AI-driven analysis enabled by wearable devices has become an influential tool shaping modern clinical research. The technology embedded in today’s clinical trial wearables has evolved into a meaningful scientific and operational capability that can influence how studies are designed, conducted, and interpreted.
While the use of wearables in clinical research may feel like a recent breakthrough, researchers have been using early versions for decades. Early wearable tools were used as far back as the 1950s to measure physical activity, and by the 1970s, they were used to gain a better understanding of movement-based sleep-wake detection and ambulatory ECG monitoring. What has changed is not the concept, but the scale, complexity, and accessibility. Advances in sensor technology, connectivity, and AI analytics have transformed wearables from simple tracking tools into sources of real-time, continuous evidence.
Emergence of Wearable AI in Clinical Research
The evolution of wearable devices has accelerated through the application of artificial intelligence (AI) to wearable data. An AI-enabled wearable uses algorithms to interpret data, detect patterns and early risk, and generate insights in real-time or near real-time. These devices go beyond passive data collection by combining continuous physiological monitoring with advanced analytics that detect meaningful changes, such as early indicators of risk, and improved data quality and integrity.
Smartwatches, patch sensors, and AI-enhanced biosensors are increasingly used in clinical research, particularly in hybrid and decentralized clinical trial designs. They improve endpoint sensitivity and data quality by identifying subtle signals that traditional methods may miss, such as changes in activity or sleep patterns. The AI algorithms transform raw sensor streams into clinically meaningful features, often in near real time, including examples such as:
- Step quality instead of just a step count
- Detecting arrhythmias from ECG signals
- Predicting disease exacerbations from activity and digital biomarkers
Predictive analytics flag changes that may indicate clinical deterioration, safety signals, adherence issues, or protocol deviations, enabling earlier intervention and targeted follow‑up.
Integration of Clinical Trial Wearables into Study Design
A central consideration now is whether AI analysis of wearable data will provide meaningful data aligned with study endpoints. When in the draft stage of protocol development, it’s best to start with a clearly defined concept of interest, such as mobility, fatigue, autonomic function (involuntary bodily processes), or treatment tolerance, then select devices and analytics that support that objective.
Early alignment across clinical, data, operations, sourcing, and regulatory teams has become a defining requirement of trial design and execution. This is especially true as wearable programs are now integrated with systems such as electronic data capture (EDC), electronic clinical outcome assessment (eCOA), and centralized analytics platforms.
When thoughtfully integrated, the use of wearables in clinical trials enhances research quality and decision-making by providing objective insights into disease progression and treatment effects, reducing recall bias in patient-reported outcomes (PROs), and enabling the development of sensitive digital endpoints that reflect the participants’ actual ongoing experiences.
Digital Literacy, Access, and Data Security
Digital literacy and comfort with technology vary widely. To support equitable participation, sponsors, with help from industry partners, can provide training, clear guides, technical support, and user-friendly interfaces. Supplying devices to participants who lack access helps bridge the digital divide, particularly for older adults and underserved populations.
Robust data security measures are essential. End-to-end encryption, secure cloud storage, early de-identification, and regular audits aligned with HIPAA and GDPR standards help protect sensitive data and maintain participant trust.
Regulatory Oversight and Global Complexity
Clinical research using AI-enabled wearables spans multiple regulatory frameworks, including medical device regulation, data protection law, and clinical trial oversight, such as GCP standards. Wearable data must be well-justified, validated, and transparently described for use as primary endpoints. There must also be:
- Version-controlled algorithms
- Data that is auditable and reproducible
- A validated rationale showing how raw sensor signals correspond to clinically relevant outcomes
United States
The FDA issued guidance in 2023 that outlines recommendations to ensure that digital health technologies (DHTs) are properly validated for their intended clinical use, focusing on both their design and specific functions within a study.
In January 2025, the FDA issued draft guidance on AI-enabled device software functions, outlining expectations for development, validation, and lifecycle management. While this guidance is focused on marketing submissions, the principles are increasingly relevant to using wearables in clinical trials, shaping how AI-enabled wearables are evaluated for fit-for-purpose use, data integrity, and regulatory readiness.
Global
In global clinical trials, sponsors must also navigate varying requirements across different regions, which can be complex and often require early engagement with multiple agencies. To streamline multiregional clinical trials, it is beneficial to consult with regional experts and harmonize validation protocols.
Case Study: Measuring Mobility Outside the Clinic
In a Phase 2 neurology study, investigators introduced a wearable accelerometer to understand better treatment effects on mobility and fatigue—outcomes meaningful to participants but difficult to capture during site visits. While clinic-based assessments showed little differentiation, wearable data revealed clear differences in daily activity patterns and correlated strongly with patient-reported fatigue. These insights informed refinement of the Phase 3 endpoints and strengthened regulatory discussions, demonstrating the value of continuous, real-world data.
Successful Implementation of Using Wearables in Clinical Trials – The Imperial Advantage
Wearable AI technologies offer the potential for more proactive, participant-centered research, but success depends on addressing operational, technical, and regulatory challenges.
Imperial offers comprehensive solutions to help sponsors and CROs successfully integrate wearables. Our expertise spans the study lifecycle, from site startup to closeout, ensuring operational efficiency and regulatory compliance:
- Ancillary Supplies & Equipment: Imperial efficiently sources, manages, kits, delivers, and facilitates the return of wearable devices and related equipment.
- Study & Site Materials Development: Development of participant and site materials to support device adoption and digital literacy.
- Translation Services: High-accuracy translation services to support global study populations.
- Patient Engagement Solutions: Strategies to boost retention, compliance, and engagement, especially when using wearable devices.
- Global Logistics: Navigation of global logistics and regulatory documentation requirements.
By consolidating these services under one provider, you can simplify workflows, reduce costs, and accelerate timelines for clinical trials involving wearable technologies. Visit Imperial’s website for more information.
FAQs About Using Wearables in Clinical Research
Q: Why are wearables being used more frequently in clinical trials?
A: Wearables capture continuous, real-world data that traditional site visits cannot provide. This allows study teams to better understand daily function, symptom variability, and treatment impact outside the clinic while supporting more patient-centric and decentralized trial designs.
Q: Are consumer wearables acceptable for use in clinical research?
A: Consumer wearables can be used in clinical trials, but they must be demonstrated to be fit for purpose. Regulators focus less on whether a device is classified as “consumer” or “medical grade” and more on:
- Validation and verification
- Algorithm transparency and version control
- Data integrity and auditability
- Clear linkage between the measurement and the clinical endpoint
Additional rigor is often required when consumer devices are used to support key or registrational endpoints.
Q: How do regulators view wearable-derived endpoints?
A: Regulatory agencies are becoming increasingly open to clinical trial data derived from wearables when they are:
- Scientifically justified
- Pre-specified in the protocol and statistical analysis plan (SAP)
- Supported by analytical and clinical validation
- Governed by clear data handling and change-control processes
Q: What is the biggest mistake organizations make when adopting wearables in clinical research?
A: The most common mistake is starting with the device instead of the clinical question when planning the clinical study design. This can create gaps in justification, validation, and endpoint relevance.
Q: What are the key differences between clinical trial wearables & traditional clinical trial supplies?
A: The key differences between clinical trial wearables and traditional clinical trial supplies include:
- Data systems integration: Wearables collect continuous data, so they require validated software platforms, data transfer controls, and cybersecurity measures.
- Participant-facing technology: Wearables rely heavily on patient adherence, usability, and the availability of technical support.
- Bring Your Own Device (BYOD) vs. provisioned models: In some studies, participants may use their own devices, which can affect data consistency and require careful oversight to ensure integrity.
Sources and Further Reading
Privacy, ethics, transparency, and accountability in AI systems for wearable devices https://pubmed.ncbi.nlm.nih.gov/40599875/
Digital Health Technologies for Remote Data Acquisition in Clinical Investigations: Guidance for Industry, Investigators, and Other Stakeholders https://www.fda.gov/media/155022/download
Challenges and recommendations for wearable devices in digital health: Data quality, interoperability, health equity, fairness https://pmc.ncbi.nlm.nih.gov/articles/PMC9931360/.
Artificial Intelligence-Enabled Device Software Functions: Lifecycle Management and Marketing Submission Recommendations Draft FDA Guidance https://www.fda.gov/media/184856/download
Wearable AI to enhance patient safety and clinical decision-making https://www.nature.com/articles/s41746-025-01554-w#Sec1
The Impact of Wearable Technologies in Health Research: Scoping Review https://pmc.ncbi.nlm.nih.gov/articles/PMC8826148/