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.

翻译：临床预测模型通常依赖患者的电子健康记录（EHR），但整合医学知识以增强预测和决策仍具挑战性。这是由于个性化预测需要个性化知识图谱（KG），而这类图谱难以通过患者EHR数据直接生成。为解决此问题，我们提出开放世界框架\textsc{GraphCare}，利用外部知识图谱改善基于EHR的预测。该方法从大语言模型（LLM）和外部生物医学知识图谱中提取知识，构建患者特定知识图谱，进而训练本文提出的双注意力增强（BAT）图神经网络（GNN）用于医疗预测。在MIMIC-III与MIMIC-IV两个公共数据集上，\textsc{GraphCare}在死亡率预测、再入院预测、住院时长（LOS）预测及药物推荐四项关键医疗预测任务中全面超越基准模型。在MIMIC-III数据集上，该模型使死亡率与再入院预测的AUROC分别提升17.6%和6.6%，住院时长与药物推荐的F1分数分别提升7.9%和10.8%。值得注意的是，\textsc{GraphCare}在数据稀缺场景中展现出显著优势。研究结果揭示了外部知识图谱在医疗预测任务中的应用潜力，并证明\textsc{GraphCare}在生成个性化知识图谱以促进精准医疗方面具有广阔前景。