Prediction of Mortality and Intervention in COVID-19 Patients Using Generative Adversarial Networks

Uiwon Hwang, Euideuk Hwang, Minsoo Kang, Sungroh YoonHealthcare AI and COVID-19 Workshop 2022 · OpenReview

Abstract

The COVID-19 pandemic has resulted in significant mortality and poses a major threat to global public health. Accurate predictions of mortality risk and the need for medical interventions are essential for patient survival and the efficient allocation of limited medical resources. However, machine learning classifiers often struggle with limited data characterized by missing attributes and class imbalances. To address these challenges, we propose HexaGAN, a generative adversarial network with a hint mechanism designed to predict patient survival and interventions such as intubation and supplemental oxygen. Our experiments demonstrate that HexaGAN outperforms existing benchmark techniques, particularly in correctly predicting mortality, where it showed approximately twice the performance of standard methods. This approach offers a promising path toward timely treatment and optimized resource allocation.

Introduction

Predicting critical outcomes for COVID-19 patients, such as the need for mechanical ventilation or the risk of mortality, is vital for hospital resource management. However, Electronic Health Records (EHRs) are frequently incomplete and unbalanced. Specifically, clinical datasets often suffer from three simultaneous "limited data" problems:

  1. Missing Data: Not all patients receive every diagnostic test, leading to missing attributes.
  2. Missing Labels: Outcomes for some patients may go unrecorded due to administrative gaps or labeling costs.
  3. Class Imbalance: The majority of patients survive, making the "deceased" class significantly smaller and harder for standard algorithms to learn.

Traditional approaches typically address these issues sequentially (e.g., imputation followed by oversampling). However, this "cascade" method often fails because it ignores the inherent dependencies between these data flaws. This paper explores a unified framework to address these challenges simultaneously.

Methods and Data

The proposed solution utilizes HexaGAN, a generative framework designed to address missing data, missing labels, and class imbalance within a single architecture. HexaGAN consists of six interacting components, including an encoder (E), multiple generators for imputation ($G_{MI}$) and oversampling ($G_{CG}$), discriminators ($D_{MI}$, $D_{CG}$), and a classifier (C).

A key innovation is the Hint Mechanism. During the data imputation phase, a "hint generator" provides the discriminator with partial information regarding which values were originally missing. This forces the generator to produce more realistic, distribution-faithful data, which in turn improves the final classifier’s performance.

The HexaGAN architecture integrates an encoder, generators, and discriminators with a hint mechanism to handle missing data and class imbalance.

The study utilized the publicly available covid-chestxray-dataset, which includes chest X-ray images and tabular metadata such as age, sex, temperature, and various blood cell counts. The dataset comprised 846 total records, with 468 confirmed COVID-19 cases used as labeled data to predict survival, intubation, and supplemental oxygen requirements.

Results and Discussion

HexaGAN was evaluated against 24 combinations of standard techniques, such as MICE for imputation and SMOTE for oversampling. The results indicated that treating imputation, oversampling, and classification as a single adversarial game is superior to sequential pipelines, as the components "help" each other learn the true underlying distribution of patient data.

Performance Metrics

  • Mortality Prediction: HexaGAN achieved a specificity of 0.8071, nearly doubling the performance of the best benchmark combination (0.4141). This jump in specificity is crucial for correctly identifying high-risk patients despite severe class imbalance.
  • Intervention Prediction: The model achieved a sensitivity of 1.0000 for intubation, successfully identifying every patient in the test set who required a ventilator. For oxygen requirements, it reached an AUROC of 1.0000 at specific hint rates.

The Role of the Hint Rate

The "hint rate" (the probability with which the hint generator provides information to the discriminator) is a critical hyperparameter. Analysis showed that a hint rate between 0.7 and 0.8 yielded the best balance for both mortality and intervention prediction, as shown in the performance curves below.

Performance metrics (F1-score and Specificity) as a function of the hint rate, showing optimal performance peaks.

Conclusion

HexaGAN demonstrates significant potential in predicting COVID-19 outcomes from messy, real-world clinical data. By integrating data imputation and class balancing into the training process via an adversarial framework, the model achieves superior predictive accuracy for high-stakes medical interventions. While the current study is cross-sectional, future work should extend this framework to longitudinal, time-series data to provide real-time clinical recommendations and validate the model on larger, multi-hospital datasets.

Summary updated

Abstract

The COVID-19 pandemic hits worldwide with a significant number of deaths and poses a major threat to public health. Accurate predictions of the risk of death and medical interventions are crucial for the survival of infected patients and the distribution of limited medical resources. Although machine learning classifiers can be used to predict mortality and medical interventions, it is problematic to employ the methods because training data are limited whose attributes may be missing and classes may be imbalanced. To effectively cope with these problems, we construct HexaGAN with a hint mechanism to predict the survival of the patients and medical interventions such as intubation and supplemental oxygen. In experiments, our method outperforms combinations of existing techniques for limited data problems. Notably, our method showed about twice higher performance than benchmarks in predicting deceased patients correctly. We anticipate that our approach could help provide appropriate treatments on time, allocate limited medical resources efficiently, and ultimately reduce the mortality rate of COVID-19 patients.
BibTeX
@inproceedings{hwang2022prediction,
  author = {Uiwon Hwang and Euideuk Hwang and Minsoo Kang and Sungroh Yoon},
  title = {{Prediction of Mortality and Intervention in COVID-19 Patients Using Generative Adversarial Networks}},
  booktitle = {Healthcare AI and COVID-19 Workshop},
  year = {2022},
  url = {https://openreview.net/forum?id=zxxSAdmQsj},
}
Figure