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
Traditional RCTs face high costs, long timelines, recruitment challenges, and lack of diversity.
Recruitment efficiency in stroke trials has decreased over the past 25 years.
Digital tools for stroke prevention often lack quality and interactive functionality.
Decentralized RCTs present challenges in data quality and require validation.
Regulatory and compliance requirements vary significantly across regions.

Recommendations
Adopt decentralized RCTs with a patient-centric approach.
Leverage digital technologies to improve trial efficiency and participant experience.
Ensure participant engagement and education in trial design.
Provide high-quality training and support for decentralized procedures.

Regulatory Considerations
Collaborate with regulatory agencies early in trial design.
Compliance with varying international standards is necessary.
Rapid evolution of technology outpaces regulatory changes.
Cross-border data standards and privacy rules must be observed.

Findings
Digital health technologies often produce noisier data with additional sources of variation compared to traditional clinical trial settings.
There is a significant challenge in maintaining participant engagement and adherence in digital trials.
The need for pilot studies to address data flow, integration, and integrity is crucial.

Recommendations
Enhance participant engagement through hybrid approaches combining digital and traditional methods.
Conduct pilot studies to test data flow and integration before full-scale trials.
Refine data management guidelines based on experiences from digital trials like AHS.
Include diverse expertise in trial leadership, such as software engineers and biostatisticians.
Plan for comprehensive data analysis, including handling missing data.

Regulatory Considerations
Ensure data security, privacy, and integrity throughout the trial.
Develop a comprehensive plan for data analysis and management.
Consider the composition of the Data & Safety Monitoring Board to include diverse expertise.

Findings
The use of Intended Use and Indication for Use is crucial for digital health products to ensure the product is used appropriately and effectively to meet the needs of the intended population. This information helps establish clear expectations for a product's performance and safety, facilitates regulatory approval, and ensures compliance. The Intended Use provides a general description of the digital health product's purpose or function. The Indication for Use describes the disease or condition the device will diagnose, treat, prevent, cure, or mitigate, including a description of the patient population. A change in a product's indication for use from general to specific usually results in a narrower indication concerning function, target population, or disease entity. Levels of specificity for diagnostic and therapeutic products can be categorized, ranging from the identification of a physical parameter (most general) to the identification of an effect on the clinical outcome (most specific).

Recommendations
The Intended Use statement should include the name of the product, the medical purpose, and what it is trying to do for the user. The Indication for Use statement should include the name of the product, the specific condition or disease state it is addressing, the patient population being targeted, what the product features do, whether other technology components are used with the product, and whether it is for "prescription" or "over-the-counter" use. Developers should characterize the users (e.g., by age, knowledge, or language) and describe the usage context (e.g., hospital ward, emergency room, web-based app). The Indication for Use statement should clearly state the product's clinical capabilities and what it is not intended for (e.g., not intended to provide a diagnosis or replace traditional methods).

Regulatory Considerations
The information provided in the Intended Use and Indication for Use statements is used to inform the product's design and development, as well as to guide regulatory decisions about its approval and marketing. Defining these statements facilitates the regulatory approval process and helps ensure compliance with relevant regulations and standards. The FDA defines the levels of specificity as a qualitative ranking of the proposed indications for use. The document provides examples of FDA's "Indications for Use" from submissions, such as the use of an Atrial Fibrillation History Feature, illustrating the necessary detail for regulatory submissions like a 510(k).

Findings
The PPG-based Wrist-monitor provides comparable measurements to traditional devices with less inconvenience.
Further research is needed to confirm accuracy in specific subpopulations.
Current ABPM devices may impact long-term adherence due to discomfort.

Recommendations
Conduct further studies on the device's accuracy in various subpopulations.
Consider the PPG-based device for continuous BP monitoring.
Use the device for hypertension diagnosis and treatment.
Explore the device's use in other inpatient settings.

Regulatory Considerations
The device is FDA cleared for BP measurements.
It is undergoing validation for other inpatient settings.

Findings
The CardiacSense PPG device can reliably detect heart rate in various situations, but noise suppression during activity remains a challenge.
The study did not directly address the device's ability to detect atrial fibrillation in ambulatory patients, indicating a gap in current research.
Further studies are needed to confirm the device's effectiveness in detecting AF during ambulatory conditions.

Recommendations
Improve noise suppression technology to enhance the device's accuracy during motion.
Conduct further studies to validate the device's ability to detect atrial fibrillation in ambulatory patients.
Continue research to address the limitations identified in the current study.

Regulatory Considerations
Adherence to FDA guidance for new medical device applications is crucial.
Ensure compliance with regulatory standards for digital health technologies.

Findings
There is a need for a deeper understanding of biomarker dynamics in response to tcVNS for real-time physiological monitoring.
PPG amplitude is identified as a superior biomarker compared to heart rate for predicting responses to tcVNS.
Current digital health technologies may benefit from exploring beyond standardized waveforms for tcVNS applications.

Recommendations
Focus on PPG amplitude as a primary biomarker for real-time tcVNS systems.
Consider latency in clinical monitoring7 and closed-loop system design.
Explore multimodal closed-loop systems utilizing signals other than ECG and PPG.

Regulatory Considerations
Use of FDA-approved devices like gammaCore for tcVNS.
Ensure user safety during stimulation by varying parameters appropriately.

Findings
The probability of receiving an irregular pulse notification was low, indicating a gap in detection sensitivity.
The study was not designed to assess the algorithm as a screening tool, highlighting a need for further research in this area.
The paroxysmal nature of atrial fibrillation presents challenges in interpreting notifications, suggesting a gap in understanding the condition's episodic nature.

Recommendations
Conduct further research to understand the implications of irregular pulse notifications.
Explore the potential for digital health technologies to engage users with healthcare systems.
Investigate the use of smartwatches and similar devices as population screening tools.
Develop methods to improve the accuracy and reliability of health monitoring algorithms.
Enhance user engagement and follow-up after receiving health notifications.

Regulatory Considerations
Ensure data privacy and consent in large-scale digital health studies.
Address the accuracy and reliability of health monitoring algorithms.
Consider the implications of using consumer-owned devices for health monitoring.

Findings
Existing PROs for HF, such as KCCQ and MLHFQ, are insufficiently sensitive and rely on subjective assessments.
Accelerometer technology offers objective and continuous real-world data that may better capture patient activity and health.
Novel endpoints must be validated through analytical and cross-sectional studies, correlating "time walking" with HF severity and clinical outcomes.
Developing and validating these endpoints is more feasible for patients with NYHA class II/III HF due to their moderate activity levels.
Future refinements and central databases of accelerometer data will enhance endpoint development and application.

Recommendations
Use accelerometer-derived metrics, such as "time spent walking per day," as novel endpoints to complement traditional clinical measures.
Validate novel endpoints through controlled and real-world studies, including correlating them with existing HF measures and clinical outcomes.
Include accelerometer endpoints in exploratory analyses within ongoing HF trials to gather supportive data without requiring regulatory submission.
Establish data standards and centralized databases for accelerometer-derived endpoints to streamline future development.
Collaborate across stakeholders, including patients, clinicians, investigators, and regulators, to align endpoint development with real-world applicability and regulatory requirements.

Regulatory Considerations
Demonstrate that accelerometer-derived endpoints reflect meaningful changes in patient health and correlate with established HF measures.
Validate endpoints in diverse patient populations and real-world settings to support generalizability and regulatory acceptance.
Address missing data and potential biases in accelerometer readings during endpoint analysis and validation.
Ensure endpoints align with regulatory trial design and analysis standards, including blinding and pre-specified analytical plans.
Develop frameworks for incorporating accelerometer-based endpoints into regulatory submissions alongside traditional clinical outcomes.