Multiple Organ Failure Prediction with Classifier-Guided Generative Adversarial Imputation Networks

TL;DR

This paper introduces Classifier-GAIN, a novel imputation method that integrates label information into generative adversarial networks to improve early detection of multiple organ failure from incomplete electronic health records.

Contribution

It proposes a classifier-guided generative adversarial imputation network that enhances MOF prediction by jointly training imputation and classification with label-aware data imputation.

Findings

Outperforms classical imputation methods in MOF prediction.

Achieves higher accuracy across various missing data scenarios.

Demonstrates robustness and improved predictive performance.

Abstract

Multiple organ failure (MOF) is a severe syndrome with a high mortality rate among Intensive Care Unit (ICU) patients. Early and precise detection is critical for clinicians to make timely decisions. An essential challenge in applying machine learning models to electronic health records (EHRs) is the pervasiveness of missing values. Most existing imputation methods are involved in the data preprocessing phase, failing to capture the relationship between data and outcome for downstream predictions. In this paper, we propose classifier-guided generative adversarial imputation networks Classifier-GAIN) for MOF prediction to bridge this gap, by incorporating both observed data and label information. Specifically, the classifier takes imputed values from the generator(imputer) to predict task outcomes and provides additional supervision signals to the generator by joint training. The classifier-guide generator imputes missing values with label-awareness during training, improving the classifier's performance during inference. We conduct extensive experiments showing that our approach consistently outperforms classical and state-of-art neural baselines across a range of missing data scenarios and evaluation metrics.