If you use PDD Graph data in your work, please cite the following publication:

  • PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking. In International Semantic Web Conference (ISWC). Springer, Cham, 2017: 219-227. (arxiv pdf)
  • We ask that users who download significant portions of the database cite the MIMIC-III paper in any resulting publications.

  • MIMIC-III, a freely accessible critical care database. Scientific data, 3. (PMC version)
  • The latest news

    In the new version 1.4, we add detailed information about the prescriptions, including the dosage, the duration and so on. These information will be applied to conveniently retrieve the exact adverse drug combinations taken by corresponding patients.

    A specific example please refer to the Tutorial SPARQL Query Example5


    The gap between clinical data and biomedical knowledge graphs:

    The gap between clinical data and biomedical KGs prohibits further exploring medical entity relationships on ether side, as shown in the following figure:


    What is PDD Graph (Patient-Disease-Drug Graph):

    Electronic medical records contain multi-format electronic medical data that consist of an abundance of medical knowledge. Facing with patients symptoms, experienced caregivers make right medical decisions based on their professional knowledge that accurately grasps relationships between symptoms, diagnosis, and treatments. We aim to capture these relationships by constructing a large and high-quality heterogeneous graph linking patients, diseases, and drugs (PDD) in EMRs.

    Specifically, we 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 is accessible on the Web via the SPARQL endpoint, and provides a pathway for medical discovery and applications, such as effective treatment recommendations.

    A subgraph of PDD is illustrated in the following figure to better understand the PDD graph.

    A subgraph of PDD


    Format 1:N-Triples

    RDF data files ended by .nt.

    Format 2:Apache Jena

    Formatted by Apache Jena TDB , you can user it in Jena API.

    Friendly Link

    Our data uses other resources, so we make a statement here.


    Creative Commons License

    This work is licensed under a Creative Commons Attribution 4.0 International License.


  • Meng Wang
  • Lei Shi
  • Update