Risk prediction model for in-hospital mortality in women with ST-elevation myocardial infarction: A machine learning
Hend Mansoor1, Islam Y Elgendy2, Richard Segal3
1Department of Health Services Research, University of Florida, College of Public Health, Gainesville, FL, USA.
Insights
This study developed and validated prediction models for in-hospital mortality in women with ST-elevation myocardial infarction (STEMI). Both logistic regression and random forest models showed comparable accuracy, offering useful clinical tools.
Area of Science:
- Cardiology
- Medical Informatics
- Biostatistics
Background:
- Mortality from ST-elevation myocardial infarction (STEMI) is higher in women than men.
- Accurate prediction of in-hospital mortality is crucial for managing STEMI in women.
Purpose of the Study:
- To develop and validate prediction models for all-cause in-hospital mortality in women admitted with STEMI.
- To compare the performance and validity of logistic regression and random forest models.
Main Methods:
- Utilized National Inpatient Sample (NIS) data from 2011-2013 for women admitted with STEMI.
- Developed and internally validated models using 2012 data, and externally validated using 2011 and 2013 data.
- Compared multivariate logistic regression, full random forest, and reduced random forest models.
Main Results:
- Logistic regression model included 11 variables; random forest models included 32 (full) and 17 (reduced) variables.
- Internal validation showed C-indices of 0.84 (logistic regression), 0.81 (full RF), and 0.80 (reduced RF).
- External validation demonstrated stable performance across years, with C-indices ranging from 0.81 to 0.85.
Conclusions:
- Random forest models demonstrated comparable predictive accuracy to logistic regression for in-hospital mortality in women with STEMI.
- Both approaches are valuable and accurate tools for clinical practice in managing STEMI in this population.
Background:
Studies had shown that mortality due to ST-elevation myocardial infarction (STEMI) is higher in women compared with men. The purpose of this study is to develop and validate prediction models for all-cause in-hospital mortality in women admitted with STEMI using logistic regression and random forest, and to compare the performance and validity of the different models.
Methods:
Data from the National Inpatient Sample (NIS) data years 2011-2013 were used to identify women admitted with STEMI. The main outcome was all-cause in-hospital mortality. Patients were divided into development and validation cohorts, and trained models were internally validated using 20% of the 2012 data, and externally validated using 2011 and 2013 NIS data.
Results:
Three main models were developed and compared; multivariate logistic regression, full and reduced random forest models. In the multivariate logistic regression, 11 variables were included in the final model based on backward elimination. The full random forest model contained 32 variables, and the reduced model contained 17 variables selected based on individual variable importance. In the internal validation cohort, the C-index was 0.84, 0.81, and 0.80 for the multivariate logistic regression, full, and reduced random forest models, respectively. The models showed good stability in the external validation cohorts with a C-index for the logistic regression, full, and reduced random forest models of 0.84, 0.85, and 0.81 for year 2011, and 0.82, 0.81, and 0.81 for year 2013, respectively.
Conclusions:
Random forest was comparable to logistic regression in predicting in-hospital mortality in women with STEMI, and can be a useful and accurate tool in clinical practice.