Contrastive learning improves critical event prediction in COVID-19 patients

Abstract

Deep Learning (DL) models typically require large-scale, balanced training data to be robust, generalizable, and effective in the context of healthcare. This has been a major issue for developing DL models for the coronavirus-disease 2019 (COVID-19) pandemic where data are highly class imbalanced. Conventional approaches in DL use cross-entropy loss (CEL) which often suffers from poor margin classification. We show that contrastive loss (CL) improves the performance of CEL especially in imbalanced electronic health records (EHR) data for COVID-19 analyses. We use a diverse EHR data set to predict three outcomes: mortality, intubation, and intensive care unit (ICU) transfer in hospitalized COVID-19 patients over multiple time windows. To compare the performance of CEL and CL, models are tested on the full data set and a restricted data set. CL models consistently outperform CEL models with differences ranging from 0.04 to 0.15 for AUPRC and 0.05 to 0.1 for AUROC.

Longwise Cluster Analysis for the Prediction of COVID-19 Severity within 72 h of Admission: COVID-DATA-SAVE-LIFES Cohort

“…Another study developed with machine learning tools and based on a decision tree model to anticipate COVID-19 outcomes from a list of 132,939 recovered COVID-19 subjects evidenced that mortality prevalence was specifically clustered among males, older cases, and hospital admission history as predictors of case fatality [ 35 ]. In addition, a database study encompassing hospitalized COVID-19 patients over 24 and 48 h in the Mount Sinai Health System predicted intubation, intensive care unit transfer, and mortality and was able to identify important features, such as pulse oximetry with clinical importance in the outcome [ 36 ]. Results from the current analyses confirm trends during the 72-h outcomes among the three clusters, with some differential responses concerning PCR, hemoglobin, and coagulation indicators, while the fitted logistic regression model for the risk of mechanical ventilation and death considered both variables independently influenced by cluster allocation.…”

State-of-the-Art Deep Learning Methods on Electrocardiogram Data: Systematic Review

“…Mean squared error alone can be minimized with a constant predictor if the BP range does not vary significantly. Alternative cost functions such as cosine similarity, which is maximized with constant inputs, contrastive losses, or combinations thereof, have been successful in classification problems in imbalanced, rare event prediction problems such as critical events in patients with COVID-19 [ 330 ]. For other promising solutions, it would be prudent to examine similar trend prediction problems in other fields such as stock price movement, where progress has been made using intuitive data preparation and creative representation of the prediction targets, in this case, price changes, to generate trend deterministic predictions [ 331 ].…”

Sex trouble: Sex/gender slippage, sex confusion, and sex obsession in machine learning using electronic health records

“…The use of EHRs for machine learning EHR data have been used by machine learning researchers in a variety of contexts, including for retrospective analysis to better understand health phenomena, 80 to identify patients for potential treatments or interventions, 81 and/or to guide clinical care in real time. 82 While training data for medical machine learning does not have to come from EHRs, collecting information at scale makes EHR data especially appealing for machine learning purposes.…”