Region-specific Risk Quantification for Interpretable Prognosis of COVID-19

TL;DR

This paper presents an interpretable deep survival prediction model for COVID-19 prognosis using chest X-ray images, integrating region detection and risk localization to improve clinical interpretability and decision-making.

Contribution

It introduces a novel region-specific, interpretable deep survival model that combines pretrained encoders, risk-specific Grad-CAM, and anatomical detection for COVID-19 prognosis.

Findings

Achieved superior C-indexes of 0.764 and 0.727 on multi-center datasets.

Demonstrated improved interpretability through risk area localization.

Outperformed traditional survival analysis methods in predictive accuracy.

Abstract

The COVID-19 pandemic has strained global public health, necessitating accurate diagnosis and intervention to control disease spread and reduce mortality rates. This paper introduces an interpretable deep survival prediction model designed specifically for improved understanding and trust in COVID-19 prognosis using chest X-ray (CXR) images. By integrating a large-scale pretrained image encoder, Risk-specific Grad-CAM, and anatomical region detection techniques, our approach produces regional interpretable outcomes that effectively capture essential disease features while focusing on rare but critical abnormal regions. Our model's predictive results provide enhanced clarity and transparency through risk area localization, enabling clinicians to make informed decisions regarding COVID-19 diagnosis with better understanding of prognostic insights. We evaluate the proposed method on a multi-center survival dataset and demonstrate its effectiveness via quantitative and qualitative assessments, achieving superior C-indexes (0.764 and 0.727) and time-dependent AUCs (0.799 and 0.691). These results suggest that our explainable deep survival prediction model surpasses traditional survival analysis methods in risk prediction, improving interpretability for clinical decision making and enhancing AI system trustworthiness.