PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking

Patient-drug-disease (PDD) Graph dataset, utilising Electronic medical records (EMRS) and biomedical Knowledge graphs. The novel framework to construct the PDD graph is described in the associated publication.<br>PDD is an RDF graph consisting of PDD facts, where a PDD fact is represented by an RDF triple to indicate that a patient takes a drug or a patient is diagnosed with a disease. For instance, (<i>pdd</i>:274671, <i>pdd</i>:diagnosed, sepsis)<br>Data files are in .nt N-Triple format, a line-based syntax for an RDF graph. These can be accessed via openly-available text edit software.<br><b>diagnose_icd_information.nt - </b>contains RDF triples mapping patients to diagnoses. For example:(<i>pdd</i>:18740, <i>pdd</i>:diagnosed, icd99592),where <i>pdd</i>:18740 is a patient entity, and icd99592 is the ICD-9 code of sepsis.<br><b>drug_patients.nt</b><b>- </b>contains RDF triples mapping patients to drugs. For example:(<i>pdd</i>:18740, <i>pdd</i>:prescribed, aspirin),where <i>pdd</i>:18740 is a patient entity, and aspirin is the drug's name.<br><b>Background:</b>Electronic medical records contain multi-format electronic
medical data that consist of an abundance of medical knowledge. Faced with patients' symptoms, experienced caregivers make the right medical decisions
based on their professional knowledge, which accurately grasps relationships
between symptoms, diagnoses and corresponding treatments. In
the associated paper, we aim to capture these relationships by constructing a large
and high-quality heterogenous graph linking patients, diseases, and drugs
(PDD) in EMRs. Specifically, we propose a novel framework to extract
important medical entities from MIMIC-III (Medical Information Mart
for Intensive Care III) and automatically link them with the existing
biomedical knowledge graphs, including ICD-9 ontology and DrugBank.
The PDD graph presented in this paper is accessible on the Web via the
SPARQL endpoint as well as in .nt format in this repository, and provides a pathway for medical discovery and
applications, such as effective treatment recommendations.<br><b>De-identification</b>It is necessary to mention that MIMIC-III contains clinical information of patients. Although the protected health information was de-identifed, researchers who seek to use more clinical data should complete an on-line training course and then apply for the permission to download the complete MIMIC-III dataset: https://mimic.physionet.org/

患者-药物-疾病（Patient-drug-disease, PDD）图谱数据集，依托电子病历（Electronic medical records, EMRS）与生物医学知识图谱构建。构建该PDD图谱的创新研究框架详见相关已发表学术论文。

PDD是一类包含PDD事实的资源描述框架（Resource Description Framework, RDF）图谱，每条PDD事实以RDF三元组形式呈现，用于表述某患者服用某药物，或某患者被诊断患有某疾病。例如：(pdd:274671, pdd:diagnosed, sepsis)，其中sepsis指脓毒症。

数据集文件采用.nt N-Triple格式，这是一种面向RDF图谱的行式语法文件，可通过公开可得的文本编辑软件读取与查看。

**diagnose_icd_information.nt**：包含将患者映射至诊断结果的RDF三元组。示例如下：(pdd:18740, pdd:diagnosed, icd99592)，其中pdd:18740为患者实体，icd99592为脓毒症对应的国际疾病分类第9版（International Classification of Diseases 9th Revision, ICD-9）编码。

**drug_patients.nt**：包含将患者映射至药物的RDF三元组。示例如下：(pdd:18740, pdd:prescribed, aspirin)，其中pdd:18740为患者实体，aspirin为药物名称（阿司匹林）。

**研究背景**：电子病历包含多格式电子医疗数据，蕴含大量医学知识。面对患者的临床症状，经验丰富的医护人员可凭借专业知识，精准把握症状、诊断结果与对应治疗手段之间的关联，从而做出正确的医疗决策。在本研究相关论文中，我们旨在通过构建电子病历中关联患者、疾病与药物的大型高质量异质图谱（即PDD图谱）来捕捉这些关键关联。具体而言，我们提出了一种创新框架，从重症监护医学信息数据库第三版（Medical Information Mart for Intensive Care III, MIMIC-III）中提取关键医学实体，并将其与现有生物医学知识图谱（包括ICD-9本体与药物银行（DrugBank））自动关联。本文所提出的PDD图谱可通过SPARQL端点在Web端获取，同时也可在本仓库中以.nt格式下载，可为医学发现与相关应用（如高效治疗推荐）提供支撑路径。

**去标识化说明**：需要说明的是，MIMIC-III包含患者临床信息。尽管其中受保护的健康信息已完成去标识化处理，但如需使用更多临床数据，研究者需完成在线培训课程并申请权限后方可下载完整的MIMIC-III数据集：https://mimic.physionet.org/