BIO-CXRNET: A Robust Multimodal Stacking Machine Learning Technique for Mortality Risk Prediction of COVID-19 Patients using Chest X-Ray Images and Clinical Data

TL;DR

This paper introduces a multimodal machine learning framework combining chest X-ray images and clinical data to accurately predict mortality risk in COVID-19 patients, aiding early intervention and resource allocation.

Contribution

The study presents a novel multimodal stacking technique and a nomogram-based scoring system for COVID-19 mortality risk prediction, improving accuracy over single-modality models.

Findings

Multimodal approach achieved 89.03% precision and 90.44% sensitivity.

The model predicted death probability with an F1 score of 92.88%.

Area under the curve was 0.981 for development and 0.939 for validation.

Abstract

Fast and accurate detection of the disease can significantly help in reducing the strain on the healthcare facility of any country to reduce the mortality during any pandemic. The goal of this work is to create a multimodal system using a novel machine learning framework that uses both Chest X-ray (CXR) images and clinical data to predict severity in COVID-19 patients. In addition, the study presents a nomogram-based scoring technique for predicting the likelihood of death in high-risk patients. This study uses 25 biomarkers and CXR images in predicting the risk in 930 COVID-19 patients admitted during the first wave of COVID-19 (March-June 2020) in Italy. The proposed multimodal stacking technique produced the precision, sensitivity, and F1-score, of 89.03%, 90.44%, and 89.03%, respectively to identify low or high-risk patients. This multimodal approach improved the accuracy by 6% in comparison to the CXR image or clinical data alone. Finally, nomogram scoring system using multivariate logistic regression -- was used to stratify the mortality risk among the high-risk patients identified in the first stage. Lactate Dehydrogenase (LDH), O2 percentage, White Blood Cells (WBC) Count, Age, and C-reactive protein (CRP) were identified as useful predictor using random forest feature selection model. Five predictors parameters and a CXR image based nomogram score was developed for quantifying the probability of death and categorizing them into two risk groups: survived (<50%), and death (>=50%), respectively. The multi-modal technique was able to predict the death probability of high-risk patients with an F1 score of 92.88 %. The area under the curves for the development and validation cohorts are 0.981 and 0.939, respectively.