Evaluating biomedical feature fusion on machine learning’s predictability and interpretability of COVID-19 severity types

Abstract

AbstractBackgroundAccurately differentiating severe from non-severe COVID-19 clinical types is critical for the healthcare system to optimize workflow, as severe patients require intensive care. Current techniques lack the ability to accurately predict COVID-19 patients’ clinical type, especially as SARS-CoV-2 continues to mutate.ObjectiveIn this work, we explore both predictability and interpretability of multiple state-of-the-art machine learning (ML) techniques trained and tested under different biomedical data types and COVID-19 variants.MethodsComprehensive patient-level data were collected from 362 patients (214 severe, 148 non-severe) with the original SARS-CoV-2 variant in 2020 and 1000 patients (500 severe, 500 non-severe) with the Omicron variant in 2022-2023. The data included 26 biochemical features from blood testing and 26 clinical features from each patient’s clinical characteristics and medical history. Different types of ML techniques, including penalized logistic regression (LR), random forest (RF),k-nearest neighbors (kNN), and support vector machines (SVM) were applied to build predictive models based on each data modality separately and together for each variant set.ResultsAll ML models performed similarly under different testing scenarios. The fused characteristic modality yielded the highest area under the curve (AUC) score achieving 0.914 on average. The second highest AUC was 0.876 achieved by the biochemical modality alone, followed by 0.825 achieved by clinical modality alone. All ML models were robust when cross-tested with original and Omicron variant patient data. Upon model interpretation, our models ranked elevated d-dimer (biochemical feature), elevated high sensitivity troponin I (biochemical feature), and age greater than 55 years (clinical feature) as the most predictive features of severe COVID-19.ConclusionsWe found ML to be a powerful tool for predicting severe COVID-19 based on comprehensive individual patient-level data. Further, ML models trained on the biochemical and clinical modalities together witness enhanced predictive power. The improved performance of these ML models when trained and cross-tested with Omicron variant data supports the robustness of ML as a tool for clinical decision support.