{
  "abstract": "Real-world evidence (RWE) is increasingly used to inform healthcare delivery and expedite access to new therapies, but its value depends on the quality and completeness of information in real-world data (RWD) sources. Tokenization technology enables the integration of patient data from multiple sources, facilitating the development of a comprehensive overview of the patient journey. This study evaluated the accuracy of linked electronic health record (EHR) and insurance claims data for 93 patients with hemophilia B (HB). Tokenization enables secure linkage of patient data from multiple sources by replacing personal identifiers with encrypted tokens, allowing integration while preserving privacy. We assessed the resulting linkage accuracy by comparing hemophilia-related documentation (proportion of patients with matches for hemophilia medication and laboratory results) and patient location (ZIP code). We also evaluated the completeness of these two linked datasets of additional select variables. Tokenization achieved up to 98% linkage accuracy. Completeness varied by data source: EHRs captured 89–100% of key clinical variables, which include disease severity and laboratory values, while claims data ranged from 44–100%, which include healthcare utilization and cost. Full matches were observed in 12% of medication records and 2% of factor laboratory results, highlighting availability in cross-source completeness. Tokenization proved feasible and reliable in a rare disease setting. The small cohort size and rarity of HB enabled manual validation and reduced the risk of erroneous linkages. Findings support the use of tokenization to create composite datasets that integrate clinical and utilization information to provide richer data, thus enhancing the quality of RWE studies in rare diseases. The study’s findings are also limited by the small sample size, which may affect generalizability. However, this study provides a foundational description and provides valuable methodological insights into tokenization accuracy and data completeness across EHR and claims datasets for RWE generation.",
  "abstract_shown": true,
  "affiliations": [
    "Pfizer Inc, United States of America",
    "Pfizer Inc, Bucharest, Romania"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Anna Stachel Kane"
    },
    {
      "affs": [
        1
      ],
      "name": "Diana Madalina Stan"
    },
    {
      "name": "Darren Jeng"
    },
    {
      "name": "Yong Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/brx419rpfm4v4.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0355051",
  "fulltext_url": null,
  "id": "brx419rpfm4v4",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0355051",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "3605|Medical Coding and Health Information"
    ],
    [
      "plos",
      "/Biology and life sciences/Genetics/Heredity/Genetic linkage/Sex linkage/X-linked traits/Hemophilia"
    ],
    [
      "plos",
      "/Computer and information sciences/Data management"
    ],
    [
      "plos",
      "/Computer and information sciences/Information technology/Health information technology/Electronic medical records"
    ],
    [
      "plos",
      "/Medicine and health sciences/Cardiology/Cardiovascular medicine/Cardiovascular diseases/Coagulation disorders/Hemophilia"
    ],
    [
      "plos",
      "/Medicine and health sciences/Cardiology/Cardiovascular medicine/Cardiovascular diseases/Coagulation disorders/Hemophilia B"
    ],
    [
      "plos",
      "/Medicine and health sciences/Clinical genetics/X-linked traits/Hemophilia"
    ],
    [
      "plos",
      "/Medicine and health sciences/Health care/Health care providers"
    ],
    [
      "plos",
      "/Medicine and health sciences/Health care/Health economics/Health insurance"
    ],
    [
      "plos",
      "/Medicine and health sciences/Health care/Health information technology/Electronic medical records"
    ],
    [
      "plos",
      "/Medicine and health sciences/Hematology/Blood coagulation/Coagulation disorders/Hemophilia"
    ],
    [
      "plos",
      "/Medicine and health sciences/Hematology/Blood coagulation/Coagulation disorders/Hemophilia B"
    ],
    [
      "plos",
      "/Medicine and health sciences/Medical conditions/Cardiovascular diseases/Coagulation disorders/Hemophilia"
    ],
    [
      "plos",
      "/Medicine and health sciences/Medical conditions/Cardiovascular diseases/Coagulation disorders/Hemophilia B"
    ],
    [
      "plos",
      "/Medicine and health sciences/Pharmaceutics/Drug therapy"
    ],
    [
      "plos",
      "/Research and analysis methods/Research design/Laboratory tests"
    ],
    [
      "plos",
      "/Social sciences/Economics/Health economics/Health insurance"
    ]
  ],
  "openalex": "W7211943395",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0355051&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/brx419rpfm4v4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:56Z",
      "native_id": "10.1371/journal.pone.0355051",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0355051"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "plos:cardiovascular diseases",
      "subfield": "cardiovascular"
    }
  ],
  "title": "Evaluation of the completeness of a medical record dataset linked to administrative claims through tokenization in patients with Hemophilia B",
  "title_text": "Evaluation of the completeness of a medical record dataset linked to administrative claims through tokenization in patients with Hemophilia B",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:56Z",
  "url": "https://research.draconitic.com/paper/brx419rpfm4v4",
  "venue": "PLOS One",
  "versions": []
}