Machine learning models for predicting new-onset diabetes following acute pancreatitis using real-world data

Djibril M Ba, Alireza Vafaei Sadr, Yue Zhang, Phil A. Hart, Nazia Raja-Khan, Ruizhe Zhou, Ayesha Siddiqui, Tian Qiu, Jennifer Maranki, Vernon M. Chinchilli, Vida Abedi · 2026

Read Machine learning models for predicting new-onset diabetes following acute pancreatitis using real-world data by Djibril M Ba, Alireza Vafaei Sadr, Yue Zhang, Phil A. Hart, Nazia Raja-Khan, Ruizhe Zhou, Ayesha Siddiqui, Tian Qiu, Jennifer Maranki, Vernon M. Chinchilli, Vida Abedi (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-13536021.txt.

Description

About a quarter of people who survive acute pancreatitis develop diabetes within three years. Djibril Ba and co-authors ask whether machine learning can spot them early. They used a large federated health records network covering 2017 to 2024. The cohort held 58,746 pancreatitis patients with no prior diabetes. Five model types were trained across four prediction windows. Simple logistic regression won.

Its accuracy averaged 0.72, with a discrimination score of 0.79. Top predictors included age, pancreatic necrosis, body weight, and blood pressure. Visit counts and past lab values also mattered. The authors say routine records already carry much of the signal needed for early warning.

Catalog record

CREATORDjibril M Ba, Alireza Vafaei Sadr, Yue Zhang, Phil A. Hart, Nazia Raja-Khan, Ruizhe Zhou, Ayesha Siddiqui, Tian Qiu, Jennifer Maranki, Vernon M. Chinchilli, Vida Abedi
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE41 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13536021

Browse the full library · About the Tower of Babel