medRxiv PreprintsInternational20 November 2026
Clinician gaze as a supervisory signal for electrocardiogram deep learning: a matched-control proof-of-concept study
This is an official announcement record
Firsthand records what medRxiv Preprints announced and links to the original. The wording below is theirs, not ours.
Aims To assess what evidence is required to attribute an apparent effect of clinician-gaze supervision on an electrocardiogram (ECG) deep-learning model to gaze itself, separating target engagement, case specificity, and diagnostic preservation. Methods and results Ten ECG stimuli interpreted by 63 readers yielded 12-lead gaze targets for nine consultants and 20 clinicians. A pretrained 23-output ECG network was fine-tuned with gaze-only loss on eight ECGs per cross-validation fold. Held-out gaze cosine improved modestly (consultants 0.858 to 0.872; all clinicians 0.884 to 0.898), but untraine
Read the official announcement
Opens www.medrxiv.org
More from medRxiv Preprints
- Unmet needs of Polish patients with cystic fibrosis seen through the lens of crowdfunding20 November 2026
- Motherly Plus: Study Protocol of a Randomized Controlled Trial Evaluating a Smartphone-Assisted Single-Session Psychotherapy Intervention for Postpartum Depression20 November 2026
- Targeting memory consolidation in major depression via pharmacological slow-wave sleep promotion20 November 2026
- Epidemiology of Cardiac Structure and Function Among African Caribbeans in Tobago: A Population-based Cohort Study20 November 2026
- Depressive Symptom Trajectories and Incident Cognitive Impairment by Outcome Ascertainment20 November 2026
This content is for informational purposes only and is not medical advice. It is not intended to diagnose, treat, cure, or prevent any disease. Consult a healthcare professional before starting any supplement, treatment, or program: especially if you are pregnant, nursing, taking medication, or managing a health condition.