Your Wearable Score Is Not a Clinical Outcome — Until It Proves It Matters
In August, the FDA released a paper on digitally derived measures created from sensors, software, connected devices, and some AI-enabled tools. The agency’s central point is clear: a measure should not be selected simply because a device can collect it; it should link to an aspect of health meaningful to patients, suit the intended population and use case, and be supported by evidence that it is fit for purpose.
Why it matters for your wellness
When an app introduces a new score, ask what it claims to measure, whether it was tested in people and for a purpose like yours, and what decision—if any—it should change.
The futurist lens
Health technology is moving beyond counting everything. The next era is about measuring what matters—and proving it with transparent, patient-relevant evidence.
What happened
The FDA’s paper explains how digitally derived measures (DDMs) from digital health technologies may be used as clinical outcome assessments, biomarkers, or parts of broader research endpoints. It distinguishes verification—whether a technology measures the physical parameter it claims—from analytical validation—whether a derived measure reflects the relevant clinical event or characteristic—and clinical validation—whether that measure captures something meaningful about health or disease status.
The hidden risk / opportunity
Continuous data outside clinics could reveal changes a short appointment misses, make clinical trials more accessible, detect safety signals earlier, and show how treatment affects daily life. The hidden risk is metric theater: a clean dashboard can make an inferred score feel more meaningful than it is. If a measure was built in a different population or lacks a clear connection to a patient-important outcome, precision can become an illusion.
The privacy angle
The FDA says evidence should be proportionate to a digital measure’s risk and intended context of use. A tool used for exploratory research does not have the same evidence needs as a primary endpoint in a pivotal study. Wherever it is used, DDMs can combine sensor data, apps, cloud analytics, research teams, and AI models—so participants need a clear explanation of the data path, retention period, and purpose.
What you should do
Treat an unclear score as a conversation starter or personal observation, not a diagnosis or treatment instruction. If you are in a study that uses an app or wearable, ask what is measured, how long data is kept, whether raw data is shared, and what happens if the device is inaccurate, lost, or not worn as intended.
The bigger picture
The strongest digital-health tools will connect a transparent measurement to a meaningful human outcome, while respecting the people whose data makes that measurement possible. More data does not automatically create better evidence.