Development and Validation of a Machine Learning Model for Predicting Serum Creatinine-Defined Acute Kidney Injury in Older Adults After Cardiac Surgery

Yuhao Fu, Jiajie Qian, Yang Zhang, Fuhai Ji · 2026

Read Development and Validation of a Machine Learning Model for Predicting Serum Creatinine-Defined Acute Kidney Injury in Older Adults After Cardiac Surgery by Yuhao Fu, Jiajie Qian, Yang Zhang, Fuhai Ji (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-13267824.txt.

Description

Yuhao Fu, Jiajie Qian, Yang Zhang, and Fuhai Ji built and validated a machine learning model that predicts kidney injury after heart surgery in older adults, in a 2026 study. This complication is frequent and devastating in this age group, and early warning would let clinicians act preventively. Data from two centers trained the models; a third center's patients were held back for a truly external test.

Four feature-selection methods agreed on a predictor set, and six learning algorithms were compared. A gradient boosting model, LightGBM, performed best, with an accuracy score of about 0.78 on the standard curve measure. The strongest predictors were lactate level, operation length, two clotting times, and transfusion volume, a clinically sensible list. Explanation plots showed how each factor pushes risk up or down, including nonlinear effects. The authors present the model as a practical risk-stratification tool, while noting it needs prospective testing.

Catalog record

CREATORYuhao Fu, Jiajie Qian, Yang Zhang, Fuhai Ji
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE44 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13267824

Browse the full library · About the Tower of Babel