A multimodal generative model for structured and unstructured electronic health records
Sonish Sivarajkumar, Hang Zhang, Yuelyu Ji, Maneesh Bilalpur, Xizhi Wu, Chenyu Li, Min Gu Kwak, Shyam Visweswaran, Yanshan Wang · 2026
Read A multimodal generative model for structured and unstructured electronic health records by Sonish Sivarajkumar, Hang Zhang, Yuelyu Ji, Maneesh Bilalpur, Xizhi Wu, Chenyu Li, Min Gu Kwak, Shyam Visweswaran, Yanshan Wang (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/PMC13269122.txt.
Description
Sonish Sivarajkumar and co-authors published a journal article in 2026 presenting a computer model for hospital records. The model, called Generative Deep Patient, learns from both numbered data, such as lab results, and doctors' written notes. Most earlier tools used only one kind of record.
Trained on a large intensive care database, the model predicted heart failure and type 2 diabetes with strong scores. Its score for predicting return to hospital within 30 days was weaker. It also wrote discharge summaries that human reviewers rated as faithful, fluent, and useful in care. The authors argue that joining both record types in one model is workable and useful.
Catalog record
| CREATOR | Sonish Sivarajkumar, Hang Zhang, Yuelyu Ji, Maneesh Bilalpur, Xizhi Wu, Chenyu Li, Min Gu Kwak, Shyam Visweswaran, Yanshan Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 106637 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |