Machine learning-based model for prediction of carbamazepine- and allopurinol-induced severe cutaneous adverse reactions in Vietnamese☆
Nguyen Thanh Nguyen, Mai Hoang Tran, Hien Quoc Vu, Vinh Chi Duong, Thi Minh Nguyet Nguyen, Oanh Thi Hoang, Vu Nguyen Anh Mai, Thu-Thuy Can, Nga Quynh Do, Huong Le Thi Minh, Nguyet Nhu Nguyen, Hang Vu Thi, Mai Thi Vu, Anh Quynh Nguyen, Yen Thi Hai Pham, Khiem Van Nguyen, Ly Le, Sheryl van Nunen, Timo · 2026
Read Machine learning-based model for prediction of carbamazepine- and allopurinol-induced severe cutaneous adverse reactions in Vietnamese☆ by Nguyen Thanh Nguyen, Mai Hoang Tran, Hien Quoc Vu, Vinh Chi Duong, Thi Minh Nguyet Nguyen, Oanh Thi Hoang, Vu Nguyen Anh Mai, Thu-Thuy Can, Nga Quynh Do, Huong Le Thi Minh, Nguyet Nhu Nguyen, Hang Vu Thi, Mai Thi Vu, Anh Quynh Nguyen, Yen Thi Hai Pham, Khiem Van Nguyen, Ly Le, Sheryl van Nunen, Timo (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/pmc-13254861.txt.
Description
Nguyen Thanh Nguyen and a large team build machine learning models to predict severe drug skin reactions in Vietnamese patients in a 2026 study. Carbamazepine and allopurinol, two widely used medicines, can trigger life-threatening cutaneous reactions, and the known genetic warning flags, two HLA variants, catch only a fraction of cases. The team sequenced the exomes of 249 patients and controls to search wider.
Eight prediction models were trained separately for each drug. For allopurinol reactions, random forest and extra trees models reached an average accuracy of 99.67 percent across ten independent tests. For carbamazepine, a linear support vector classifier performed best, with an accuracy-curve score of eighty-six percent on held-out data. The authors say the models capture genomic risk beyond the two classic HLA flags. Clinically, they propose assessing high-risk HLA carriers with the model before the first dose.
Catalog record
| CREATOR | Nguyen Thanh Nguyen, Mai Hoang Tran, Hien Quoc Vu, Vinh Chi Duong, Thi Minh Nguyet Nguyen, Oanh Thi Hoang, Vu Nguyen Anh Mai, Thu-Thuy Can, Nga Quynh Do, Huong Le Thi Minh, Nguyet Nhu Nguyen, Hang Vu Thi, Mai Thi Vu, Anh Quynh Nguyen, Yen Thi Hai Pham, Khiem Van Nguyen, Ly Le, Sheryl van Nunen, Timo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |