Related Experiment Video
Updated: Jun 10, 2025
An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Performance of the Models Predicting In-Hospital Mortality in Patients with ST-Segment Elevation Myocardial
K I Shakhgeldyan1, N S Kuksin2, I G Domzhalov3
1Associate Professor, Director of the Institute of Information Technologies; Vladivostok State University, 41 Gogolya St., Vladivostok, 690014, Russia; Head of the Laboratory of Big Data Analysis in Medicine and Healthcare; Far East Federal University, 10 Ayaks Village, Russkiy Island, Vladivostok, 690922, Russia.
Insights
Predictive models for in-hospital mortality in ST-segment elevation myocardial infarction patients after percutaneous coronary intervention were developed. Machine learning models showed high accuracy, with Shapley additive explanations aiding predictor analysis.
Area of Science:
- Cardiology
- Medical Informatics
- Data Science
Background:
- Predicting in-hospital mortality (IHM) in ST-segment elevation myocardial infarction (STEMI) patients post-percutaneous coronary intervention (PCI) is crucial for patient management.
- Existing scoring systems may not fully capture the complexity of IHM prediction in this population.
- The study investigates the utility of continuous and categorical predictors in enhancing IHM prediction models.
Purpose of the Study:
- To assess the performance of predictive models for IHM in STEMI patients undergoing PCI.
- To compare models developed using continuous versus categorical predictor forms.
- To identify novel predictors and evaluate their influence on IHM using advanced analytical methods.
Main Methods:
- Retrospective analysis of 4674 patient records from a single center.
- Development of IHM prognostic models using multivariate logistic regression (MLR), random forest (RF), and stochastic gradient boosting (SGB).
- Application of Shapley additive explanations (SHAP) for predictor categorization and influence assessment.
Main Results:
- New IHM predictors were identified and validated, augmenting the GRACE scoring system factors.
- Developed MLR, RF, and SGB models demonstrated high and comparable predictive accuracy (AUC 0.88-0.90).
- SHAP analysis revealed varying predictor influences and offered advantages in categorizing predictors compared to other methods.
Conclusions:
- Machine learning algorithms and SHAP analysis enable the development of accurate and interpretable predictive models for IHM.
- Categorization of predictors and assessment of their impact enhance model transparency and clinical utility.
- These advanced data mining techniques offer a robust approach to improving prognostic accuracy in STEMI patients.
Abstract:
The aim of the study is to assess the performance of predictive models developed on the basis of predictors in the continuous and categorical forms to predict the probability of in-hospital mortality (IHM) in patients with ST-segment elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI).
Materials And Methods:
A single-center retrospective study has been conducted, within the framework of which data from 4674 medical records of patients with STEMI after PCI, treated at the Regional Vascular Center of Vladivostok (Russia), have been analyzed. Two groups of patients were identified: group 1 consisted of 318 (6.8%) individuals who died in the hospital, group 2 included 4356 (93.2%) patients with a favorable outcome of treatment. IHM prognostic models were developed using multivariate logistic regression (MLR), random forest (RF), and stochastic gradient boosting (SGB). 6-metric qualities were used to evaluate the accuracy of the models. Threshold values of IHM predictors were determined using a grid search to find the optimal cut-off points, calculating centroids, and Shapley additive explanations. The latter helped evaluate the degree to which the model predictors influence the endpoint.
Results:
Based on the results of the multi-stage analysis of indicators of clinical and functional status of the STEMI patients, new predictors of IHM have been identified and validated, complementing the factors of the GRACE scoring system, their categorization has been carried out and prognostic models with continuous and categorical variables based on MLR, RF, and SGB have been developed. These models had a high (AUC - 0.88 to 0.90) and comparable predictive accuracy, but their predictors differed in various degrees of influence on the endpoint. The comparative analysis has shown that the Shapley additive explanation method has advantages in categorizing predictors compared to other methods and allows for detailing the structure of their relationships with IHM.
Conclusion:
The use of modern data mining methods, including machine learning algorithms, categorization of predictors, and assessment of the degree of their effect on the endpoint, makes it possible to develop predictive models possessing high accuracy and the properties of explanation of the generated conclusions.
Related Concept Videos
01:20Comparing the Survival Analysis of Two or More Groups
01:15Assumptions of Survival Analysis
01:24Kaplan-Meier Approach
01:21Cancer Survival Analysis
01:09Censoring Survival Data
01:30Heart Failure IV: Classification and Diagnostic Evaluation