Evaluation of the completeness of a medical record dataset linked to administrative claims through tokenization in patients with Hemophilia B
Anna Stachel Kane, Diana Madalina Stan, Darren Jeng, Yong Chen · 2026
Read Evaluation of the completeness of a medical record dataset linked to administrative claims through tokenization in patients with Hemophilia B by Anna Stachel Kane, Diana Madalina Stan, Darren Jeng, Yong Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0355051.txt.
Description
Anna Stachel Kane and coauthors published a 2026 study in PLOS ONE on gluing together medical records and insurance claims without exposing patient identities, using tokenization, which swaps identifiers for encrypted tokens. The test case was hemophilia B, a rare bleeding disorder, where just under one hundred patients' records were linked and hand-checked, the small cohort allowing manual validation. The team judged linkage accuracy and how completely each source captured key facts.
Tokenization linked records with accuracy up to ninety-eight percent. Completeness split by source: the medical records held nearly all key clinical variables, while claims were patchier on clinical detail but carried the utilization and cost data records lack. Only a small share of medication and laboratory entries matched fully across both sources, underlining why combining them adds value. Tokenized linkage, they conclude, is feasible and reliable even in rare diseases, producing richer datasets for real-world evidence.
Catalog record
| CREATOR | Anna Stachel Kane, Diana Madalina Stan, Darren Jeng, Yong Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48244 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |