FDA Weighs in on the Development and Use of Digitally Derived Measures for Clinical Investigations

FDA Voices

By: Rick Abramson, M.D., Director, Digital Health Center of Excellence

For decades, much of what we have known about a participant’s health during a clinical investigation has been shaped by what could be observed, measured, or reported during periodic visits to a research site or clinic. Among the most promising opportunities in healthcare today is the use of digital health technologies (DHTs) that are expanding that window. DHTs, especially those enabled by artificial intelligence, can capture information about a person’s health continuously, in real time, and in the context of a person’s everyday life. These technologies can bring clinical investigation closer to participants and patients in their daily lives and at various stages along their health journey. DHTs also enable earlier detection of treatment effects or safety signals and may facilitate decentralized clinical trials.

Rick Abramson, M.D.

The opportunities associated with DHTs align directly with the U.S. Food and Drug Administration’s mission to protect, promote, and advance public health, and they build on the agency’s longstanding commitment to supporting responsible innovation in the development and regulation of medical products. With this goal in mind, the FDA’s medical product centers have jointly published a white paper entitled: “Key Considerations for the Development and Use of Digitally Derived Measures for Clinical Investigations.” The white paper highlights key considerations drawn from existing FDA guidances for the development and use of digitally derived measures (DDMs) as outcomes in clinical investigations. This work directly advances one of the FDA’s express priorities under Public Health Pillar 1, Innovation and Global Leadership: strengthening the use of emerging technologies, including digital health technologies.

DDMs are measures derived from data collected using DHTs. Depending on their intended use, they may serve as clinical outcome assessments, biomarkers, or components of composite endpoints derived from multimodal data. Their potential is significant. A DDM may, in some circumstances, provide insight into mobility, sleep, cardiovascular function, cognition, or other aspects of health as they occur in daily life. In many instances, DDMs can provide information that is even more reflective of a patient’s health and daily functioning than measures collected only in traditional clinical settings.

A measurement taken during a brief clinical encounter may tell us something important about a patient at that moment. A well-designed digital measure may help us understand how that patient is functioning across many moments — and whether a meaningful change persists over time.

The value of a DDM, however, does not simply come from the novelty or sophistication of the technology that produces it. Its value comes from whether the measure is clinically relevant, meaningful to patients, and supported by evidence appropriate to its context of use.

Start With What Matters

One of the central messages of the white paper is that development of a DDM should not begin with the sensor, algorithm, or device. It is helpful to begin with the meaningful aspect of health that researchers seek to understand.

From there, developers should clearly define the concept of interest, the target population, and the intended context of use.

It also highlights the importance of ensuring that the DHT and the resulting measure are fit for purpose. This includes verification that the technology performs a precise and accurate measurement, analytical validation that it appropriately assesses the clinical event or characteristic of interest, and clinical validation that the DDM reflects meaningful changes in a patient’s health or clinical status.

Patients Are Essential to the Science

As the tools for measuring health become more sophisticated, an equally important question remains remarkably simple: Are we measuring something that matters to patients?

Direct input from patients about their experiences can help identify the aspects of health that matter most and ensure that DDMs are designed and evaluated with those priorities in mind.

This approach aligns with our broader mission to ensure patient access to medical products that are safe and effective for their intended uses. It also underscores our dedication to facilitating innovation across the medical enterprise and further supports our understanding that collaboration with stakeholders is essential to unlocking the full potential of DHTs to streamline clinical trials and move care to the home.

Building the Next Generation of Clinical Measurement

DHTs are creating possibilities that would have been difficult to imagine using traditional approaches to clinical measurement alone. Advances in sensors, connected technologies, analytics, artificial intelligence, and multimodal data are expanding both the volume and the types of information that can be collected during a clinical investigation.

The next challenge is not simply technological; it is scientific. We need to determine how to translate those capabilities into measures that are trustworthy, interpretable, meaningful, and appropriate for the decisions they are intended to support.

Experience has shown that technology does not deliver meaningful benefits through innovation alone. Its value depends on careful application to well-defined clinical questions and an understanding of the needs and experiences of the patients it is intended to serve. This white paper is intended to support that process by bringing together key considerations from existing FDA guidances and encouraging collaborative, patient-centered development. Through continued engagement with patients, caregivers, clinicians, researchers, and sponsors, the FDA seeks to help realize the potential of DHTs and DDMs to advance clinical investigation and medical product development.