Contrastive Learning-based Imputation-Prediction Networks for In-hospital Mortality Risk Modeling using EHRs

TL;DR

This paper introduces a contrastive learning-based network that improves in-hospital mortality risk prediction from EHRs by effectively imputing missing data and capturing patient similarities through graph analysis.

Contribution

It proposes a novel contrastive learning framework combined with graph analysis for better imputation and risk prediction from irregular EHR data, outperforming existing methods.

Findings

Outperforms state-of-the-art methods in imputation accuracy.

Achieves higher predictive performance for mortality risk.

Effectively handles irregular and missing EHR data.

Abstract

Predicting the risk of in-hospital mortality from electronic health records (EHRs) has received considerable attention. Such predictions will provide early warning of a patient's health condition to healthcare professionals so that timely interventions can be taken. This prediction task is challenging since EHR data are intrinsically irregular, with not only many missing values but also varying time intervals between medical records. Existing approaches focus on exploiting the variable correlations in patient medical records to impute missing values and establishing time-decay mechanisms to deal with such irregularity. This paper presents a novel contrastive learning-based imputation-prediction network for predicting in-hospital mortality risks using EHR data. Our approach introduces graph analysis-based patient stratification modeling in the imputation process to group similar patients. This allows information of similar patients only to be used, in addition to personal contextual information, for missing value imputation. Moreover, our approach can integrate contrastive learning into the proposed network architecture to enhance patient representation learning and predictive performance on the classification task. Experiments on two real-world EHR datasets show that our approach outperforms the state-of-the-art approaches in both imputation and prediction tasks.