Multiple Organ Failure Prediction with Classifier-Guided Generative Adversarial Imputation Networks
This work addresses a critical issue for clinicians in intensive care by improving early detection of a high-mortality syndrome, though it is incremental as it builds on existing imputation and prediction techniques.
The paper tackled the problem of predicting multiple organ failure in ICU patients by addressing missing values in electronic health records, proposing a classifier-guided generative adversarial imputation network that outperformed existing methods in various scenarios.
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.