Contrastive Learning-based Imputation-Prediction Networks for In-hospital Mortality Risk Modeling using EHRs
This work addresses early warning for healthcare professionals by improving mortality risk prediction from EHRs, but it is incremental as it builds on existing imputation and time-decay methods.
The paper tackles predicting in-hospital mortality risk from EHR data, which is challenging due to irregularity and missing values, and shows that their contrastive learning-based network outperforms state-of-the-art methods in imputation and prediction tasks on two real-world datasets.
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.