Key Considerations for the Development and Use of Digitally Derived Measures for Clinical Investigations, FDA Paper
The FDA’s Center for Biologics Evaluation and Research, Center for Drug Evaluation and Research, Center for Devices and Radiological Health, and Oncology Center of Excellence jointly published this paper to highlight key considerations drawn from existing FDA guidances to support the development and use of digitally derived measures (DDMs) as outcomes in clinical investigations.
Executive Summary
Digital health technologies (DHTs), including those enabled by artificial intelligence (AI), have the potential to capture information about a person’s health, continuously in real time, outside of health care settings, for a variety of purposes. For the purposes of this paper, we refer to measures derived from data collected using DHTs as digitally derived measures (DDMs).
This paper highlights key considerations drawing from existing U.S. Food and Drug Administration (FDA) guidances to support the development and use of DDMs as outcomes in clinical investigations. DDMs may be used as clinical outcome assessments (COAs), biomarkers, or as part of multicomponent endpoints derived from multimodal data. FDA encourages the assessment of clinical outcomes that are both clinically relevant and capture what is meaningful to patients. When considering incorporating a DDM as an outcome in a clinical investigation, it can be helpful to start with a justification, which may be updated over time, to identify what evidence will be needed to support the DDM selection, relevance, and validity.
In the context of clinical investigations, a DHT used to generate a DDM should be verified and validated to be considered fit for purpose. Evidence for validation should demonstrate that users understand and can follow the instructions for use. When using a DDM as an outcome in a clinical investigation, it is important to identify potential sources of error and factors that might negatively impact the validity of the DDM. It is also important to involve patients, caregivers, and clinicians in the development process to determine meaningfulness and clinical relevance of the DDM. This paper identifies key considerations from FDA guidances that may facilitate the development of DDMs that quantify meaningful aspects of health, consistent with best practices for patient engagement, measurement science, and software and AI verification and validation. This paper also highlights FDA’s continued focus on a risk-based approach to facilitate innovations in clinical investigations and medical product development by tailoring evidence generation commensurate with the intended use of the DDM. FDA believes a collaborative, patient-centered approach may help unlock the full potential of DHTs to support medical product development and innovation.