Uncertainty and Risk at the Point of Care: Implications of Patient-Generated ECGs and Algorithmic Interpretations for Clinical Decision Making

2026. To appear at ACM CHI 2026.

Rachel Keys, Aisling O'Kane, Paul Marshall & Graham Stuart.

Wearable technologies allow users to generate their own electrocardiogram (ECG) data with heart rhythm interpretations. While patient-generated ECGs have been adopted by cardiologists, their use in decision-making beyond specialist care remains under-explored. In order to improve health outcomes, they must also be actionable for point-of-care clinicians who determine access to further investigations and specialists. We conducted vignette-based interviews with 33 clinicians from primary and emergency care. We found that patient-generated data introduces diagnostic uncertainty, shaped by four factors: legitimacy concerns, challenges in ECG interpretation, the influence of the wider clinical context on trust and diagnostic confidence, and the balancing of patient and professional risk. This duality of risk often overrode earlier considerations, determining how patient-generated data was acted upon. We explore the concepts of diagnostic uncertainty and the duality of risk to situate our findings and explain their clinical implications for integrating PGD at the point of care.