Findings
The quality of evidence for the analytical validation of sensor-based digital health technologies (sDHTs), which is the evaluation of algorithms converting sensor data into a clinically interpretable measure, is often inconsistent and insufficient. The existing V3+ framework codifies the overall evaluation process, which includes verification, usability validation, analytical validation, and clinical validation. To improve the scientific rigor of analytical validation, a hierarchical framework for selecting reference measures is needed because not all potential reference measures are of equal quality. The framework classifies reference measures based on attributes that contribute to reduced measurement variability, with defining and principal measures being the most rigorous due to objective data acquisition and the ability to retain source data.

Recommendations
The proposed framework sequentially moves the investigator through four steps: (1) Compile preliminary information, including the digital clinical measure, context of use (COU), algorithm requirements, and sensor verification evidence . (2) Select an existing reference measure, develop a novel comparator, or identify a set of anchor measures, prioritizing measures with the highest scientific rigor (defining → principal → manual → reported) . (3) Consider the impact of the data collection environment to determine if the analytical validation study can be conducted in the intended use environment with the highest-order measure, or if in-lab validation is necessary, ensuring the results are generalizable . (4) Describe the rationale for key study design decisions to encourage transparency for evaluators, regulators, and payers . Investigators must justify passing over a higher-ranked reference measure, generally only acceptable if the higher-ranked measure poses unacceptable risk or is not applicable to the context of use.

Regulatory Considerations
The principles of the framework for analytical validation apply regardless of the regulatory status of the sDHT (regulated medical device, low-risk general wellness apps, or research product) or its intended use (clinical care or clinical research). The framework is intended to help investigators support the most rigorous claims regarding sDHT performance, which is important for acceptance by evaluators, peer-reviewers, regulators, and payers. The categorization of the digital clinical measure as a digital biomarker or an electronic clinical outcome assessment also does not change the framework's applicability.

Findings
The most promising aspects of mental health for digital measurement are sleep, physical activity, stress, and social behavior, which have the strongest scientific evidence. Core barriers to adoption include high cost and limited access, data privacy concerns, poor technological literacy, and a lack of technology adaptation for specific mental health needs. Essential technology characteristics for "fit-for-purpose" sDHTs include usability, reliable performance, strong data privacy and security, and long battery life.

Recommendations
Research and development should prioritize moving promising measures (sleep, activity, stress, social behavior) to large-scale clinical trials. Algorithms must be refined and clinically validated for mental health indications, and new sensor modalities should be explored. Infrastructure must be developed by creating standards and ontologies for mental health sensor data to ensure interoperability and scalability. To improve access and equity, financial support mechanisms and inclusive, culturally tailored design are critical.

Regulatory Considerations
The report does not provide a separate section for "Regulatory Considerations" but emphasizes that future development and funding should prioritize clinical validation across diverse populations. It notes the importance of a clear understanding of the intended measurement claims and the need for rigorous validation studies to move beyond pilot and feasibility stages to demonstrate real-world clinical utility.

Findings
Collaborative Communities are sustained, multi-stakeholder forums (including patients, industry, academia, and the FDA) dedicated to solving shared challenges in the medical device ecosystem. These communities are not intended to replace formal regulatory mechanisms. They are equipped to perform activities such as:
Developing best practices and strategies.
Generating and evaluating evidence to support novel approaches.
Clarifying ill-defined challenges and generating consensus on definitions.
Addressing issues related to product quality and safety.

Recommendations
The FDA/CDRH does not establish or fund these communities. Instead, the FDA recommends that interested stakeholders convene and lead these groups. The FDA reviews opportunities on a case-by-case basis for participation, considering:
The community's potential public health impact.
Alignment with the CDRH mission, priorities, and resources.
The existence of a formal governance structure, a convener, a plan to measure success, and a mechanism for sustained engagement.

Regulatory Considerations
The FDA's participation in these communities is a strategic priority for advancing regulatory science and fostering responsible medical device innovation. Examples of digital health-related collaborations include those focused on AI/ML, Digital Biomarkers, Digital Health Technologies (DHTs), and Real-World Data (RWD). The outcomes developed by these groups can inform and accelerate the development of science-based solutions to policy and scientific challenges.

Findings
MCID represents the smallest change that someone living with Alzheimer's disease would identify as important, but faces several universal application challenges. Alzheimer's disease progresses differently for each individual, complicating the establishment of universal standards that account for individual-level issues. The disease is gradual and evolving, with what is perceived as clinically meaningful varying significantly at early and late disease stages. People living with Alzheimer's disease and caregivers may have differing perspectives on treatment benefits, making it challenging to establish appropriate MCID. Current Alzheimer's trials rely on various tests to evaluate cognitive and functional impairments, but these tests often lack sensitivity to early-stage changes and are affected by variability in rater rankings. Digital biomarkers offer promising approaches for detecting real-time, objective clinical differences and improving patient outcomes through continuous monitoring, individualized assessments, and artificial intelligence learning for complex analytical predictions.

Recommendations
Digital biomarkers and advanced health technologies should be leveraged to enable continuous monitoring and individualized assessments that can better capture meaningful change in Alzheimer's disease. The primary focus must remain on outcomes that truly matter to people living with Alzheimer's disease and their caregivers, ensuring that the principle of clinical meaningfulness is not lost as new technologies are introduced.

Regulatory Considerations
Important considerations around standardization, accuracy, and integration into current clinical frameworks must be addressed as digital biomarkers are adopted. As new technologies are introduced alongside evolving regulatory frameworks, maintaining focus on clinically meaningful outcomes for patients and caregivers is essential.

Findings
Clinically Acceptable Performance: A clinical study demonstrated that the weekly AFib burden estimates from the Apple AFib History Feature were in close agreement with a reference ECG patch, with an average difference of just 0.67%. The vast majority of measurements had paired differences within ±10% of the reference device.
Generalizable Across Subgroups: The device's accuracy was similar across various subgroups, including different sexes, races, ages, and skin tones.
Performance Post-Ablation is Uncertain: In a small subgroup of patients with a prior cardiac ablation, the device's performance, while still strong, showed slightly more variability and exceeded a pre-specified acceptance criterion. The study was not designed or powered to demonstrate equivalent performance in this specific group.
Technical Limitations Exist: The feature only provides a retrospective weekly estimate and does not give specific timestamps or durations of AFib episodes. It also does not detect other atrial tachyarrhythmias, like atrial flutter.

Recommendations
Appropriate Use: The document implicitly recommends using the tool precisely within its qualified context of use—as a secondary, not primary, endpoint for comparing AFib burden between study arms in cardiac ablation device trials.
Supplemental Data Collection: For studies involving patients who have had a prior ablation, it would be beneficial to assess the tool alongside other methods of determining AFib burden to better characterize its performance in this population.
Define Study-Specific Endpoints: Investigators using the tool are responsible for defining and justifying their specific study designs and what constitutes a clinically significant reduction in AFib burden.

Regulatory Considerations
MDDT Qualification: The Apple AFib History Feature is officially qualified by the FDA as a Medical Device Development Tool (MDDT), which reduces the burden on device developers, as they no longer need to independently justify its methodology for collecting weekly AFib burden estimates in their clinical studies.
Secondary Endpoint Only: A key limitation for its regulatory use is its qualification only as a secondary endpoint. It cannot, by itself, be used to evaluate the primary safety and effectiveness of cardiac ablation devices. This is partly because FDA typically requires the inclusion of any atrial tachyarrhythmia (not just AFib) for defining ablation success in pivotal studies.
Not a Replacement for Primary Endpoints: The tool's utility is intended to provide supplemental data and help better understand post-treatment AFib burden; it is not meant to replace more clinically well-defined primary endpoints.

Findings
Regulatory Acceptance is Complex: Gaining regulatory acceptance for endpoints derived from Digital Health Technologies (DHTs) is a lengthy, multifaceted, and costly process that requires a global strategy and early health authority consultation.
"Fit-for-Purpose" is Key: A DHT's clearance or approval as a medical device does not automatically ensure it is fit-for-purpose in a clinical trial; its intended use must align with the specific context of use (COU) in the study.
Meaningfulness is a Hurdle: Demonstrating the clinical meaningfulness of novel digital endpoints, especially for abstract concepts like cognitive decline in Alzheimer's Disease, remains a significant challenge for regulatory acceptance.
International Harmonization is Lacking: Differences in regulatory requirements for DHT validation between major health authorities can delay or prevent the successful implementation of digital measures in global clinical trials.
Technology Changes Pose Risks: Software and hardware updates to DHTs during a clinical trial can have significant implications, potentially invalidating study results if not managed through a predetermined change-control plan.

Recommendations
Engage Health Authorities Early and Often: Sponsors should conduct multiple consultations with major health authorities (e.g., FDA, EMA) early in the development process to align on the Concept of Interest (COI), COU, and the validation roadmap.
Develop a Comprehensive Regulatory Strategy: A global regulatory strategy should be an integral part of the overall development plan, tailored to the program's objectives and endpoint hierarchy.
Establish "Fit-for-Purpose" Criteria: Before selecting a DHT, sponsors should establish the minimum technical and performance specifications required for the specific COU to guide the selection of a fit-for-purpose device.
Create a Conceptual Framework: For novel endpoints, sponsors should develop a conceptual framework that visualizes how the DHT-derived measure relates to meaningful health concepts and patient experiences.
Plan for Change and Missing Data: Sponsors should establish predetermined change-control plans with manufacturers to manage DHT updates and create risk management plans to minimize and handle missing data from remote acquisition.

Regulatory Considerations
Distinct Pathways in US vs. EU: The US FDA uses a risk-based approach for DHTs that are medical devices, while in Europe, CE marking for the intended COU is generally expected by the EMA.
Qualification is an Option, Not a Requirement: Both the FDA and EMA offer voluntary qualification programs for Drug Development Tools (DDTs), which can validate a DHT for a specific COU across multiple drug programs, though the process is resource-intensive.
Scientific Advice for Individual Programs: For DHTs used within a single drug development program, engaging with health authorities through scientific advice meetings is a more targeted and confidential pathway for gaining feedback and agreement.
Data Privacy and Security are Paramount: Sponsors must ensure that the collection, transfer, and storage of personal data via DHTs comply with all applicable regulations, such as GDPR in the EU, including cybersecurity and data transfer measures.

Findings
Usability gaps in sDHTs remain a barrier to adoption, with many technologies failing to prioritize ease of use, accessibility, and diverse user needs​
Human-centered design is critical for ensuring that digital health solutions are intuitive, functional, and scalable across different healthcare environments​
Standardized usability metrics for evaluating digital health technologies are lacking, leading to inconsistent reporting and validation of usability outcomes​
Use-related risk analysis is essential to identifying and mitigating risks associated with user errors, ensuring the safety and effectiveness of sDHTs​
The V3+ framework provides a structured approach to integrating usability validation into digital health technology development, aligning with global regulatory expectations​

Recommendations
Developers should incorporate human-centered design principles from the outset, ensuring that usability, accessibility, and user needs are central to sDHT development​
Usability validation should be standardized, with clear methodologies for measuring usability, including satisfaction, ease of use, efficiency, and error mitigation​
Regulatory and clinical stakeholders should collaborate on defining best practices for usability evaluation, ensuring that digital endpoints are both meaningful and scalable​
Risk analysis should be iterative, with developers continuously refining their technologies based on real-world user feedback and testing​
The usability validation component of V3+ should be widely adopted to ensure that digital clinical measures meet patient-centered, regulatory, and technical expectations​

Regulatory Considerations
Regulators are emphasizing the need for usability validation to ensure that digital endpoints are both clinically relevant and patient-friendly​
sDHTs must comply with human factors engineering guidelines, aligning with global regulatory frameworks such as ISO 9241-210 and FDA usability requirements​
Data security, privacy, and interoperability must be ensured, particularly as sDHTs become integrated into remote monitoring and decentralized clinical trials​
Real-world evidence (RWE) should support usability validation, helping to bridge the gap between regulatory approval and real-world adoption​
Regulatory bodies should work toward standardizing usability testing methodologies, ensuring consistency across clinical research, digital endpoints, and medical device evaluations​

Findings
Digital health measures for ADRD must align with patient and care partner priorities, including functional daily activities such as remembering object locations and maintaining speech fluency.
Sensor placement, data collection modalities, and algorithmic interpretation significantly impact the accuracy and reliability of digital measures.
While digital cognitive and behavioral assessments have strong potential as clinical endpoints, standardization is needed to ensure regulatory acceptance.
Sleep and mobility disruptions in ADRD can be measured with actigraphy, EEG, and ambient sensor-based approaches, but usability considerations are crucial.
Metadata, including environmental conditions and patient comorbidities, must be accounted for to ensure valid interpretations of digital measures in both research and clinical practice.

Recommendations
Researchers and technology developers should adopt standardized ontologies for digital measures to improve consistency across studies and regulatory submissions.
Digital biomarkers should be selected and validated with reference to patient and care partner needs, ensuring they reflect meaningful aspects of health.
Considerations such as sensor placement, data processing methods, and cultural neutrality of cognitive assessments must be accounted for in study designs.
Clinical trials should incorporate digital health technologies as both exploratory endpoints and potential screening tools for ADRD progression.
Further research is needed to refine algorithms for sleep, mobility, and speech-based digital biomarkers to enhance their predictive power for cognitive decline.

Regulatory Considerations
Digital measures of sleep and mobility have been recognized as potential clinical trial endpoints by regulatory agencies such as the FDA.
Standardized reporting and frameworks should be followed to ensure interoperability and data integrity in digital health studies.
Developers must document and validate scoring algorithms used for cognitive and behavioral assessments to meet regulatory expectations.
Data privacy and security regulations must be adhered to, particularly when collecting real-world behavioral and biometric data.
Ongoing validation and real-world evidence generation are necessary to establish digital measures as reliable clinical and regulatory endpoints in ADRD research.

Findings
Sleep disturbances are common across multiple therapeutic areas, making standardized digital measures essential for cross-condition research.
Measurement accuracy varies depending on sensor placement, algorithms, and contextual factors such as sleep environment.
While home-based digital sleep tracking improves accessibility, challenges remain in ensuring consistency with clinical polysomnography.
Digital measures of sleep provide new opportunities for continuous and longitudinal monitoring, but standardization in data collection and interpretation is needed.
Stakeholders, including regulatory agencies, increasingly recognize digital sleep biomarkers, but additional validation is required to ensure widespread adoption.

Recommendations
Researchers and clinicians should integrate core digital sleep measures into study designs to improve data comparability across trials and clinical contexts.
Algorithm transparency and validation protocols should be established to enhance the accuracy of digital sleep monitoring tools.
Regulatory engagement should be prioritized early in the development process to ensure that digital sleep measures meet evidentiary standards.
Multi-stakeholder collaboration, including patient and care partner input, is essential to ensure sleep measures reflect meaningful aspects of health.
Further research is needed to refine wearable and sensor-based technologies to improve real-world applicability and clinical utility of digital sleep biomarkers.

Regulatory Considerations
The FDA and other regulatory bodies increasingly acknowledge sleep measures as potential clinical endpoints, but clear validation frameworks are necessary.
Digital sleep measures should align with industry standards such as HL7 to ensure interoperability and data integrity.
Data privacy and security regulations must be followed, particularly for continuous sleep monitoring in real-world settings.
Post-market validation and real-world evidence generation are critical to support regulatory acceptance of digital sleep biomarkers.
Developers must document the derivation of sleep measures, including algorithmic processing and sensor accuracy, to meet regulatory review requirements.

Findings
Data analytics are challenging due to diverse metrics and study aims.
Most devices lack built-in software for data output.
There is a lack of comparison and validation studies for different devices and metrics.
Validation of PA metrics is difficult due to the absence of a gold standard.
The integration of various databases is needed but challenging.

Recommendations
Conduct comparison and validation studies between different brands of devices and PA metrics.
Develop standardized metrics for measuring PA.
Improve data integration methods across different studies and databases.
Focus on developing built-in software for devices to facilitate data output.
Encourage research on the validation of PA metrics.

Regulatory Considerations
1Not mentioned

Findings
The field lacks a centralized, standardized database of validated digital health technologies, making it difficult for researchers and clinicians to select appropriate tools.
Non-wearable sensors and software applications are the most common types of DHTs, with 83% of ambient technologies categorized as software or applications.
Most DHTs focus on mild cognitive impairment (MCI) and early Alzheimer’s disease, with fewer technologies validated for moderate or severe dementia stages.
Uneven Distribution of Dementia Subtypes – The review identified a gap in DHT validation for frontotemporal dementia (FTD) and Lewy Body dementia, with Alzheimer’s disease being the predominant focus.

Recommendations
Expand and maintain an open-access database of validated DHTs to improve accessibility and standardization.
Increase research on digital measures applicable to moderate and severe stages of dementia, as well as non-Alzheimer’s dementias.
Promote integration of wearable, ambient, and cognitive assessment tools to generate comprehensive digital phenotypes of patients.
Follow clear guidelines for analytical and clinical validation of DHTs to improve regulatory acceptance and research applicability.
Conduct more usability and feasibility assessments, especially for populations with cognitive decline, to ensure DHTs are accessible and effective in real-world settings.

Findings
There is a lack of systematic approaches to guide the processes of collecting, interpreting, analyzing, and translating health data from wearables into digital biomarkers.
Most wearables have fixed measurement capabilities, limiting their translation to digital biomarkers.
Current guidance lacks study design and conduct elements that involve all stakeholders in an iterative approach for implementing digital biomarkers in practice.
Researchers and health professionals often rely on limited guidance for using wearable data in clinical practice and chronic disease management.

Recommendations
Implement the DACIA framework to provide interdisciplinary guidance on using wearable sensor data for digital biomarker development.
Focus on participant needs as a crucial factor for study success, applicable to both short and long-duration studies.
Involve relevant stakeholders in each key step of the DACIA framework in an iterative manner.
Apply the DACIA framework to explore digital biomarkers using various devices or signal measurements.
Reduce participant burden through support and continuous feedback.

Regulatory Considerations
Not mentioned