Findings
Different Digital Health Technologies (DHTs) estimate sleep staging using data from various sensor-based sources (e.g., EEG, actigraphy, ballistocardiography), each with different properties impacting the estimation. Sleep staging algorithms are often proprietary. DHTs interpret sleep staging at different time intervals, or epochs (e.g., polysomnography uses 30-second epochs). DHT vendors transmit data at different levels, ranging from epoch-level data to pre-calculated summary data (e.g., "total sleep time").

Recommendations
Method and Signals: Ask the vendor about their method of sleep monitoring and which signals are being recorded and used, and understand the strengths and limitations of the technology.
Granularity and Epochs: Inquire about the granularity of sleep data estimated (coarse to fine grain) and the epoch length used for sleep annotations, as this informs interpretation and comparability to other research.
Thresholds and Rules: Ask what rules and thresholds are set for confirming events like sleep onset and offset to ensure certainty in the data and inform future interpretation of results.
Data Level: To align with the Core Digital Measures of Sleep, epoch-level data is preferred for further analysis and comparison between measurement systems. If only summary data is offered, ask for a detailed description of the estimation process.
Algorithms and Evidence: Ask for evidence to support the validity and reliability of the estimated sleep stages, which may include peer-reviewed manuscripts, technical documentation, and conference abstracts.

Regulatory Considerations
While not a regulatory document, the recommendations emphasize the need for vendors to provide evidence for the validity and reliability of their proprietary sleep staging algorithms. This evidence, which can be found in peer-reviewed literature or technical documentation, is crucial for establishing confidence in the results arising from the technology, and can be used for inclusion in, for example, regulatory documents.

Findings
Only a small number of novel digital measures have matured into regulatory qualification or efficacy endpoints.
Demonstrating that digital measures are meaningful to patients is a key challenge.
There is resistance from sponsors due to uncertainty about the value of DHT-derived endpoints in regulatory discussions.
Patient experiences are highly heterogeneous, making it difficult to generalize meaningful aspects of health.
Challenges exist in defining clinical significance and classifying digital measures as COAs vs biomarkers.

Recommendations
Engage patients and caregivers in facilitated discussions to incorporate their voices.
Determine the best method for gathering patient input on a case-by-case basis.
Engage patients to inform evidence needs, implementation, and value delivery.
Return summarized health data to participants to motivate and encourage communication with clinicians.

Regulatory Considerations
Understand the FDA's recent guidance on patient engagement in drug development.
Recognize the shift in evidence rigor required by the FDA for demonstrating meaningfulness.
Provide evidence that DHTs are usable, acceptable, and clinically relevant.
Utilize early engagement channels like CPIM and pre-LOI programs offered by the FDA.

Findings
There is a lack of standardized methodologies for deriving meaningful change thresholds for digital endpoints (DEs).
Challenges exist in identifying DEs that capture the most meaningful concepts to patients.
There is a need for further unification and synergy of efforts in the field, especially given the absence of clear cross-agency regulatory frameworks.

Recommendations
Form multidisciplinary task forces to develop consensus expert guidance recommendations.
Improve transparency and sharing of learnings within the industry.
Engage with regulatory bodies early and frequently throughout the DHT development process.
Use anchor-based methods as the primary approach for deriving meaningful change thresholds.
Ensure DEs reflect concepts that are meaningful to patients.

Regulatory Considerations
Early and frequent engagement with regulators is crucial.
DEs must reflect meaningful patient concepts and be validated early in the development process.
Anchor-based methods are preferred by regulatory authorities for deriving meaningful change thresholds.

Findings
There are gaps in assessing aspects of physical function that matter to patients.
Existing assessment methods have limitations, including their episodic nature and burden to patients.
There are currently no approved drugs in the United States for the treatment of cancer cachexia.

Recommendations
Develop and validate digital measures of health.
Ensure digital measures are meaningful to patients.
Qualify digital measures for use in clinical development and regulatory decision-making.

Regulatory Considerations
Qualification of digital measures as drug development tools is necessary.
Digital measures are gaining traction in regulatory decision-making.
The FDA recommends qualification of digital measures in their PFDD guidelines."

Findings
SV95C provides a reliable and sensitive measure of maximal ambulation, addressing limitations of traditional assessments like the 6MWT.
Real-world data collection via wearable devices enhances accuracy and reflects true ambulatory capabilities.
Longitudinal studies confirmed SV95C's ability to detect disease progression and response to corticosteroid treatments.
Correlations with existing clinical outcome assessments (6MWT, NSAA, and 4SC) validate SV95C’s construct validity.
Patients and caregivers support the use of wearable devices in clinical trials, emphasizing reduced burden and improved trial attractiveness.

Recommendations
Use SV95C as a primary endpoint in DMD clinical trials to monitor maximal stride velocity in real-world conditions.
Incorporate SV95C alongside traditional endpoints to ensure comprehensive assessment of therapeutic efficacy.
Establish training protocols for patients and caregivers to optimize compliance with device usage.
Expand normative data for SV95C in younger and more diverse patient populations.
Conduct further research on meaningful change thresholds (MCTs) to refine clinical relevance.

Regulatory Considerations
Ensure SV95C is included as a primary endpoint with supporting secondary endpoints (e.g., muscle strength assessments) for consistency.
Validate wearable devices used for SV95C measurement to meet regulatory standards for accuracy and reliability.
Address variability and standardize protocols for data collection to ensure regulatory compliance.
Collect additional longitudinal data to strengthen the predictive value of SV95C for regulatory submissions.
Incorporate privacy and data security measures to comply with data protection regulations, including anonymization and encryption.

Findings
Despite progress, DHTs are not yet fully accepted in clinical research.
Challenges include small study samples, unrepresentative samples, lack of normative data sets, feature selection bias, and replication issues due to sensor variability.
There is a need for a framework to identify and mitigate sources of variability in DHTs.

Recommendations
Develop a conceptual framework to identify and mitigate sources of variability.
Consider both active and passive monitoring approaches in study designs.
Align knowledge and data sharing across consortia to improve DHTs.
Emphasize normative data sets to establish ground truths for variability.
Encourage precompetitive collaborations to advance regulatory maturity.

Regulatory Considerations
Collaborative efforts like the 3DT project are essential for regulatory maturity.
Global regulatory agencies encourage data-driven engagement through consortia.

Findings
DMOs offer a novel method to monitor mobility performance in real-world conditions across multiple diseases, but no current gold standard exists for direct comparison.
A 24-month observational clinical study with disease-specific cohorts is considered a valid exploratory step for validating DMOs.
Disease-specific endpoints (e.g., EDSS for MS, FEV1 for COPD) are supported as anchors for evaluating DMOs’ predictive capacity and construct validity.
The Later-Life Function & Disability Instrument (LLFDI) requires additional validation for use as a disease-independent biomarker, especially in younger populations.
Validation of DMOs as surrogate endpoints is contingent upon demonstrating robust correlations with established clinical outcomes in each disease.

Recommendations
Continue using disease-specific endpoints (e.g., EDSS for MS, FEV1 for COPD) to validate DMOs within individual diseases.
Validate the LLFDI tool across diverse age groups and diseases to establish its utility as a disease-independent biomarker.
Explore combining multiple DMOs to enhance predictive capacity where applicable.
Focus on disease-specific biomarkers until sufficient evidence supports the use of DMOs as disease-independent endpoints.
Conduct randomized clinical trials as a follow-up to the observational study to evaluate DMOs’ responsiveness to therapeutic interventions.

Regulatory Considerations
Established endpoints must be used to validate DMOs for consideration as secondary endpoints in regulatory submissions.
Disease-specific validation should be prioritized over disease-independent validation until robust evidence supports the latter.
Provide standardized and regionally consistent criteria for endpoints such as care home admission (PFF) or fall frequency (PD).
Correlate DMOs with widely accepted clinical measures (e.g., FEV1 in COPD) to strengthen regulatory positioning.
Incorporate randomization in future studies to further validate DMOs as surrogate endpoints predictive of clinical outcomes.

Findings
Lack of widely accepted tools for digital mobility assessment.
Challenges in technical and clinical validation due to multiple expertise requirements.
Inconsistent testing procedures and variations in norms.
Limitations of current mobility measurement methods.
Need for real-world mobility assessment.

Recommendations
Adopt best practices and innovate with standards and open access tools.
Ensure transparency through regular interaction with stakeholders.
Develop algorithms in an agnostic and fully documented manner.
Make data accessible through a digital data biobank.
Aim for regulatory approval with accurate real-world mobility measurement.

Regulatory Considerations:
Engage in early dialogue with regulatory authorities.
Understand different regulatory requirements based on context of use.
Focus on qualification of new methodologies for safety and efficacy.
Use DMOs to monitor disease progression and as surrogates for secondary endpoints.
Adopt a staged approach to regulatory qualification.

Findings
There is a gap in developing robust and meaningful outcome measures based on DHTT sensor data.
A major challenge is integrating vast amounts of sensor data into meaningful clinical outcome measures.
There is no clear pathway for developing these outcome measures, indicating a need for standardized methods.

Recommendations
Develop roadmaps for data-centric and patient-centric digital outcome measures.
Integrate patient insights into the development of outcome measures.
Ensure statistical robustness and validity in digital outcome measures.
Encourage scientific discourse to reach a consensus on digital outcome measure development.
Combine subjective and objective data for comprehensive patient assessment.

Regulatory Considerations
The field relies on guidance from regulatory authorities like the FDA and EMA.
Regulatory frameworks need to keep pace with the fast-moving nature of DHTTs.
There is a need for consensus on digital outcome measure development that respects established methods.

Findings
Lack of consensus on the type and scope of digital outcome measures.
Partial integration of mobile health technologies into clinical practice.
Challenges in data presentation and interpretation.
Poorly addressed patient compliance and technology illiteracy.
Validation challenges for mobile health technologies.

Recommendations
Target deficits confirmed to be relevant to patients.
Use a combination of devices with an acceptable benefit-to-burden ratio.
Integrate data into patient management platform standards.
Ensure regulatory approval and adoption by healthcare organizations.
Consider pilot use of competing platforms for better integration.

Regulatory Considerations
Understand and overcome regulatory hurdles.
Ensure sustainable financial models.
Consider pilot use of platforms for regulatory integration.

Findings
Widespread use of mobile technologies in clinical trials is impeded by perceived challenges.
Scientific and technical challenges affect decision-making around using mobile technology for data capture.
Concerns include choosing appropriate technology, data collection and analysis, ensuring data authenticity, and designing protocols.

Recommendations
Use CTTI's framework for mobile technology selection to assist sponsors.
Conduct feasibility studies prior to launching trials.
Engage with regulatory authorities early to discuss endpoint appropriateness and validation processes.
Secure data generated by mobile technologies using recommended practical approaches.
Optimize data quality to minimize variability and ensure robust conclusions.

Regulatory Considerations
Engage with the FDA early in the trial design process.
Ensure data integrity and security throughout the data life cycle.
Maintain open dialogue with regulatory authorities regarding trial-specific strategies for data collection and sharing.

Findings
SV95C is a promising secondary endpoint for evaluating drug efficacy in ambulant DMD patients aged 5 and above.
The wearable device provides continuous, objective measurements, overcoming the limitations of episodic tests like the 6MWT, which are influenced by patient motivation and clinic settings.
The system demonstrates strong correlation with existing endpoints (e.g., 6MWT, NSAA), but further longitudinal data are needed to establish it as a primary endpoint.
Variability in SV95C decreases significantly with longer recording durations, with 180 hours recommended as optimal.
Combining SV95C with other gait variables could enhance sensitivity to change and predictive capacity for disease progression.

Findings
SV95C is a promising secondary endpoint for evaluating drug efficacy in ambulant DMD patients aged 5 and above.
The wearable device provides continuous, objective measurements, overcoming the limitations of episodic tests like the 6MWT, which are influenced by patient motivation and clinic settings.
The system demonstrates strong correlation with existing endpoints (e.g., 6MWT, NSAA), but further longitudinal data are needed to establish it as a primary endpoint.
Variability in SV95C decreases significantly with longer recording durations, with 180 hours recommended as optimal.
Combining SV95C with other gait variables could enhance sensitivity to change and predictive capacity for disease progression.

Regulatory Considerations
SV95C requires validation in conjunction with traditional endpoints (e.g., 6MWT, NSAA) to support regulatory submissions.
Device and software updates must be accompanied by bridging data to ensure consistent measurement properties.
Patient data privacy and security must comply with regulatory standards, including encryption of recorded data and limited researcher access to identifiers.
Future applications of SV95C as a primary endpoint will require expanded normative datasets and stronger correlation with clinically meaningful outcomes.
Incorporate SV95C in early-phase exploratory trials to build a robust case for its clinical relevance in pivotal studies.