S. (2024) ‘The use of wearable devices in oncology patients: A systematic review’, The Oncologist, 29(4), e419–e430.

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.

Dinh-Le, C., Chuang, R., Chokshi, S. and Mann, D. (2019) ‘Wearable health technology and electronic health record integration: Scoping review and future directions’, JMIR mHealth and uHealth, 7(9).

Doherty, C., Baldwin, M., Keogh, A., Caulfield, B. and Argent, R. (2024) ‘Keeping pace with wearables: A living umbrella review of systematic reviews evaluating the accuracy of consumer wearable technologies in health measurement’, Sports Medicine, 54, pp. 2907–2926.

Dunn, J., Runge, R. and Snyder, M. (2018) ‘Wearables and the medical revolution’, Personalized Medicine, 15(5), pp. 429–448.

Eisenkraft, A., Goldstein, N., Ben Ishay, A., Fons, M., Tabi, M., Sherman, A.D., Merin, R. and Nachman, D. (2023) ‘Clinical validation of a wearable respiratory rate device: A brief report’, Chronic Respiratory Disease, 20, 14799731231198865.

Fraser, R.A., Walker, R.J., Campbell, J.A. et al. (2025) ‘Integration of artificial intelligence and wearable technology in the management of diabetes and prediabetes’, npj Digital Medicine, 8(1), 687.

Frasier, K., Li, V., Sobotka, M., Vinagolu-Baur, J. and Herrick, G. (2024) ‘The role of wearable technology in real-time skin health monitoring’, JEADV Clinical Practice, 4, pp. 21–29.

George, A.S.H., Shahul, A. and George, D.A.S. (2023) ‘Wearable sensors: A new way to track health and wellness’, Partners Universal International Innovation Journal, 1(4), pp. 15–34.

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(1), 102.

HL7 International (2026) Personal Health Device Implementation Guide Home Page – Personal Health Device Implementation Guide v2.0.0. <https://build.fhir.org/ig/HL7/phd/en/>

Hua, Z., Dai, C., Yang, Y. and Song, Y. (2025) ‘Wearable bioelectronics for cancer theranostics’, Microsystems & Nanoengineering, 11(1), 180.

Hussain, T., Ullah, S., Fernández-García, R. and Gil, I. (2023) ‘Wearable sensors for respiration monitoring: A review’, Sensors, 23(17), 7518.

Iqbal, M.H., Aydin, A., Brunckhorst, O., Dasgupta, P. and Ahmed, K. (2016) ‘A review of wearable technology in medicine’, Journal of the Royal Society of Medicine, 109(10), pp. 372–380.

Iqbal, S.M.A., Mahgoub, I., Du, E., Leavitt, M.A. and Asghar, W. (2021) ‘Advances in healthcare wearable devices’, npj Flexible Electronics, 5(1), 9.

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.

Kim, B., Ding, S. and Wang, J. (2026) ‘Wearable multimodal sensing for geriatric healthcare’, Soft Science, 6(2), 26.

Kim, D., Ahmed, S.S., Amjad, A., Won, K. and Xian, X. (2026) ‘Integrating Artificial Intelligence with Wearable Sensors for Advanced Health Monitoring and Diagnosis’, Biosensors, 16(6), 344.

Kololichalil, A. and Gaurav, V. (2026) ‘Wearables in dermatology: Quiz on next-generation technical advances’, Indian Journal of Postgraduate Dermatology, 4(1), pp. 146–153.

Laffi, A., Persiani, M., Piras, A., Meoni, A. and Raffi, M. (2025) ‘Effectiveness of wearable technologies in supporting physical activity and metabolic health in adults with type 2 diabetes: A systematic-narrative hybrid review’, Healthcare, 13(19), 2422.

Leanpolchareanchai, J. and Nuchtavorn, N. (2023) ‘Wearable microneedle-based colorimetric and fluorescence sensing for transdermal diagnostics’, Talanta Open, 8, 100247.

Liao, Y., Thompson, C., Peterson, S., Mandrola, J. and Beg, M.S. (2019) ‘The Future of Wearable Technologies and Remote Monitoring in Health Care’, American Society of Clinical Oncology Educational Book, 39(39), pp. 115–121.

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.

Niu, Q., Li, H., Liu, Y., Qin, Z., Zhang, L., Chen, J. and Lyu, Z. (2024) ‘Toward the Internet of Medical Things: Architecture, trends and challenges’, Mathematical Biosciences and Engineering, 21(1), pp. 650–678.

Park, Y., Choi, H.-R., Shin, J.W., Huh, C.-H. and Choi, K.C. (2024) ‘A wearable OLED medical device for enhanced cutaneous wound healing and patient comfort: Revolutionizing dermatology’, Journal of Information Display, 25(2), pp. 151–156.

Patel, B. (2026) ‘The role of AI-integrated wearables in predictive healthcare: A scoping review’, Journal of Medical Artificial Intelligence, 9, 26.

Patel, V., Orchanian-Cheff, A. and Wu, R. (2021) ‘Evaluating the validity and utility of wearable technology for continuously monitoring patients in a hospital setting: Systematic review’, JMIR mHealth and uHealth, 9(8), e17411.

Qadrie, Z., Ashraf, H., Maqbool, M. and Farooq, S. (2025) ‘Wearable Technology in Healthcare: Opportunities, Challenges, and Future Directions’, Smart Wearable Technology, pp. 1–17.

Radanliev, P. (2025) ‘Privacy, ethics, transparency, and accountability in AI systems for wearable devices’, Frontiers in Digital Health, 7.

Ray, T.R., Choi, J., Bandodkar, A.J., Krishnan, S., Gutruf, P., Tian, L., Ghaffari, R. and Rogers, J.A. (2019) ‘Bio-integrated wearable systems: A comprehensive review’, Chemical Reviews, 119(8), pp. 5461–5533.

Schink, K., Gaßner, H., Reljic, D., Herrmann, H.J., Kemmler, W., Schwappacher, R., Meyer, J., Eskofier, B.M., Winkler, J., Neurath, M.F., Klucken, J. and Zopf, Y. (2020) ‘Assessment of gait parameters and physical function in patients with advanced cancer participating in a 12-week exercise and nutrition programme: A controlled clinical trial’, European Journal of Cancer Care, 29(2), e13199.

Schwartz, F.L., Marling, C.R. and Bunescu, R.C. (2018) ‘The promise and perils of wearable physiological sensors for diabetes management’, Journal of Diabetes Science and Technology, 12(3), pp. 587–591.

Singh, B., Zopf, E.M. and Howden, E.J. (2022) ‘Effect and feasibility of wearable physical activity trackers and pedometers for increasing physical activity and improving health outcomes in cancer survivors: A systematic review and meta-analysis’, Journal of Sport and Health Science, 11(2), pp. 184–193.

Sugiyama, Y., Naiki, T., Tasaki, Y., Kataoka, T., Mimura, Y., Kondo, Y., Etani, T., Iida, K., Nozaki, S., Ando, R., Osaga, S., Yasui, T. and Kimura, K. (2020) ‘Effectiveness of continuous monitoring by activity tracker of patients undergoing chemotherapy for urothelial carcinoma’, Cancer Treatment and Research Communications, 25, 100245.

Talaiti, M., Liao, X., Abulimiti, N., Zeng, M. and Wang, Y. (2026) ‘Effectiveness of wearable devices for diabetes management: An overview of systematic reviews and meta-analyses’, Journal of Diabetes Research, 2026, 1464982.

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

U.S. Government Accountability Office (2026) Wearable Technologies: Potential Benefits and Challenges in Clinical Decision-Making, GAO-26-107847 (Washington, D.C.: U.S. Government Accountability Office).

Vitazkova, D., Foltan, E., Kosnacova, H., Micjan, M., Donoval, M., Kuzma, A., Kopani, M. and Vavrinsky, E. (2024) ‘Advances in respiratory monitoring: A comprehensive review of wearable and remote technologies’, Biosensors, 14(2), 90.

Wang, S., Lafaye, C., Saubade, M., Besson, C., Margarit-Taule, J.M., Gremeaux, V. and Liu, S.-C. (2022) ‘Predicting Hydration Status Using Machine Learning Models From Physiological and Sweat Biomarkers During Endurance Exercise: A Single Case Study’, IEEE Journal of Biomedical and Health Informatics, 26(9), pp. 4725–4732.

Xiao, X., Yin, J., Xu, J., Tat, T. and Chen, J. (2024) ‘Advances in Machine Learning for Wearable Sensors’, ACS Nano, 18(34), pp. 22734–22751.

Xu, S., Kim, J., Walter, J.R., Ghaffari, R. and Rogers, J.A. (2022) ‘Translational gaps and opportunities for medical wearables in digital health’, Science Translational Medicine, 14(666).

Yin, H., Mukadam, B., Dai, X. and Jha, N.K. (2021) ‘DiabDeep: Pervasive diabetes diagnosis based on wearable medical sensors and efficient neural networks’, IEEE Transactions on Emerging Topics in Computing, 9(3), pp. 1139–1150.

Zahedani, A.D., McLaughlin, T., Veluvali, A., Aghaeepour, N., Hosseinian, A., Agarwal, S., Ruan, J., Tripathi, S., Woodward, M., Hashemi, N. and Snyder, M. (2023) ‘Digital health application integrating wearable data and behavioral patterns improves metabolic health’, npj Digital Medicine, 6(1), 216.