Hierarchical Analysis of Visual COVID-19 Features from Chest Radiographs

TL;DR

This paper introduces a hierarchical, interpretable model for analyzing COVID-19 features in chest radiographs, improving transparency and understanding of model failures in clinical settings.

Contribution

It proposes a human-interpretable class hierarchy for radiological features and a data-driven error analysis method to identify model blind spots.

Findings

Model failures correlate with ICU imaging conditions.

Hierarchical analysis aligns with radiologists' findings.

Enhanced transparency improves clinical utility assessment.

Abstract

Chest radiography has been a recommended procedure for patient triaging and resource management in intensive care units (ICUs) throughout the COVID-19 pandemic. The machine learning efforts to augment this workflow have been long challenged due to deficiencies in reporting, model evaluation, and failure mode analysis. To address some of those shortcomings, we model radiological features with a human-interpretable class hierarchy that aligns with the radiological decision process. Also, we propose the use of a data-driven error analysis methodology to uncover the blind spots of our model, providing further transparency on its clinical utility. For example, our experiments show that model failures highly correlate with ICU imaging conditions and with the inherent difficulty in distinguishing certain types of radiological features. Also, our hierarchical interpretation and analysis facilitates the comparison with respect to radiologists' findings and inter-variability, which in return helps us to better assess the clinical applicability of models.