Interpretable machine learning for in-hospital mortality risk prediction in patients with ST-elevation myocardial
Karina Iosephovna Shakhgeldyan1, Nikita Sergeevich Kuksin2, Igor Gennadievich Domzhalov3
1Far Eastern Federal University, School of Medicine and Life Science, 10 Ajax Bay, Russky Island, 690922, Vladivostok, Russia; Vladivostok State University, Institute of Information Technology, Gogolya St. 41, 690014, Vladivostok, Russia.
Insights
This study developed an explainable machine learning model to predict in-hospital mortality risk in ST-elevation myocardial infarction (STEMI) patients after percutaneous coronary intervention (PCI). The model achieved high accuracy, aiding in better patient risk assessment.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Coronary heart disease (CHD), particularly ST-elevation myocardial infarction (STEMI), remains a leading cause of mortality globally.
- Despite advancements, predicting in-hospital mortality (IHM) in STEMI patients post-percutaneous coronary intervention (PCI) requires improved tools.
Purpose of the Study:
- To develop and validate an explainable machine learning model for predicting IHM in STEMI patients undergoing PCI.
- To identify key predictors and risk factors for IHM in this patient cohort.
Main Methods:
- Retrospective analysis of 4677 electronic medical records of STEMI patients post-PCI.
- Development and validation of prognostic models using logistic regression, random forest, and stochastic gradient boosting.
- Application of SHapley Additive exPlanations (SHAP) for model interpretability and risk factor identification.
Main Results:
- Prognostic models demonstrated high predictive accuracy, with AUC values of 0.85 and 0.9 at different treatment stages.
- Models incorporating validated risk factors achieved an AUC of 0.87, with the SHAP-based model performing best.
- Key predictors were identified and converted into actionable risk factors for IHM.
Conclusions:
- Explainable machine learning models, particularly those using SHAP, can accurately predict IHM in STEMI patients post-PCI.
- Categorizing continuous variables into risk factors using SHAP enhances the interpretability of IHM predictions.
- The developed models offer valuable tools for clinical decision-making and risk stratification in STEMI management.
Background And Objective:
Despite the constant improvement of coronary heart disease (CHD) diagnostics and treatment methods it remains one of the main causes of death in most countries around the world. And myocardial infarction with ST segment elevation on the electrocardiogram (STEMI) still is one of the most dangerous clinical variants of CHD. This study aims to develop an explainable machine learning model for in-hospital mortality (IHM) risk prediction in STEMI patients after myocardial revascularization by percutaneous coronary intervention (PCI).
Methods:
A single-center observational retrospective study was conducted, enrolling 4677 electronic medical records of patients with STEMI after PCI, which were analyzed using statistical analysis and machine learning methods. A pool of potential IHM predictors was identified, and prognostic models were developed and validated based on multivariate logistic regression, random forest, and stochastic gradient boosting methods at two stages of hospital treatment: during the initial physicians examination in the emergency department and immediately after PCI surgery. To explain the IHM prognosis, threshold values of IHM risk factors were determined using 3 grid search methods for optimal cut-off points, calculating centroids and SHapley Additive exPlanations (SHAP).
Results:
IHM prognostic models were developed using clinical and functional status data of STEMI patients during two stages of hospital treatment. The IHM prediction accuracy according to the first scenario was AUC = 0.85, and according to the second - AUC = 0.9. Predictors identified and validated in the models were converted into risk factors. Models whose parameters were risk factors demonstrated high forecast accuracy (AUC = 0.87), with the best model formed using the SHAP method.
Conclusions:
For the forecast result interpretation risk factors obtained by categorizing continuous variables can be used by assessing the impact of the latter on the end point using the SHAP method.
More Related Videos
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018