Hierarchical Analysis of Visual COVID-19 Features from Chest Radiographs
This work addresses deficiencies in reporting and evaluation for COVID-19 radiology models, potentially aiding clinical workflows, but it is incremental as it builds on existing methods with enhanced interpretability.
The paper tackles the challenge of improving machine learning for COVID-19 chest radiograph analysis by modeling radiological features with a human-interpretable hierarchy and using data-driven error analysis to uncover model blind spots, such as correlations with ICU conditions and feature distinction difficulties.
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.