Explainable Boosting Machine in Sepsis Prediction Using Platelet Metabolomics: An Interpretable Machine Learning Approach
Emek Guldogan, Burak Yagin, Yavuz Korkmaz, Sarah A. Alzakari, Amal K. Alkhalifa, Fahaid Al-Hashem, Fatma Hilal Yagin · 2026
Read Explainable Boosting Machine in Sepsis Prediction Using Platelet Metabolomics: An Interpretable Machine Learning Approach by Emek Guldogan, Burak Yagin, Yavuz Korkmaz, Sarah A. Alzakari, Amal K. Alkhalifa, Fahaid Al-Hashem, Fatma Hilal Yagin (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-13256616.txt.
Description
Emek Guldogan and co-authors present a 2026 study that predicts sepsis from platelet chemistry using a machine learning model built to explain itself. Sepsis kills quickly when missed, and doctors distrust black-box predictors. The data came from twenty-five emergency sepsis patients and fourteen matched non-sepsis patients, with platelet metabolites read by NMR spectroscopy.
Five models went head to head under strict nested validation, and the explainable boosting machine won on discrimination and calibration alike. It flagged carnitine, myo-inositol, ADP, and one phosphate compound as leading single predictors, plus pairings linking energy and amino acid measures. For single patients, the model shows exactly which chemistry pushed the prediction, shown by one case it flagged right. The authors argue open models like this can earn clinical trust while teaching clues about sepsis metabolism.
Catalog record
| CREATOR | Emek Guldogan, Burak Yagin, Yavuz Korkmaz, Sarah A. Alzakari, Amal K. Alkhalifa, Fahaid Al-Hashem, Fatma Hilal Yagin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |