An Interpretable PK-Informed Hybrid Model for Voriconazole Exposure Prediction: Roles of CYP2C19 Genotype and Inflammation
Yehui Zhou, Yuting Yun, Shiting Chen, Xinyi Liu, Hao Liu, Jiaxin Ren, Mengmeng Lu, Jing Ling, Xuping Yang, Zhou Zhou, James Afriyie Osei, Respina Soheili, Jianjun Zou, Nan Hu · 2026
Read An Interpretable PK-Informed Hybrid Model for Voriconazole Exposure Prediction: Roles of CYP2C19 Genotype and Inflammation by Yehui Zhou, Yuting Yun, Shiting Chen, Xinyi Liu, Hao Liu, Jiaxin Ren, Mengmeng Lu, Jing Ling, Xuping Yang, Zhou Zhou, James Afriyie Osei, Respina Soheili, Jianjun Zou, Nan Hu (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-13168551.txt.
Description
Yehui Zhou and co-authors present a 2026 model to forecast exposure to a fungus drug called voriconazole. The drug has a narrow safe band and varies a lot between patients. Wrong doses can fail the cure or cause toxicity, so dose choice needs sharp forecasts.
The team studied 489 inpatients at one hospital from 2020 to 2024. Two filter tools picked the traits that drive drug clearance, among them a gene type tied to drug breakdown and swelling state. Four learning methods were trained on the shared traits, and their clearance forecasts fed a standard dose equation. A mediation analysis and an importance tool explain the paths and weights, which keeps the hybrid model readable for clinicians.
Catalog record
| CREATOR | Yehui Zhou, Yuting Yun, Shiting Chen, Xinyi Liu, Hao Liu, Jiaxin Ren, Mengmeng Lu, Jing Ling, Xuping Yang, Zhou Zhou, James Afriyie Osei, Respina Soheili, Jianjun Zou, Nan Hu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 74 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |