Please use this identifier to cite or link to this item: https://ruomo.lib.uom.gr/handle/7000/1674
Title: Explainable SHAP-XGBoost models for in-hospital mortality after myocardial infarction
Authors: Tarabanis, Constantine
Kalampokis, Evangelos
Khalil, Mahmoud
Alviar, Carlos L.
Chinitz, Larry A.
Jankelson, Lior
Type: Article
Subjects: FRASCATI::Medical and Health sciences::Clinical medicine
FRASCATI::Engineering and technology
Keywords: Acute coronary syndrome
Explainable machine learning
Myocardial infarction
SHAP
In-hospital mortality
Issue Date: 2023
Publisher: Elsevier
Source: Cardiovascular Digital Health Journal
Volume: 4
Issue: 4
First Page: 126
Last Page: 132
Abstract: Background A lack of explainability in published machine learning (ML) models limits clinicians’ understanding of how predictions are made, in turn undermining uptake of the models into clinical practice. Objective The purpose of this study was to develop explainable ML models to predict in-hospital mortality in patients hospitalized for myocardial infarction (MI). Methods Adult patients hospitalized for an MI were identified in the National Inpatient Sample between January 1, 2012, and September 30, 2015. The resulting cohort comprised 457,096 patients described by 64 predictor variables relating to demographic/comorbidity characteristics and in-hospital complications. The gradient boosting algorithm eXtreme Gradient Boosting (XGBoost) was used to develop explainable models for in-hospital mortality prediction in the overall cohort and patient subgroups based on MI type and/or sex. Results The resulting models exhibited an area under the receiver operating characteristic curve (AUC) ranging from 0.876 to 0.942, specificity 82% to 87%, and sensitivity 75% to 87%. All models exhibited high negative predictive value ≥0.974. The SHapley Additive exPlanation (SHAP) framework was applied to explain the models. The top predictor variables of increasing and decreasing mortality were age and undergoing percutaneous coronary intervention, respectively. Other notable findings included a decreased mortality risk associated with certain patient subpopulations with hyperlipidemia and a comparatively greater risk of death among women below age 55 years. Conclusion The literature lacks explainable ML models predicting in-hospital mortality after an MI. In a national registry, explainable ML models performed best in ruling out in-hospital death post-MI, and their explanation illustrated their potential for guiding hypothesis generation and future study design.
URI: https://doi.org/10.1016/j.cvdhj.2023.06.001
https://ruomo.lib.uom.gr/handle/7000/1674
ISSN: 2666-6936
Other Identifiers: 10.1016/j.cvdhj.2023.06.001
Appears in Collections:Department of Business Administration

Files in This Item:
File Description SizeFormat 
PIIS2666693623000361.pdf832,75 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons