Digital healthcare systems have enabled the collection of mass healthcare data in electronic healthcare records (EHRs), allowing artificial intelligence solutions for various healthcare prediction tasks. However, existing studies often focus on isolated components of EHR data, limiting their predictive performance and interpretability. To address this gap, we propose ProtoEHR, an interpretable hierarchical prototype learning framework that fully exploits the rich, multi-level structure of EHR data to enhance healthcare predictions. More specifically, ProtoEHR models relationships within and across three hierarchical levels of EHRs: medical codes, hospital visits, and patients. We first leverage large language models to extract semantic relationships among medical codes and construct a medical knowledge graph as the knowledge source. Building on this, we design a hierarchical representation learning framework that captures contextualized representations across three levels, while incorporating prototype information within each level to capture intrinsic similarities and improve generalization. To perform a comprehensive assessment, we evaluate ProtoEHR in two public datasets on five clinically significant tasks, including prediction of mortality, prediction of readmission, prediction of length of stay, drug recommendation, and prediction of phenotype. The results demonstrate the ability of ProtoEHR to make accurate, robust, and interpretable predictions compared to baselines in the literature. Furthermore, ProtoEHR offers interpretable insights on code, visit, and patient levels to aid in healthcare prediction.

Extensive adoption of electronic health records (EHRs) offers opportunities for its use in various clinical analyses. We could acquire more comprehensive insights by enriching an EHR cohort with external knowledge (e.g., standardized medical ontology and wealthy semantics curated on the web) as it divulges a spectrum of informative relations between observed medical codes. This paper proposes a novel Knowledge-Induced Medicine Prescribing Network (KindMed) framework to recommend medicines by inducing knowledge from myriad medical-related external sources upon the EHR cohort, rendering them as medical knowledge graphs (KGs). On top of relation-aware graph representation learning to unravel an adequate embedding of such KGs, we leverage hierarchical sequence learning to discover and fuse clinical and medicine temporal dynamics across patients' historical admissions for encouraging personalized recommendations. In predicting safe, precise, and personalized medicines, we devise an attentive prescribing that accounts for and associates three essential aspects, i.e., a summary of joint historical medical records, clinical condition progression, and the current clinical state of patients. We exhibited the effectiveness of our KindMed on the augmented real-world EHR cohorts, etching leading performances against graph-driven competing baselines.

Medical knowledge graphs (KGs) constructed from Electronic Medical Records (EMR) contain abundant information about patients and medical entities. The utilization of KG embedding models on these data has proven to be efficient for different medical tasks. However, existing models do not properly incorporate patient demographics and most of them ignore the probabilistic features of the medical KG. In this paper, we propose DARLING (Demographic Aware pRobabiListic medIcal kNowledge embeddinG), a demographic-aware medical KG embedding framework that explicitly incorporates demographics in the medical entities space by associating patient demographics with a corresponding hyperplane. Our framework leverages the probabilistic features within the medical entities for learning their representations through demographic guidance. We evaluate DARLING through link prediction for treatments and medicines, on a medical KG constructed from EMR data, and illustrate its superior performance compared to existing KG embedding models.