Digital biomarkers are reshaping how health data is gathered and interpreted in clinical trials, especially in neurology. Instead of relying only on occasional clinic visits, researchers can now capture continuous signals from everyday life. Wearables, smartphones and sensors turn movement, speech, sleep and cognition into measurable data points, offering a richer picture of patient health.

What Are Digital Biomarkers?

Traditional biomarkers usually come from snapshots in time, such as blood tests, imaging scans or tissue samples taken during clinic visits. While invaluable, they don’t always reveal how a patient’s biology shifts day to day or how treatment response progresses beyond the hospital walls. That’s the gap digital biomarkers aim to close.1

Digital biomarkers are measurable physiological or behavioral data collected through everyday technologies - wearables, smartphones, sensors, apps and remote monitoring platforms. By tracking health in real-world settings, they provide insights that traditional assessments often miss.¹

Digital biomarker data can be collected through:

• Wearable devices: smartwatches, fitness trackers or medical-grade wearables
• Mobile phones and tablets: leveraging built-in sensors and apps
• Physiological and environmental sensors: monitoring heart rate, tremor or ambient conditions
• Health and research apps: capturing patient-reported outcomes and behavioral data
• Remote patient monitoring platforms: integrating continuous streams of patient information

Depending on the study design, these tools can measure heart rate, physical activity, sleep patterns, gait, tremor, speech or other behavioral markers, painting a dynamic picture of health that static lab tests alone cannot provide.¹

How Digital Biomarkers Differ from Traditional Biomarkers²

Technologies That Enable Digital Biomarkers

A powerful mix of devices, software and analytical tools now enables the collection and interpretation of digital biomarker data. The “right” technology depends on the type of signal being measured, the clinical context and how often data needs to be captured.

Wearables and Sensors

Wearable devices such as smartwatches, fitness trackers, patches and specialized medical sensors can record physiological signals continuously or intermittently. Depending on the device and the disease, these may include heart rate, physical activity, movement, temperature, oxygen saturation or other measures.³

Mobile Apps and Smartphones

Because smartphones are already part of daily life, they offer a convenient way to collect biomarker data without extra training. Apps can track activity levels, location, sleep, medication use or patient-reported outcomes. Built-in microphones and cameras can assess speech, facial movement, gait and other functional measures.⁴

AI and Data Analytics

Digital biomarkers can generate large volumes of data, which require computational methods to uncover patterns. By using statistical analysis, machine learning and artificial intelligence algorithms, researchers can process these data, detect changes over time and identify signals associated with disease progression or treatment response.⁵

Cloud and Integration Platforms

Managing large datasets requires secure, scalable systems. Cloud platforms collect information from wearables, smartphones, electronic health records and other sources, enabling storage, rapid processing and remote access. Integration reduces silos and gives researchers a more complete view of participants.⁶

Types of Digital Biomarkers

Digital biomarkers can be grouped according to the type of information they capture, although some measures may fall into more than one category.^7-9

• Physiological: body temperature, heart rate, blood pressure, oxygen saturation
• Behavioral: daily routines, physical activity, device interaction patterns
• Cognitive: memory, attention, reaction time
• Speech: rate, pauses, pitch, articulation, voice quality
• Motor: gait, balance, tremor, coordination
• Sleep: duration, stages, nighttime movement, sleep–wake cycles
• Cardiovascular: heart rate variability, rhythm, cardiovascular signals
• Respiratory: breathing rate, patterns, oxygen saturation
• Digital phenotyping: behavioral data from everyday device interactions
• Environmental: air quality, temperature, noise or other exposures

Why Digital Biomarkers Matter in Clinical Trials?

Clinical trials often rely on measurements collected during scheduled site visits. While these assessments are important, they provide only a limited view of how a patient’s health changes between visits. Digital biomarkers can complement biological measures taken during visits by capturing data in patients’ everyday environments.⁷

One of their biggest advantages is frequency. Instead of a single data point from a clinic, connected devices can continuously track activity, sleep, heart rate or movement over days or weeks. This richer timeline helps researchers spot subtle changes that might otherwise slip through the cracks.¹

Digital biomarkers also ease the burden on patients and trial sites. Remote data collection can reduce the number of in-person visits, making participation more manageable for those with limited mobility or who live far from trial centers.¹

Beyond convenience, the additional data points support longitudinal monitoring and the use of more sensitive endpoints. Continuous measurements reveal how disease progression or treatment response unfolds in real life, influenced by lifestyle and environment, rather than in controlled clinical settings.¹

These advantages make digital biomarkers particularly attractive for decentralized and hybrid clinical trials, in which some study activities occur remotely. By combining remote digital measurements with conventional clinical assessments, researchers can collect richer datasets for a more comprehensive clinical oversight.

Key Applications of Digital Biomarkers in Clinical Trials

Because of their unique advantages, digital biomarkers are being used across multiple stages of clinical trials, from participant identification to long-term outcome tracking.

• Patient screening and stratification: Digital measures help researchers identify relevant characteristics before treatment begins or group participants by baseline features. For example, smartphone‑based cognitive tests can establish baseline function in early Alzheimer’s disease.¹⁰
• Remote symptom monitoring: Patients can report symptoms through an app, where the data they provide may reflect changes in their condition. Remote monitoring strategies are frequently used in Parkinson’s disease studies to track changes in sleep, activity or movement patterns.¹¹
• Detection of treatment response: Frequent digital measurements can help identify changes following treatment. For instance, a wearable device could track changes in tremor or gait in patients following an investigational therapy for Parkinson’s disease.¹²
• Monitoring adherence and functional status: Devices and apps confirm whether participants follow study protocols, from medication schedules to exercise routines, while also capturing how they function in daily life.¹³
• Capturing endpoints between clinic visits: Digital measures reveal information during the periods when participants are not at the study site, enabling researchers to tailor treatment protocols accordingly. This type of monitoring has been implemented to capture changes in mobility between scheduled assessments in a multiple sclerosis trial.¹⁴
• Supporting continuous data collection in long-duration studies: Continuous digital monitoring enables researchers to follow disease progression over months or years without requiring frequent in‑person assessments. Such long-term investigations are especially helpful when investigating disease progression in neurological disorders.¹⁵

Digital Biomarkers in Neurology

Many neurological conditions progress gradually and can affect movement, cognition, speech, sleep and everyday activities over months or even years. These subtle changes are hard to capture in brief clinic visits, which is why neurology is one of the most promising areas for digital biomarker strategies.¹⁶

Some neurological conditions where digital biomarkers are being investigated include:

• Parkinson’s disease: Wearables and smartphone-based assessments can measure tremor, gait, movement speed, balance and other motor symptoms. These measures may help researchers track fluctuations that can vary throughout the day.¹²
• Alzheimer’s disease: Digital cognitive assessments, speech analysis and monitoring of daily activities can provide information about changes in memory, attention, communication and functional ability.¹⁰
• Multiple sclerosis: Digital measures can be used to assess mobility, fatigue, balance and activity levels. A wearable could, for instance, track walking patterns and daily activity between neurological assessments.¹⁴
• Epilepsy: Wearable and other sensor-based technologies may help detect physiological changes associated with seizures, complementing patient-reported seizure diaries.17
• Huntington’s disease: Because the disease affects movement and cognition, digital measures of motor control, gait, speech and activity can be informative about the disease stage and inform subsequent treatment options.¹⁸
• Stroke recovery is another field strongly supported by digital biomarkers. For example, motion sensors can help healthcare practitioners monitor changes in mobility, upper-limb movement, speech and daily activity during rehabilitation.¹⁹

Common Types of Neurology Digital Biomarkers

Neurological diseases can affect several aspects of function at once, from movement and speech to cognition and sleep. Digital biomarkers transform these changes into measurable signals, giving researchers objective tools to track progression and treatment response.¹⁶

• Motor biomarkers: gait speed, tremor intensity, balance, movement variability
• Speech and voice biomarkers: articulation, pause patterns, vocal changes
• Cognitive biomarkers: reaction time, memory tasks, attention patterns
• Sleep and circadian biomarkers: sleep duration, fragmentation, activity rhythms
• Behavioral biomarkers: activity level, routine changes, interaction patterns

Challenges and Limitations

Despite their potential, digital biomarkers still face several challenges before they can be used routinely across clinical trials. Before collecting large amounts of data, researchers need to establish that a digital measure is reliable, reproducible and relevant. Several issues may surface before transition to clinical use, including:²⁰

• Data quality and validation concerns: Missing data, sensor errors, inconsistent measurements and differences in how participants use devices can undermine the reliability of digital biomarkers.
• Device variability and interoperability issues: Different devices may use different sensors, algorithms, sampling rates or processing methods, making cross-study comparisons difficult.
• Algorithm transparency and reproducibility: Algorithms used to process digital biomarker data may be proprietary. Before using these algorithms, researchers should have a sound understanding of how these methods work. Particularly in AI-powered biomarker discovery technologies, transparency and explainability of the algorithm should be prioritized before data processing and analysis.
• Patient adherence and usability barriers: Regardless of how robust a digital biomarker is, challenges in patient adherence can significantly diminish the quality of data. Inevitably, some participants may forget to wear a device, stop using an app or find the technology difficult to use. These issues can create data gaps that skew the outcomes of long-duration studies.
• Regulatory uncertainty around endpoint acceptance: Although regulatory experience with digital measures is growing, questions can remain about how digital biomarkers should be validated and when they are suitable for use as clinical trial endpoints.
• Privacy, security and data governance concerns: Devices and platforms can sometimes collect sensitive information about a participant’s health, behavior and daily activities. Therefore, approaches to consent, data protection, access and storage must be deliberated beforehand.²¹
• Need for clinical validation before broad adoption: A digital measure may be technically accurate without necessarily being clinically useful. Evidence is needed to establish its relationship with disease status, progression or treatment response before it can be widely adopted.

Regulatory and Scientific Considerations

Using digital biomarkers in clinical trials requires more than proving a device can capture a signal. Researchers must show that the measurement is reliable, ethically collected and unbiased.²² Three key criteria define this process:

• Analytical validity: Does the technology measure the intended signal accurately and consistently? For example, a wearable used to measure heart rate should produce reliable measurements at different time points and across populations.
• Clinical validity: Is the digital measurement meaningfully associated with a disease, clinical state or outcome of interest?
• Clinical utility: Does using the digital biomarker provide useful information that can support patient care, trial decisions or evaluation of a treatment?

Variability remains a bottleneck across all three pillars, underscoring the need for standardized protocols for data collection, processing, analysis and handling missing data. Standardization also enables comparisons across studies and populations.²²

Regulatory requirements continuously evolve; however, validation and clinical evidence are constant prerequisites for regulatory acceptance. The FDA has provided guidance on the use of digital health technologies in clinical investigations, emphasizing factors such as device selection, data collection, performance and user-friendliness. The agency's framework reflects the need to demonstrate that technology-generated data are fit for use in a particular clinical investigation.²⁰

The EMA has likewise highlighted the importance of appropriate qualification and validation when digital technologies are used to generate data for drug discovery and development. Developers should consider factors such as the reliability of the measurement, its clinical relevance and whether the technology performs consistently in the target population and setting.²⁰

Feature Product

References

1. Vasudevan S, Saha A, Tarver ME, Patel B. Digital biomarkers: convergence of digital health technologies and biomarkers. NPJ Digit Med 2022;5(1):36.
2. Song J, Cho E, Lee H, Lee S, Kim S, Kim J. Development of neurodegenerative disease diagnosis and monitoring from traditional to digital biomarkers. Biosensors 2025;15(2):102.
3. Daniore P, Nittas V, Haag C, Bernard J, Gonzenbach R, von Wyl V. From wearable sensor data to digital biomarker development: ten lessons learned and a framework proposal. NPJ Digit Med 2024;7(1):161.
4. Chen I-M, Chen Y-Y, Liao S-C, Lin Y-H. Development of digital biomarkers of mental illness via mobile apps for personalized treatment and diagnosis. J Pers Med 2022;12(6):936.
5. Wasilewski T, Kamysz W, Gębicki J. AI-assisted detection of biomarkers by sensors and biosensors for early diagnosis and monitoring. Biosensors 2024;14(7):356.
6. Crichton D, Cinquini L, Kincaid H, Mahabal A, Altinok A, Anton K, et al. From space to biomedicine: Enabling biomarker data science in the cloud. Cancer Biomark 2022;33(4):479-488.
7. Alonso AKM, Hirt J, Woelfle T, Janiaud P, Hemkens LG. Definitions of digital biomarkers: a systematic mapping of the biomedical literature. BMJ Health Care Inform 2024;31(1):e100914.
8. Al-Alusi MA, Friedman SF, Kany S, Rämö JT, Pipilas D, Singh P, et al. A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram. NPJ Digit Med 2025;8(1):120.
9. Landry V, Matschek J, Pang R, Munipalle M, Tan K, Boruff J, et al. Audio-based digital biomarkers in diagnosing and managing respiratory diseases: a systematic review and bibliometric analysis. Eur Respir Rev 2025;34(176):240246.
10. Da Cunha E, Manera V, Chorin F, Lemaire J, Plonka A, Mouton A, et al. Speech-based digital biomarkers for early etiological stratification of Alzheimer’s disease and frontotemporal degeneration: a biomarker-confirmed prospective study. J Prev Alzheimers Dis 2026;13(6):100573.
11. Sun Y-m, Wang Z-y, Liang Y-y, Hao C-w, Shi C-h. Digital biomarkers for precision diagnosis and monitoring in Parkinson’s disease. NPJ Digit Med 2024;7(1):218.
12. Taylor KI, Lipsmeier F, Scelsi MA, Volkova-Volkmar E, Rukina D, Popp W, et al. Exploratory digital outcome measures of motor sign progression in Parkinson’s disease patients treated with prasinezumab. NPJ Digit Med 2025;8(1):365.
13. Dockendorf MF, Hansen BJ, Bateman KP, Moyer M, Shah JK, Shipley LA. Digitally enabled, patient‐centric clinical trials: shifting the drug development paradigm. Clin Transl Sci 2021;14(2):445-459.
14. Dini M, Comi G, Leocani L. Digital remote monitoring of people with multiple sclerosis. Front Immunol 2025;16:1514813.
15. Asare KO, Moshe I, Terhorst Y, Vega J, Hosio S, Baumeister H, et al. Mood ratings and digital biomarkers from smartphone and wearable data differentiates and predicts depression status: A longitudinal data analysis. Pervasive Mob Comput 2022;83:101621.
16. Nerrise F, Schütz N, Zhao Q, Gould C, Milstein A, Schulman K, et al. A framework of digital biomarkers for neurodegenerative diseases. Nat Rev Bioeng 2026:1-20.
17. Russo EE, Simmatis LE, Wu T, Kadak K, Harmsen IE, Samuel N. Digital biomarkers and ambulatory seizure detection in epilepsy clinical trials. Discover Neuroscience 2026;21(1):15.
18. Tortelli R, Rodrigues FB, Wild EJ. The use of wearable/portable digital sensors in Huntington's disease: a systematic review. Parkinsonism Relat Disord 2021;83:93-104.
19. Gruia D-C, Trender W, Hellyer P, Banerjee S, Kwan J, Zetterberg H, et al. IC3 protocol: a longitudinal observational study of cognition after stroke using novel digital health technology. BMJ Open 2023;13(11):e076653.
20. Lieberwirth JK, Mittermaier M, Stern AD. Challenges and potential of using digital biomarkers in healthcare and clinical trials. Commun Med 2026;6(1):151.
21. Manikandan S, Shore S, Waszczuk D, Miriyala S, Sadanala G. Digital biomarkers in chronic disease management: a systematic review of personalization and ethical challenges. Per Med 2026;23(3):275-295.
22. Koller C, Blanchard M, Hügle T. Navigating through regulatory frameworks for digital therapeutics and biomarkers. Health Inform J 2025;31(4):14604582251387656.