Wearable devices in neurological disorders: a narrative review of status quo and perspectives

Introduction

Neurological disorders, as the primary contributor to disability and the second leading cause of mortality worldwide, have led to a significant increase in both mortality and disability rates over the past three decades (1). Neurological disorders affect the brain, spinal cord, muscles, neuromuscular junctions, and peripheral nerves (2). Vascular, degenerative, and metabolic conditions, as well as infections, cancers, and trauma affecting the nervous system, are representative of this category (3). Clinical manifestations commonly include motor and sensory dysfunctions, cognitive impairments, and disorders of consciousness. Despite significant progress in the prevention and management of neurological diseases, the current healthcare model remains hospital-centered. There is a pressing need to focus on innovative approaches for early detection, real-time monitoring, and personalized rehabilitation strategies.

Wearable devices, also known as wearables, are electronic devices worn by individuals to capture and monitor physiological and functional metrics both within and beyond clinical environments. These devices work by collecting data on a continuous, scheduled, or event-driven basis. The data collected encompasses physiological, biochemical, and imaging information. Wearable devices are mainly utilized for health and safety monitoring, disease diagnosis, chronic disease management, and treatment and rehabilitation processes. The expanding adoption of wearable technology, evidenced by a significant increase in user penetration from 28% to 30% in 2019 to 36.36% in 2022 (4), has synergistically propelled growth in the neuromedical wearable market. Their capacity to record, store, and analyze data renders them valuable tools for the ongoing management of neurological disorders (5).

In this review, we aim to assess the landscape of wearable technology in neurological diseases and propose directions for further research. We delve into specific modules and parameters of wearable technologies that are pertinent to neurological diseases, and analyze the limitations and future development prospects of wearable technology. We present this article in accordance with the Narrative Review reporting checklist (available at https://atm.amegroups.com/article/view/10.21037/atm-25-46/rc).

Methods

We conducted the review by systematically searching papers prior to and including May 31, 2025, in PubMed, Web of Science, and Science Direct (Table 1 and Table S1). The keywords included “wearable devices”, “wearable technology”, “wearables”, “sensor”, “motor function”, “gait”, “activities of daily living”, “neurology”, “nervous system diseases”, and “neurological”. After removing duplicates, we screened titles, abstracts, and then full-text for inclusion. Peer-reviewed studies on the application of wearable devices and wearable technology in neurology and neurological disorders were included, while non-English publications, animal studies, and case reports were excluded. We summarized the present development status of wearable devices, and outlined the potential value and future direction for further research.

Contemporary diagnostics and therapeutic scenarios in neurological disorders

Neurological disorders are a group of heterogeneous diseases mostly characterized by motor and sensory dysfunctions. In severe cases, respiratory insufficiency, cardiovascular involvement, disorders of consciousness, or death may occur (6). The diagnosis relies on physical examination, patient-reported outcomes, tests on blood and cerebrospinal fluid, electrophysiological examination, neuroimaging, biopsy, genetic testing, etc. The contemporary landscapes of neurological disorders are shown in Figure 1.

Figure 1 Contemporary landscapes of neurological disorders. Representative diseases of the nervous system (column 2), commonly assessed contents of wearable devices for diagnosis and follow-up (column 1), and commonly utilized devices for treatment and rehabilitation (column 3). ADL, activity of daily living.

Here, we provide a concise overview of several prevalent nervous system disorders. Stroke, a common form of cerebrovascular disease, is the second leading cause of death and the third leading cause of disability in adults globally (7). Alzheimer’s disease (AD) is the most common neurodegenerative disorder and the main cause of dementia, which gives rise to adverse health outcomes and burdens people with AD (8). Parkinson’s disease (PD) is the second most common neurodegenerative disorder and lacks satisfactory treatment options (9). Epilepsy is a multifaceted symptom complex that impacts over 70 million individuals globally (10). Neuromuscular diseases (NMDs), such as amyotrophic lateral sclerosis (ALS), are inherited or acquired diseases involving the anterior horn neurons, nerve roots and plexuses, peripheral nerves, neuromuscular junctions, and muscles (11). NMDs are relatively rare individually but collectively have a prevalence similar to PD or multiple sclerosis (12). The prevalence and the potentially poor prognosis of neurological disorders highlight the considerable demand for novel measurement tools. Early diagnosis, long-term monitoring, and timely intervention are crucial for slowing progression, reducing disability rate, and alleviating the disease burden.

Clinical diagnosis and follow-up primarily assess motor functions, deep and superficial sensations, cognitive functions, and bio-electrical signals. A significant challenge is the limited accessibility of routine detection methods, which require professional equipment and personnel, posing difficulties for people with mobility limitations due to neurological disorders. Assessments may be influenced by examiner competence, examinees’ cognitive ability, and the empirical effects of repeated testing. Meanwhile, examinations in medical centers are time-consuming, with limited continuity and sensitivity to detect subtle changes. There is an urgent need for mobile, sustainable, and wearable devices to extend follow-up from the healthcare facilities to the community and home.

Regardless of treatability, physical and occupational therapy, speech therapy, and mobility assistance are often necessary, particularly for patients with chronic or hereditary disorders. Yet the accessibility of rehabilitation hospitals is a significant barrier. Conducting rehabilitation treatments outside rehabilitation centers, such as at home, would enhance convenience and compliance. People with severely impaired motor function urgently require assistive devices.

Wearables in neurological assessment: enhancing diagnostic and follow-up practices

Motor function assessment

Wearable devices for disease management and clinical trials of neurological disorders are depicted in Figure 2. Muscle weakness and the resulting motor dysfunction are the core symptoms of NMDs, such as ALS, spinal muscular atrophy (SMA), myasthenia gravis (MG), Guillain-Barré syndrome (GBS), and are also frequently observed in cerebrovascular diseases like stroke (13). Skeletal muscle strength, defined as the maximum force a muscle can generate in a single effort, is typically assessed using manual muscle testing, and sometimes by hand-held dynamometry (14). These methods, however, provide only discrete data, they are limited by their requirement for well-trained personnel and are subject to the ceiling effect (15). The continuous, long-term assessment of muscle strength in daily life is thus a challenging but valuable research area. To address these limitations, wearable devices incorporating force sensors have been developed to measure flexion and extension strength of joints (16). Certainly, it would be ideal to validate any of these devices against the gold standard to ensure their reliability and accuracy. Some devices utilize soft strain sensors to track muscle strength based on muscle deformation, although these may be influenced by clothing and anatomical variances (17). Ocular muscle strength may be evaluated by head-mounted eye trackers that track eye movements (18). The strength test of the facial, neck, and respiratory muscles remains an underexplored area in this context. There are some portable tools, and the ErgoLAB^® multi-channel smart wearable system is designed to synchronously acquire parameters, including facial, neck, and respiratory muscles. Even so, the overall number of wearables is limited; wearable devices specifically designed for measuring a particular muscle strength remain relatively scarce.

Figure 2 Wearable devices for the diseases management and clinical trials of neurological disorders. Representative wearable devices (top) and their typical applications (bottom). ADL, activity of daily living; BCI, brain-computer interface; EEG, electroencephalogram; EMG, electromyography.

The joint range of motion (ROM) refers to the active and passive ROM exhibited by each individual joint. It is a pivotal metric in various neurological conditions, including trauma, immobilization, and abnormal muscle force. Traditional ROM assessments conducted manually or with a goniometer are time-consuming and restricted to static measurements. In contrast, wearable devices employ gravity, angle, and inertia sensing technologies for dynamic ROM assessment, enhancing measurement accuracy and efficiency (19). A three-dimensional (3D)-printed tool with rotary position sensors has shown high accuracy and repeatability in knee-joint movement measurements (20). A significant challenge in wearable technology is the accurate and continuous monitoring of ROM outside clinical settings, as movements from other body parts can confound the results. Harvard University presents a wearable ultrasound device for capturing joint torque during dynamic activities (21). Such devices not only broaden our understanding of human kinesiology but are also crucial for refining rehabilitation plans and reducing the demand for inpatient rehabilitation. Future developments may include prompting users to perform specific movements for increased accuracy and enabling longitudinal analyses to track disease progression in real time, thereby improving the management of neurological disorders.

Gait refers to the behavioral characteristics of walking, encompassing both static and dynamic features like stride length, frequency, and upper body stability (22). The analysis of gait parameters helps to early diagnosis, identification of disease stages, and evaluation of treatment efficacy. Abnormal gait patterns, such as ataxic gait in cerebral palsy, hemiplegic gait post-stroke, and festinating gait in PD, are also associated with an increased risk of falls and diminished quality of life, which calls for more accurate and convenient tools for examination (23,24). Conventional approaches involve visual observation and semi-quantitative scales like the Berg Balance Scale and Dynamic Gait Index. Quantitative data is obtained from a stopwatch, goniometer, mechanical sensor, electromyography (EMG), or high-speed photography (25). Wearable instruments, particularly inertial measurement units (IMUs) affixed to limbs or trunk, enable continuous monitoring with minimal discomfort while demonstrating proven objectivity, convenience, sensitivity, and specificity in detecting gait and balance alterations (26,27). Other applications include IMUs combined with machine learning for accurate step-length measurement, and insoles or shoes with force sensors to measure force interactions between the body and the ground (28,29). Moreover, integration with smart devices may allow for long-term data capture, facilitating the utility of these data (Figure 3).

Figure 3 Integration of wearable devices with other technologies.

Bradykinesia and tremor, predominantly associated with PD and parkinsonism, require more precise detection methods. Accelerometers, gyroscopes, and magnetometers are commonly employed sensors. Accelerometers serve as a potent and cost-effective tool for identifying individuals at risk and for monitoring motor functions in clinical settings (30). IMUs capture motion parameters from various parts of the body, thereby assisting clinicians in the diagnosis and monitoring of PD (31). For instance, the Parkinson’s Kineti Graph (Global Kinetics Corporation™, Melbourne, Australia) has shown satisfactory sensitivity and specificity in detecting dyskinesia in PD, making it a promising tool in long-term follow-up (32).

Activity of daily living (ADL) analysis

ADL involves fundamental skills for self-care and serves as a comprehensive manifestation of the functions of the nervous system (33). Timed tests like the 6-minute walk test (6MWT) and the Timed Up and Go (TUG) test are often used clinically to evaluate walking function and aerobic exercise capacity (34). However, these may not be suitable for those with severe weakness. ADL can be quantified using scales such as the modified Rankin scale (mRS). They are always based on the difficulty of independent performance, making it challenging to detect minor changes.

Wearable devices provide a time-efficient approach for continuous data collection in unsupervised settings. For example, a bodysuit equipped with sensors is capable of quantifying daily activities and exhibits a strong correlation with common clinical scales in NMDs, such as muscular dystrophy. The data collected can track disease progression and therapeutic response, suggesting its potential for remote follow-up (35). Moreover, a previous study has demonstrated that wearable devices incorporating artificial intelligence, especially machine learning, are well-suited for complex computational analysis and can provide more sensitive assessments of disease severity than traditional clinical scales. For example, equipped with machine learning models, limb-worn IMUs serve as sensitive measures of motor function in ALS. This method has the potential to reduce trial costs, facilitate virtual clinical trials, and enable at-home assessments for routine clinical care (36).

Upper limb-specific wearables, such as the AUTOMA sleeve, combine ROM and muscle strength assessment for quantitative and early-stage measurement of upper limb muscle injuries (37). Notably, future wearable devices should consider variations in upper limb movement patterns between wheelchair users and those who can walk unassisted. Wearable ultrasound imaging and sensing systems integrate EMG, mechanomyography, and ultrasound images to capture both external and internal muscle activity, offering new knowledge into muscle contraction patterns in people with neurological disorders (38). The application of this technology requires further research to understand muscle contraction patterns and disease impacts on muscular changes.

Detection and evaluation of other neurological dysfunction

Sensory dysfunction in neurological disorders affects superficial, deep, and cortical sensations, manifesting as hypesthesia, paresthesia, hyperesthesia, and sensory ataxia. This is frequently observed in peripheral neuropathies, such as diabetic peripheral neuropathy (DPN) and GBS. The clinical evaluation of sensory function encompasses pain, temperature, and vibration senses, yet given that sense is subjective to a large extent, accurately quantifying the assessment outcomes presents a formidable challenge. The absence of wearable devices significantly limits follow-up outside clinical settings. Future research may yield wearable devices, such as wristbands or anklets, that apply pressure, alter temperature, or emit vibrations to evaluate sensory thresholds quantitatively.

Cognitive function comprises attention, perception, learning, and memory. Existing tools for cognitive assessment rely on professionals and clinical centers, which limits their ability to capture long-term fluctuations. The convenience of mobile and wearable devices may enable their application for home-based cognitive assessment. Mobile devices are mobile versions of existing cognitive tests, despite sufficient accuracy, they are not suitable for prolonged and frequent assessment of cognitive capacities (39). A wearable device called Cognition Kit is designed to effectively assess key cognitive domains while ensuring high user compliance. Its feasibility and validity for high-frequency and long-term assessment of cognition have been demonstrated (40). The Ubiquitous Cognitive Assessment Tool, a watch-like wearable device, is designed for cognitive assessment in real-world settings. It allows patients to assess their attention and memory without experiencing discomfort, thereby increasing their engagement and interest (41). Nevertheless, a cause for concern is that individuals with physical or cognitive disabilities may encounter potential challenges in using these devices.

In addition to physical sensors, bioelectrical signals may also serve a function in wearable technology. Despite the precision, needle EMG is invasive and costly, making it unsuitable for continuous or frequent measurement. Surface EMG (sEMG) is a non-invasive method that measures muscle activity signals, such as tone, tremor, and myoclonus (42). High-density sEMG facilitates gait analysis and could be instrumental in acquiring dynamic electrophysiological data for disease progression monitoring (43). Machine learning algorithms can enhance the accuracy of wearable sEMG by modeling and quantifying body motion (44). Furthermore, wearable EMG devices are capable of precise and long-term wireless monitoring of physical activities (45). DPNCheck^® (Neurometrix, Waltham, MA, USA), a novel device that measures sural nerve conduction, acts as a sensitive, specific, quantitative, and convenient tool for the screening and assessment of peripheral neuropathies, especially DPN (46). However, capturing the spatial characteristics of walking patterns remains challenging outside laboratory settings, and EMG is also limited by transmission performance and spatiotemporal resolution.

The electroencephalogram (EEG) serves as a vital tool for diagnosing epilepsy and monitoring changes in the central nervous system. Long-term EEG monitoring is essential due to the chronic nature of epilepsy (10). Conventional scalp EEG is limited by its high cost, discomfort, and time-consuming nature. Noninvasive EEG has been developed to overcome these limitations. A study has indicated its comparability to traditional EEG concerning specificity and sensitivity when detecting EEG abnormalities and epileptic seizures (47). Wearable EEG also demonstrates the potential to screen for cognitive impairment and predict dementia onset (48,49). Wireless ear EEG that has emerged in recent years has further improved the portability and comfort of wearing (50). Future developments may include novel electrode materials, reduced electrode counts, advanced algorithms, and integration with smart devices.

Management of neurological disorders with systemic involvement

Apart from the nervous system and the musculoskeletal system, neurological disorders can also affect other systems, which can initially be asymptomatic and ignored. In NMDs such as Duchenne muscular dystrophy, dystrophia myotonica, and systemic amyloidosis, cardiac involvement is common and may result in sudden cardiac death (51). GBS is associated with autonomic dysfunction, manifesting as fluctuations in blood pressure or heart rate (52). Long-term cardiac monitoring via wearable electrocardiograms is beneficial, and wearable ultrasonic devices for real-time, non-invasive monitoring of central blood pressure and cardiac function is becoming an up-and-coming choice for acute progressive diseases (53). Respiratory complications, such as acute respiratory failure in GBS and myasthenic crisis, and progressive decline in ventilatory function in ALS and Duchenne muscular dystrophy, highlight the need for respiratory management (54). Wearable devices for respiratory rate, respiratory volume, and pulmonary function offer early warning of dyspnea (55). A bioadhesive ultrasound (BAUS) device features the function of continuously imaging various internal organs, including muscle, heart, and lungs (56). Notably, while consumer-grade wearables demonstrate the feasibility of continuous vital sign monitoring, the accurate and reliable tracking of subtle fluctuations in heart rate, blood pressure, and respiratory rate necessitates specialized devices equipped with higher sensitivity, enhanced stability, and clinically validated algorithms. For the prevention and control of DPN, continuous glucose monitoring via wearable devices is crucial (57). Moreover, wearable trackers can screen and assess anxiety, depression, and sleep disorders resulting from neurological disorders by capturing relevant biological signals (58).

Wearable technology in neurological rehabilitation: advances and applications

Exoskeletons in neurological rehabilitation: enhancing motor function and reducing complications

A man with motor dysfunction usually requires rehabilitation to restore muscle strength and functionality, mitigating muscle atrophy and related complications and enhancing quality of life. Exoskeletons offer an alternative to traditional rehabilitation methods that has fewer limitations on the location. These devices also contribute to the establishment of correct motor patterns and a good foundation for walking unaidedly in the future (59). Exoskeletons have demonstrated positive impacts on complications such as spasticity, osteoporosis, and cardiovascular diseases (60). Furthermore, the progression or recovery of diseases can also be evaluated with exoskeletons (61). The limitations involve the cumbersome and costly equipment, along with the requirement for professional guidance regarding appropriate wearing and operation (62).

The cyborg Hybrid Assistive Limb (HAL^®), integrating cybernetic technology, allows for voluntary movement and has been approved by the Food and Drug Administration (FDA) for medical rehabilitation (63). Its efficacy in gait training has been proven to surpass that of conventional devices, attributed to its ability to establish connections within the nervous system and induce neuroregeneration and plasticity (64). Additionally, a lightweight and flexible exoskeleton developed for paralytic person has shown potential in improving walking strength while preventing foot drop, a prevalent symptom post-stroke (65). Such a lightweight, hinge-free, and non-restrictive device can reduce users’ burden and signify a future direction for wearable technology in rehabilitation. In short, exoskeletons provide support for limb movements, assist in physical and occupational therapy, and improve motor capabilities while mitigating complications from long-term mobility restrictions.

A wearable sensor-based training system is expected to provide a safe, efficient, personalized training platform for people with neurological disorders and benefit their motor function (66). Rehabilitation robots can use a biofeedback system for user performance monitoring and instant data feedback to analyze rehabilitation efficacy. This can further contribute to the adjustment in rehabilitation programs and early fall risk detection. We look forward to applying wearable EMG in physical therapy for a more precise and individualized rehabilitation plan.

Brain-computer interface (BCI) and eye trackers

The BCI or brain-machine interface (BMI) is an innovative technology for human-machine interaction. This technology utilizes the electrical signals of the brain to control external devices such as computer cursors, prosthetic limbs, and voice generators, thereby establishing a connection between machines and the human brain (67). The BCI aims to restore movement and communication abilities in patients with neurological diseases, especially stroke, ALS, and traumatic brain disorders (68). Invasive BCIs, while providing higher-quality neural signals, are directly implanted in the brain and may be associated with immune reactions and tissue proliferation that can degrade signal quality. Non-invasive devices are convenient to wear but record a limited amount of neuronal activity and cannot capture signals from deep within the brain. Current research is working to overcome these limitations by developing new materials, utilizing different types of electrodes and probes, and increasing the number of channels (69). Besides, the brain-spine interface (BSI) is an implanted device that restores the digital bridge between the brain and spinal cord and enables paralytic individuals to stand and walk independently (70). The BSI has also enhanced participants’ neurological rehabilitation and mobility. The eye tracker monitors eye movements and serves as another augmentative and alternative communication (AAC) device for individuals with difficulties in speaking or spelling. It may also be integrated with the BCI to further improve the living quality of people with limited motor function (71). Most of these devices are still in the experimental stage, and their potential remains to be further realized.

Other applications in neurological rehabilitation

In addition to the above-mentioned, wearable devices can also have an impact in numerous other fields. The Cala kIQ system (Cala Health, San Mateo, CA, USA) is the first device approved by the FDA for the temporary alleviation of PD, which further improves the ADL of users. An evoked gamma therapy system has shown potential advantages in the relief and treatment of AD (72). A miniaturized wearable ultrasound device MiniUITra turns out to be a promising non-invasive method for transcranial focused ultrasound, contributing to the long-term at-home neuromodulation for neurodegenerative and psychiatric conditions (73). The wearable sensory neuroprosthesis can provide targeted neurostimulation and restore lost sensations to those suffering from peripheral neuropathy, such as diabetes (74). There are also wearable devices that can monitor the drug pharmacokinetics noninvasively or even realize self-administration; this is of value if it can be realized for the medicine of neurological diseases (75).

Bridging the gaps: opportunities for wearables in neurology and challenges ahead

Wearable devices represent a promising new option for the management of neurological disorders. They can function as electronic biomarker detectors to facilitate early detection and expand the data collection beyond traditional clinical visits, allowing users to detect tiny changes without the assistance of experts. They can also serve as auxiliary devices for people with limited mobility and assist in neural rehabilitation. Wearable devices can enhance the users’ compliance and the pertinence of the therapy (76).

Wearable devices should be integrated with decentralized clinical trials (DCTs), which refer to expanding clinical trial sites beyond medical centers. The advantages of DCT include increased flexibility, reduced cost and time, and enhanced accessibility. This is particularly suitable for those with limited motor ability or in remote areas and can potentially improve their willingness to participate in the trials (77). For instance, in a trial for individuals with mild cognitive impairment, a wearable medical-grade device was used for continuous collection of various physiological data. It predicted function scores with high correlation. The application of wearable technology in DCT can reduce patient burden, expand our understanding of neurological diseases, especially rare ones, and assist in the research and development of new therapies.

Indeed, challenges persist in the extensive application of wearable technology. Firstly, there are technical issues. Concerning hardware, it is essential to improve its safety, stability, sensitivity, and practicability, as well as exploring lighter and more durable materials, especially electrodes and sensors. Regarding functions to be accessed, existing wearables mainly focus on gross motor function, with the evaluation of fine motor, sensory, and cognitive function still uncommon. The future of wearable technologies may involve these points. Efforts are needed to create wearable technologies capable of detecting muscle strength in the face and neck, and bands on extremities for assessing superficial and profound sense. Non-invasive but precise equipment to obtain bioelectrical signals will also be crucial, since wearable EMG and EEG hold promise for enabling more individualized follow-up and rehabilitation strategies. In addition to data collection, efficient technology or software for data processing and integration is also necessary. Furthermore, if the collected data are incompatible with the hospital’s electronic medical record system or the wearable systems are not interoperable with one another, the value of the device will be diminished. Wearables are anticipated to be integrated with smart terminals, wireless communication, artificial intelligence, and big data (Figure 3).

While technical innovations enable higher-quality monitoring, their clinical validation remains constrained. Limited research has been conducted on real-life, home-based assessments, underscoring the discrepancy between real-world experiences and research settings (78). Meanwhile, each device possesses specific characteristics that may limit the generalization of data, including the establishment of cutpoints. Larger-scale clinical studies and multi-center cooperation may represent a feasible approach. This will enable comparisons between different devices and methods, gain insights into the correlation between changes in electronic biomarkers and disease progression, and determine the normal range or cutoff value of certain metrics.

Practical implementation also matters. Expense and technical complexity may act as barriers in real-world adoption. Many commercial wearable devices, such as robotic exoskeletons, incur significant costs. The difficulty of operating hardware devices and smartphones can reduce usability, especially among the elderly and digitally marginalized populations. Besides, most wearable devices are worn on limbs, with a design resembling a wristband or watch, thereby minimizing disruption to regular activities and aesthetic appeal. Nonetheless, people are limited to simultaneously wearing only one device at the exact location. The convenience and acceptability of wearables are expected to increase with the development of multifunctionality significantly. Researchers should develop a platform that allows users to choose specific modules based on the particular disease and its characteristics, such as motion-oriented or sensory-oriented, proximal or distal involvement, to optimize functional matching. This is crucial for the customization of wearable devices. Finally, regulatory frameworks are expected to be challenged in standardizing evaluation criteria for rapidly evolving wearables, which serves as a bottleneck requiring collaborative industry-academia initiatives. Special attention should be given to data security, as well as ethical and legal concerns that follow. There is also a need for unified industry standards.

Conclusions

The results of this review suggest that wearable devices have demonstrated significant potential for extensive applicability across a wide spectrum of neurological disorders, involving motor, sensory, and cognitive dysfunctions. They have proven to be of substantial value both in the clinical follow-up and rehabilitation. However, while promising, its widespread practical implementation still has a challenging journey ahead. Digital technology and telemedicine require improvements in sensitivity, accuracy, stability, and portability, as well as the future compatibility of hardware and software. Further studies with a larger scale are needed to enhance the practicability of the devices.

Acknowledgments

None.

Footnote

Reporting Checklist: The authors have completed the Narrative Review reporting checklist. Available at https://atm.amegroups.com/article/view/10.21037/atm-25-46/rc

Peer Review File: Available at https://atm.amegroups.com/article/view/10.21037/atm-25-46/prf

Funding: This study was supported by financial grants from the National Natural Science Foundation of China (to C.Z.) (No. 82471426), the National Key Research and Development Plan (to C.Z.) (No. 2022YFC3501303), and the Shanghai Hospital Development Center Program (to C.Z.) (No. SHDC2023CRD007).

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://atm.amegroups.com/article/view/10.21037/atm-25-46/coif). C.Z. reports funding from the National Natural Science Foundation of China (No. 82471426), the National Key Research and Development Plan (No. 2022YFC3501303), and the Shanghai Hospital Development Center Program (No. SHDC2023CRD007). The other authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Feigin VL, Vos T, Nichols E, et al. The global burden of neurological disorders: translating evidence into policy. Lancet Neurol 2020;19:255-65. [Crossref] [PubMed]
2. Voigtlaender S, Pawelczyk J, Geiger M, et al. Artificial intelligence in neurology: opportunities, challenges, and policy implications. J Neurol 2024;271:2258-73. [Crossref] [PubMed]
3. Global, regional, and national burden of disorders affecting the nervous system, 1990-2021: a systematic analysis for the Global Burden of Disease Study 2021. Lancet Neurol 2024;23:344-81. [Crossref] [PubMed]
4. Chandrasekaran R, Sadiq T M, Moustakas E. Usage Trends and Data Sharing Practices of Healthcare Wearable Devices Among US Adults: Cross-Sectional Study. J Med Internet Res 2025;27:e63879. [Crossref] [PubMed]
5. DeVore AD, Wosik J, Hernandez AF. The Future of Wearables in Heart Failure Patients. JACC Heart Fail 2019;7:922-32. [Crossref] [PubMed]
6. Carmona H, Graustein AD, Benditt JO. Chronic Neuromuscular Respiratory Failure and Home Assisted Ventilation. Annu Rev Med 2023;74:443-55. [Crossref] [PubMed]
7. Campbell BCV, Khatri P. Stroke. Lancet 2020;396:129-42. [Crossref] [PubMed]
8. Scheltens P, De Strooper B, Kivipelto M, et al. Alzheimer's disease. Lancet 2021;397:1577-90. [Crossref] [PubMed]
9. Dorsey ER, Bloem BR. The Parkinson Pandemic-A Call to Action. JAMA Neurol 2018;75:9-10. [Crossref] [PubMed]
10. Thijs RD, Surges R, O'Brien TJ, et al. Epilepsy in adults. Lancet 2019;393:689-701. [Crossref] [PubMed]
11. Rothstein JD, Hoke A, Mohassel P. Advances in neuromuscular disorders 2024. Lancet Neurol 2025;24:18-20. [Crossref] [PubMed]
12. Carey IM, Banchoff E, Nirmalananthan N, et al. Prevalence and incidence of neuromuscular conditions in the UK between 2000 and 2019: A retrospective study using primary care data. PLoS One 2021;16:e0261983. [Crossref] [PubMed]
13. Mary P, Servais L, Vialle R. Neuromuscular diseases: Diagnosis and management. Orthop Traumatol Surg Res 2018;104:S89-95. [Crossref] [PubMed]
14. Beaudart C, Rolland Y, Cruz-Jentoft AJ, et al. Assessment of Muscle Function and Physical Performance in Daily Clinical Practice: A position paper endorsed by the European Society for Clinical and Economic Aspects of Osteoporosis, Osteoarthritis and Musculoskeletal Diseases (ESCEO). Calcif Tissue Int 2019;105:1-14. [Crossref] [PubMed]
15. Bittmann FN, Dech S, Aehle M, et al. Manual Muscle Testing-Force Profiles and Their Reproducibility. Diagnostics (Basel) 2020;10:996. [Crossref] [PubMed]
16. Park S, Myong Y, Cho M, et al. Design and validation of a wearable dynamometry system for knee extension-flexion torque measurement. Sci Rep 2024;14:10428. [Crossref] [PubMed]
17. Alvarez JT, Gerez LF, Araromi OA, et al. Toward Soft Wearable Strain Sensors for Muscle Activity Monitoring. IEEE Trans Neural Syst Rehabil Eng 2022;30:2198-206. [Crossref] [PubMed]
18. Onkhar V, Dodou D, de Winter JCF. Evaluating the Tobii Pro Glasses 2 and 3 in static and dynamic conditions. Behav Res Methods 2024;56:4221-38. [Crossref] [PubMed]
19. Rajkumar A, Vulpi F, Bethi SR, et al. Wearable Inertial Sensors for Range of Motion Assessment. IEEE Sens J 2020;20:3777-87. [Crossref] [PubMed]
20. Young C, Oliver ML, Gordon KD. Design and validation of a novel 3D-printed wearable device for monitoring knee joint kinematics. Med Eng Phys 2021;94:1-7. [Crossref] [PubMed]
21. Jin Y, Alvarez JT, Suitor EL, et al. Estimation of joint torque in dynamic activities using wearable A-mode ultrasound. Nat Commun 2024;15:5756. [Crossref] [PubMed]
22. Jarchi D, Pope J, Lee TKM, et al. A Review on Accelerometry-Based Gait Analysis and Emerging Clinical Applications. IEEE Rev Biomed Eng 2018;11:177-94. [Crossref] [PubMed]
23. Foltynie T, Bruno V, Fox S, et al. Medical, surgical, and physical treatments for Parkinson's disease. Lancet 2024;403:305-24. [Crossref] [PubMed]
24. Schniepp R, Huppert A, Decker J, et al. Fall prediction in neurological gait disorders: differential contributions from clinical assessment, gait analysis, and daily-life mobility monitoring. J Neurol 2021;268:3421-34. [Crossref] [PubMed]
25. Buckley C, Alcock L, McArdle R, et al. The Role of Movement Analysis in Diagnosing and Monitoring Neurodegenerative Conditions: Insights from Gait and Postural Control. Brain Sci 2019;9:34. [Crossref] [PubMed]
26. Shah VV, Rodriguez-Labrada R, Horak FB, et al. Gait Variability in Spinocerebellar Ataxia Assessed Using Wearable Inertial Sensors. Mov Disord 2021;36:2922-31. [Crossref] [PubMed]
27. Ghislieri M, Gastaldi L, Pastorelli S, et al. Wearable Inertial Sensors to Assess Standing Balance: A Systematic Review. Sensors (Basel) 2019;19:4075. [Crossref] [PubMed]
28. Zadka A, Rabin N, Gazit E, et al. A wearable sensor and machine learning estimate step length in older adults and patients with neurological disorders. NPJ Digit Med 2024;7:142. [Crossref] [PubMed]
29. Kim S, Kim HS, Yoo JI. Sarcopenia classification model for musculoskeletal patients using smart insole and artificial intelligence gait analysis. J Cachexia Sarcopenia Muscle 2023;14:2793-803. [Crossref] [PubMed]
30. Schalkamp AK, Peall KJ, Harrison NA, et al. Wearable movement-tracking data identify Parkinson's disease years before clinical diagnosis. Nat Med 2023;29:2048-56. [Crossref] [PubMed]
31. Rovini E, Maremmani C, Cavallo F. How Wearable Sensors Can Support Parkinson's Disease Diagnosis and Treatment: A Systematic Review. Front Neurosci 2017;11:555. [Crossref] [PubMed]
32. Farzanehfar P, Woodrow H, Braybrook M, et al. Objective measurement in routine care of people with Parkinson's disease improves outcomes. NPJ Parkinsons Dis 2018;4:10. [Crossref] [PubMed]
33. Fessler EB, Brown RT, Miller RK. Rebooting Instrumental Activities of Daily Living for the 21st Century. Ann Intern Med 2022;175:278-9. [Crossref] [PubMed]
34. Agarwala P, Salzman SH. Six-Minute Walk Test: Clinical Role, Technique, Coding, and Reimbursement. Chest 2020;157:603-11. [Crossref] [PubMed]
35. Ricotti V, Kadirvelu B, Selby V, et al. Wearable full-body motion tracking of activities of daily living predicts disease trajectory in Duchenne muscular dystrophy. Nat Med 2023;29:95-103. [Crossref] [PubMed]
36. Gupta AS, Patel S, Premasiri A, et al. At-home wearables and machine learning sensitively capture disease progression in amyotrophic lateral sclerosis. Nat Commun 2023;14:5080. [Crossref] [PubMed]
37. Milazzo M, Spezzaneve A, Astrea G, et al. AUTOMA: a wearable device to assess the upper limb muscular activity in patients with neuromuscular disorders. Acta Myol 2021;40:143-51. [Crossref] [PubMed]
38. Lyu PZ, Zhu RT, Ling YT, et al. How Paretic and Non-Paretic Ankle Muscles Contract during Walking in Stroke Survivors: New Insight Using Novel Wearable Ultrasound Imaging and Sensing Technology. Biosensors (Basel) 2022;12:349. [Crossref] [PubMed]
39. Possin KL, Moskowitz T, Erlhoff SJ, et al. The Brain Health Assessment for Detecting and Diagnosing Neurocognitive Disorders. J Am Geriatr Soc 2018;66:150-6. [Crossref] [PubMed]
40. Cormack F, McCue M, Taptiklis N, et al. Wearable Technology for High-Frequency Cognitive and Mood Assessment in Major Depressive Disorder: Longitudinal Observational Study. JMIR Ment Health 2019;6:e12814. [Crossref] [PubMed]
41. Hafiz P, Bardram JE. The Ubiquitous Cognitive Assessment Tool for Smartwatches: Design, Implementation, and Evaluation Study. JMIR Mhealth Uhealth 2020;8:e17506. [Crossref] [PubMed]
42. Molina-Molina A, Ruiz-Malagón EJ, Carrillo-Pérez F, et al. Validation of mDurance, A Wearable Surface Electromyography System for Muscle Activity Assessment. Front Physiol 2020;11:606287. [Crossref] [PubMed]
43. Garg R, Driscoll N, Shankar S, et al. Wearable High-Density MXene-Bioelectronics for Neuromuscular Diagnostics, Rehabilitation, and Assistive Technologies. Small Methods 2023;7:e2201318. [Crossref] [PubMed]
44. Lin S, Gao C, Li H, et al. Wearable sensor-based gait analysis to discriminate early Parkinson's disease from essential tremor. J Neurol 2023;270:2283-301. [Crossref] [PubMed]
45. Gao X, Chen X, Lin M, et al. A wearable echomyography system based on a single transducer. Nat Electron 2024;7:1035-46. [Crossref] [PubMed]
46. Walle M, Duseja A, Whittier DE, et al. Bone remodeling and responsiveness to mechanical stimuli in individuals with type 1 diabetes mellitus. J Bone Miner Res 2024;39:85-94. [Crossref] [PubMed]
47. Biondi A, Santoro V, Viana PF, et al. Noninvasive mobile EEG as a tool for seizure monitoring and management: A systematic review. Epilepsia 2022;63:1041-63. [Crossref] [PubMed]
48. Lee B, Lee T, Jeon H, et al. Synergy Through Integration of Wearable EEG and Virtual Reality for Mild Cognitive Impairment and Mild Dementia Screening. IEEE J Biomed Health Inform 2022;26:2909-19. [Crossref] [PubMed]
49. Huh H, Shin H, Li H, et al. A wireless forehead e-tattoo for mental workload estimation. Device 2025;3:100781.
50. Kaveh R, Schwendeman C, Pu L, et al. Wireless ear EEG to monitor drowsiness. Nat Commun 2024;15:6520. [Crossref] [PubMed]
51. Ismail H, Raynor E, Zimetbaum P. Neuromuscular Disorders and the Role of the Clinical Electrophysiologist. JACC Clin Electrophysiol 2017;3:1069-79. [Crossref] [PubMed]
52. Shahrizaila N, Lehmann HC, Kuwabara S. Guillain-Barré syndrome. Lancet 2021;397:1214-28. [Crossref] [PubMed]
53. Hu H, Huang H, Li M, et al. A wearable cardiac ultrasound imager. Nature 2023;613:667-75. [Crossref] [PubMed]
54. Wijdicks EFM. The neurology of acutely failing respiratory mechanics. Ann Neurol 2017;81:485-94. [Crossref] [PubMed]
55. Sharma P, Hui X, Zhou J, et al. Wearable radio-frequency sensing of respiratory rate, respiratory volume, and heart rate. NPJ Digit Med 2020;3:98. [Crossref] [PubMed]
56. Wang C, Chen X, Wang L, et al. Bioadhesive ultrasound for long-term continuous imaging of diverse organs. Science 2022;377:517-23. [Crossref] [PubMed]
57. Elafros MA, Andersen H, Bennett DL, et al. Towards prevention of diabetic peripheral neuropathy: clinical presentation, pathogenesis, and new treatments. Lancet Neurol 2022;21:922-36. [Crossref] [PubMed]
58. Abd-Alrazaq A, AlSaad R, Aziz S, et al. Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review. J Med Internet Res 2023;25:e42672. [Crossref] [PubMed]
59. Khan AS, Livingstone DC, Hurd CL, et al. Retraining walking over ground in a powered exoskeleton after spinal cord injury: a prospective cohort study to examine functional gains and neuroplasticity. J Neuroeng Rehabil 2019;16:145. [Crossref] [PubMed]
60. Mekki M, Delgado AD, Fry A, et al. Robotic Rehabilitation and Spinal Cord Injury: a Narrative Review. Neurotherapeutics 2018;15:604-17. [Crossref] [PubMed]
61. Bruni MF, Melegari C, De Cola MC, et al. What does best evidence tell us about robotic gait rehabilitation in stroke patients: A systematic review and meta-analysis. J Clin Neurosci 2018;48:11-7. [Crossref] [PubMed]
62. Cumplido-Trasmonte C, Molina-Rueda F, Puyuelo-Quintana G, et al. Satisfaction analysis of overground gait exoskeletons in people with neurological pathology. a systematic review. J Neuroeng Rehabil 2023;20:47. [Crossref] [PubMed]
63. Sankai Y, Sakurai T. Exoskeletal cyborg-type robot. Sci Robot 2018;3:eaat3912. [Crossref] [PubMed]
64. Nakajima T, Sankai Y, Takata S, et al. Cybernic treatment with wearable cyborg Hybrid Assistive Limb (HAL) improves ambulatory function in patients with slowly progressive rare neuromuscular diseases: a multicentre, randomised, controlled crossover trial for efficacy and safety (NCY-3001). Orphanet J Rare Dis 2021;16:304. [Crossref] [PubMed]
65. Park EJ, Akbas T, Eckert-Erdheim A, et al. A hinge-free, non-restrictive, lightweight tethered exosuit for knee extension assistance during walking. IEEE Trans Med Robot Bionics 2020;2:165-75. [Crossref] [PubMed]
66. Gordt K, Gerhardy T, Najafi B, et al. Effects of Wearable Sensor-Based Balance and Gait Training on Balance, Gait, and Functional Performance in Healthy and Patient Populations: A Systematic Review and Meta-Analysis of Randomized Controlled Trials. Gerontology 2018;64:74-89. [Crossref] [PubMed]
67. Fumanal-Idocin J, Wang YK, Lin CT, et al. Motor-Imagery-Based Brain-Computer Interface Using Signal Derivation and Aggregation Functions. IEEE Trans Cybern 2022;52:7944-55. [Crossref] [PubMed]
68. Benabid AL, Costecalde T, Eliseyev A, et al. An exoskeleton controlled by an epidural wireless brain-machine interface in a tetraplegic patient: a proof-of-concept demonstration. Lancet Neurol 2019;18:1112-22. [Crossref] [PubMed]
69. Wang J, Wang T, Liu H, et al. Flexible Electrodes for Brain-Computer Interface System. Adv Mater 2023;35:e2211012. [Crossref] [PubMed]
70. Lorach H, Galvez A, Spagnolo V, et al. Walking naturally after spinal cord injury using a brain-spine interface. Nature 2023;618:126-33. [Crossref] [PubMed]
71. Park S, Ha J, Park J, et al. Brain-Controlled, AR-Based Home Automation System Using SSVEP-Based Brain-Computer Interface and EOG-Based Eye Tracker: A Feasibility Study for the Elderly End User. IEEE Trans Neural Syst Rehabil Eng 2023;31:544-53. [Crossref] [PubMed]
72. Hajós M, Boasso A, Hempel E, et al. Safety, tolerability, and efficacy estimate of evoked gamma oscillation in mild to moderate Alzheimer's disease. Front Neurol 2024;15:1343588. [Crossref] [PubMed]
73. Tang KWK, Jeong J, Hsieh JC, et al. Bioadhesive hydrogel-coupled and miniaturized ultrasound transducer system for long-term, wearable neuromodulation. Nat Commun 2025;16:4940. [Crossref] [PubMed]
74. Gozzi N, Chee L, Odermatt I, et al. Wearable non-invasive neuroprosthesis for targeted sensory restoration in neuropathy. Nat Commun 2024;15:10840. [Crossref] [PubMed]
75. Jacobs PG, Resalat N, Hilts W, et al. Integrating metabolic expenditure information from wearable fitness sensors into an AI-augmented automated insulin delivery system: a randomised clinical trial. Lancet Digit Health 2023;5:e607-17. [Crossref] [PubMed]
76. Topalovic U, Barclay S, Ling C, et al. A wearable platform for closed-loop stimulation and recording of single-neuron and local field potential activity in freely moving humans. Nat Neurosci 2023;26:517-27. [Crossref] [PubMed]
77. Jean-Louis G, Seixas AA. The value of decentralized clinical trials: Inclusion, accessibility, and innovation. Science 2024;385:eadq4994. [Crossref] [PubMed]
78. Piau A, Wild K, Mattek N, et al. Current State of Digital Biomarker Technologies for Real-Life, Home-Based Monitoring of Cognitive Function for Mild Cognitive Impairment to Mild Alzheimer Disease and Implications for Clinical Care: Systematic Review. J Med Internet Res 2019;21:e12785. [Crossref] [PubMed]