Encoding of Demographic and Anatomical Information in Chest X-Ray-based Severe Left Ventricular Hypertrophy Classifiers

TL;DR

This paper presents a novel chest X-ray classification method for severe left ventricular hypertrophy that does not depend on anatomical or demographic data, achieving high accuracy and interpretability.

Contribution

It introduces a direct classification framework that predicts hypertrophy from X-rays alone, with quantification of feature importance using Mutual Information Neural Estimation.

Findings

Achieves high AUROC and AUPRC in classification tasks.

Reveals meaningful attribute encoding through neural information estimation.

Supports transparent and interpretable model predictions.

Abstract

While echocardiography and MRI are clinical standards for evaluating cardiac structure, their use is limited by cost and accessibility.We introduce a direct classification framework that predicts severe left ventricular hypertrophy from chest X-rays, without relying on anatomical measurements or demographic inputs. Our approach achieves high AUROC and AUPRC, and employs Mutual Information Neural Estimation to quantify feature expressivity. This reveals clinically meaningful attribute encoding and supports transparent model interpretation.