English

GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs

Artificial Intelligence 2024-01-19 v3 Machine Learning

Abstract

Clinical predictive models often rely on patients' electronic health records (EHR), but integrating medical knowledge to enhance predictions and decision-making is challenging. This is because personalized predictions require personalized knowledge graphs (KGs), which are difficult to generate from patient EHR data. To address this, we propose \textsc{GraphCare}, an open-world framework that uses external KGs to improve EHR-based predictions. Our method extracts knowledge from large language models (LLMs) and external biomedical KGs to build patient-specific KGs, which are then used to train our proposed Bi-attention AugmenTed (BAT) graph neural network (GNN) for healthcare predictions. On two public datasets, MIMIC-III and MIMIC-IV, \textsc{GraphCare} surpasses baselines in four vital healthcare prediction tasks: mortality, readmission, length of stay (LOS), and drug recommendation. On MIMIC-III, it boosts AUROC by 17.6\% and 6.6\% for mortality and readmission, and F1-score by 7.9\% and 10.8\% for LOS and drug recommendation, respectively. Notably, \textsc{GraphCare} demonstrates a substantial edge in scenarios with limited data availability. Our findings highlight the potential of using external KGs in healthcare prediction tasks and demonstrate the promise of \textsc{GraphCare} in generating personalized KGs for promoting personalized medicine.

Keywords

Cite

@article{arxiv.2305.12788,
  title  = {GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs},
  author = {Pengcheng Jiang and Cao Xiao and Adam Cross and Jimeng Sun},
  journal= {arXiv preprint arXiv:2305.12788},
  year   = {2024}
}

Comments

ICLR 2024

R2 v1 2026-06-28T10:41:02.301Z