Self-supervised representation learning reveals explainable physiological structure in high-dimensional magnetocardiography - Scorecard - MDSpire

Self-supervised representation learning reveals explainable physiological structure in high-dimensional magnetocardiography

Share

Clinical Scorecard: Self-supervised learning techniques uncover interpretable physiological patterns in high-dimensional magnetocardiography data

Category	Detail
Condition
Key Mechanisms	Remove or rephrase to ensure direct attribution.
Target Population
Care Setting

Add direct sourcing for claims made.

Npj Digital Medicine

by Dominik D. Kranz, Oruç Kahriman, Dominic Dischl, Sascha Treskatsch, André Sander, Johannes Brachmann, Jai-Wun Park, Niels Wessel
June 1, 2026

Pediatric Cardiology (Springer)

Conexiant

Fundus-based model showed moderate-to-good accuracy and improved performance when combined with clinical risk factors in a high-risk cohort

Frontiers In Cardiovascular Medicine