Application of an interpretable machine learning model based on optimal feature selection for predicting triple-vessel coronary disease: a multicenter retrospective study
Ling Hou, Ke He, Jinbo Zhao, Ke Su, Changjiang Zhang · 2025
Read Application of an interpretable machine learning model based on optimal feature selection for predicting triple-vessel coronary disease: a multicenter retrospective study by Ling Hou, Ke He, Jinbo Zhao, Ke Su, Changjiang Zhang (2025) 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-12700116.txt.
Description
Ling Hou and co-authors built in 2025 an explainable machine learning model for spotting triple-vessel coronary disease. This severe pattern of heart artery blockage marks patients at high risk. The team studied 2,911 patients who had coronary angiography at two hospitals during 2024. A combined marker of leftover cholesterol and inflammation, called RCII, sat at the center of the analysis.
Feature selection narrowed the data to four shared predictors: sex, age, a liver enzyme, and RCII. Six algorithms competed, and a multilayer perceptron performed best on the test set. An explanation method then ranked what drove each prediction. RCII led the list and interacted with the other features. The authors present RCII as a strong, cheap signal for flagging high-risk patients. The open model design lets clinicians see why a flag was raised.
Catalog record
| CREATOR | Ling Hou, Ke He, Jinbo Zhao, Ke Su, Changjiang Zhang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |