Medical-AI trial: real-world registry of the Willem AI-based ECG platform (high-risk cardiac patients, large-scale observational) (NCT07333547)

An electrocardiogram (ECG) records the electrical activity of the heart through electrodes on the body and is a simple test that helps detect many cardiac conditions early, from arrhythmias to ischemia. Yet interpreting the waveform is complex, takes cardiologist time, and is costly for health systems. Automating that with AI is the aim of "Willem," the platform from Idoven (Spain) that this study evaluates.

This is a large-scale registry study (NCT07333547) collecting the real-world performance of Willem continuously. Per the registry summary, it is a single-group, observational registry that evaluates the performance of Willem in detecting cardiac abnormalities on the ECGs of high-risk cardiac patients admitted to cardiovascular units.

The performance of Willem has been examined in prior clinical trials, but additional clinical evidence is needed to embed it in real-world settings, and this study fills that gap. Enrollment is both retrospective (existing cases) and prospective (new cases), the target is 200,000 patients, it is recruiting, and completion is planned for 2036 — a long horizon.

The scale of 200,000 and the real-world collection are designed to capture actual performance and operational challenges that constrained trials can miss. AI-based ECG interpretation is expected to ease specialist workload and make screening more efficient, while proving robustness across diverse patients, devices, and settings remains the challenge.

With an industry sponsor accumulating real-world evidence, this registry is one example of how a medical-AI device moves from the trial environment toward routine care (this study evaluates performance and does not establish efficacy or safety).