Derivation and validation of a machine learning-driven score to predict the diagnostic yield of endomyocardial biopsy

1

Endomyocardial biopsy (EMB) is the gold standard for diagnosing many cardiomyopathies despite its low diagnostic yield.
2

A machine-learning score was developed to predict the likelihood of diagnostic EMB using non-invasive data from 775 heart failure patients.
3

The predictive model demonstrated excellent discrimination with an area under the curve of 0.92 in cross-validation and 0.91 in the testing set.
4

Right ventricular late gadolinium enhancement on cardiac magnetic resonance was identified as the strongest predictor for EMB outcomes.
5

This machine-learning-based score may enhance clinical decision-making regarding the use of EMB in heart failure patients.

Npj Digital Medicine

by Christian Basile, Christian L. Polte, Piero Gentile, Entela Bollano, Araz Rawshani, Anders Oldfors, Charlotta Ljungman, Sven-Erik Bartfay, Pia Dahlberg, Clara Hjalmarsson, Marie Björkenstam, Elena Gualini, Antonio Cannatá, Patrizia Pedrotti, Andrea Garascia, Gianluigi Savarese, Aldo Pietro Maggioni, Kristjan Karason, Emanuele Bobbio
February 9, 2026

1