Encoding of Demographic and Anatomical Information in Chest X-Ray-based Severe Left Ventricular Hypertrophy Classifiers
This work addresses the need for more accessible cardiac evaluation tools, offering a cost-effective alternative to echocardiography and MRI, though it appears incremental as it builds on existing imaging and classification methods.
The paper tackles the problem of predicting severe left ventricular hypertrophy from chest X-rays by introducing a direct classification framework that avoids anatomical measurements or demographic inputs, achieving high AUROC and AUPRC scores.
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.