Cross-Cancer Transfer Learning for Gastric Cancer Risk Prediction from Electronic Health Records
Daeyoung Hong, Jiung Kim, Jiyong Jung, Consolato M Sergi, Anastasios Koulaouzidis · 2025
Read Cross-Cancer Transfer Learning for Gastric Cancer Risk Prediction from Electronic Health Records by Daeyoung Hong, Jiung Kim, Jiyong Jung, Consolato M Sergi, Anastasios Koulaouzidis (2025) 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/pmc-12731710.txt.
Description
Daeyoung Hong and co-authors published a study in 2025 on predicting stomach cancer risk from health records. Finding high-risk people early could prompt timely scope exams and referrals. The team reasoned that cancers of the gut and nearby organs share signals that can aid learning. They built a method that first learns from other such cancers, then adapts to stomach cancer.
The work used records from one hospital database, with five hundred and eight stomach cancer cases in the target group. The transfer method beat basic models on the main scores and held up best when labels were cut back. The authors note that all data came from one center, so checks at more sites are needed before real use.
Catalog record
| CREATOR | Daeyoung Hong, Jiung Kim, Jiyong Jung, Consolato M Sergi, Anastasios Koulaouzidis |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |