Domain Knowledge Augmented Contrastive Learning on Dynamic Hypergraphs for Improved Health Risk Prediction
Preprint
Abstract
Accurate health risk prediction is crucial for making informed clinical decisions and assessing the appropriate allocation of medical resources. While recent deep learning based approaches have shown great promise in risk prediction, they primarily focus on modeling the sequential information in Electronic Health Records (EHRs) and fail to leverage the rich mobility interactions among health entities. As a result, the existing approaches yield unsatisfactory performance in downstream risk prediction tasks, especially tasks such as Clostridioides difficile Infection (CDI) incidence prediction that are primarily spread through mobility interactions. To address this issue, we propose a new approach that leverages Hypergraphs to explicitly model mobility interactions to improve predictive performance in health risk prediction tasks. Unlike regular graphs that are limited to modeling pairwise relationships, hypergraphs can effectively characterize the complex high-order semantic relationships between health entities. Moreover, we introduce a new contrastive learning strategy that exploits the domain knowledge to generate semantically meaningful positive (homologous) and negative (heterologous) pairs needed for contrastive learning. This unique contrastive pair augmentation strategy boosts the power of contrastive learning by generating feature representations that are both robust and well-aligned with the domain knowledge. Experiments on two real-world datasets demonstrate the advantage of our approach in both short-term and long-term risk prediction tasks, such as Clostridioides difficile infection incidence prediction and MICU transfer prediction. Our framework obtains gains in performance up to 29.49 % for PHOP, 30.64 % for MIMIC-IV for MICU transfer prediction, 13.17 % for PHOP, and 4.45 % for MIMIC-IV for CDI Incidence Prediction.Keywords
This publication has 38 references indexed in Scilit:
- MIMIC-IV, a freely accessible electronic health record datasetScientific Data, 2023
- Evaluation of available risk scores to predict multiple cardiovascular complications for patients with type 2 diabetes mellitus using electronic health recordsComputer Methods and Programs in Biomedicine Update, 2022
- Dynamic hypergraph neural networks based on key hyperedgesInformation Sciences, 2022
- Risk-aware temporal cascade reconstruction to detect asymptomatic casesKnowledge and Information Systems, 2022
- Using hospital Admission, Discharge & Transfer (ADT) data for predicting readmissionsMachine Learning with Applications, 2021
- Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health recordsNature Protocols, 2021
- Predictive Modeling of the Hospital Readmission Risk from Patients’ Claims Data Using Machine Learning: A Case Study on COPDScientific Reports, 2019
- A Generalizable, Data-Driven Approach to Predict Daily Risk ofClostridium difficileInfection at Two Large Academic Health CentersInfection Control & Hospital Epidemiology, 2018
- Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)Journal of Biomedical Informatics, 2015
- Applications of advances in nonlinear sensitivity analysis2005