Leveraging free-text clinical records for heart disease classification through structured feature mapping
Noha Alnazzawi · 2026
Read Leveraging free-text clinical records for heart disease classification through structured feature mapping by Noha Alnazzawi (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-0354916.txt.
Description
Alnazzawi, in a 2026 study, asks whether free-text notes in patient records can help predict heart disease. Heart disease covers problems such as heart failure, heart attack, and stroke, and high blood pressure and diabetes raise the risk. Finding risk signs early in messy clinical notes could help doctors act sooner.
The approach maps words in written records onto structured traits, then feeds those traits into a boosting model that learns from many small decision trees. Training drew on both a corpus of clinical narratives and a classic structured heart disease data set. The model sorted patients by whether heart disease was present with solid accuracy in the low eighties, in percent terms. Alnazzawi presents the method as a way to flag high-risk patients from records that clinics already keep.
Catalog record
| CREATOR | Noha Alnazzawi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34005 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |