Related Experiment Video
Updated: Oct 23, 2025
Real-time Pressure-volume Analysis of Acute Myocardial Infarction in Mice
Published on: July 2, 2018
Development of a machine learning model to predict the risk of late cardiogenic shock in patients with ST-segment
Zhixun Bai1,2,3, Shan Hu1,2, Yan Wang1,2
1College of Medicine, Soochow University, Suzhou, China.
Insights
This study developed machine learning models to predict cardiogenic shock (CS) risk in ST-elevation myocardial infarction (STEMI) patients. The LASSO model demonstrated superior accuracy, offering a valuable tool for early risk assessment and improved patient outcomes.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Cardiogenic shock (CS) significantly increases in-hospital mortality for ST-segment elevation myocardial infarction (STEMI) patients, exceeding 50%.
- Accurate and timely risk assessment is crucial for managing STEMI patients at risk of developing CS.
- Previous risk models may not adequately account for the dynamic nature of CS development in STEMI.
Purpose of the Study:
- To compare the performance of various machine learning models in predicting in-hospital CS risk among STEMI patients.
- To develop and validate a nomogram for predicting late-onset CS risk in STEMI patients.
- To identify the optimal model for accurate prognostic prediction of CS in STEMI.
Main Methods:
- Utilized logistic regression (LR), LASSO, SVM, LightGBM, and XGBoost models for CS risk prediction in STEMI.
- Trained and tested models on datasets comprising 1,598 and 684 STEMI patients, respectively.
- Evaluated model performance using accuracy, AUC, recall, precision, Gini score, C-index, calibration plots, and decision curve analysis.
Main Results:
- The LASSO and LR models exhibited the highest predictive power, with accuracy over 0.93 and AUC above 0.82.
- The LASSO nomogram demonstrated good differentiation and calibration, achieving a C-index of 0.811 in the test set and 0.821 in internal validation.
- Decision curve analysis confirmed the superior clinical relevance of the LASSO model compared to existing score-based models.
Conclusions:
- Five machine learning models were developed for in-hospital CS prediction in STEMI patients.
- The LASSO model emerged as the best-performing predictive tool.
- The developed LASSO nomogram offers accurate prognostic prediction for CS risk in STEMI patients.
Background:
The in-hospital mortality of patients with ST-segment elevation myocardial infarction (STEMI) increases to more than 50% following a cardiogenic shock (CS) event. This study highlights the need to consider the risk of delayed calculation in developing in-hospital CS risk models. This report compared the performances of multiple machine learning models and established a late-CS risk nomogram for STEMI patients.
Methods:
This study used logistic regression (LR) models, least absolute shrinkage and selection operator (LASSO), support vector regression (SVM), and tree-based ensemble machine learning models [light gradient boosting machine (LightGBM) and extreme gradient boosting (XGBoost)] to predict CS risk in STEMI patients. The models were developed based on 1,598 and 684 STEMI patients in the training and test datasets, respectively. The models were compared based on accuracy, the area under the curve (AUC), recall, precision, and Gini score, and the optimal model was used to develop a late CS risk nomogram. Discrimination, calibration, and the clinical usefulness of the predictive model were assessed using C-index, calibration plotd, and decision curve analyses.
Results:
A total of 2282 STEMI patients recruited between January 1, 2016 and May 31, 2020, were included in the complete dataset. The linear models built using LASSO and LR showed the highest overall predictive power, with an average accuracy over 0.93 and an AUC above 0.82. With a C-index of 0.811 [95% confidence interval (CI): 0.769-0.853], the LASSO nomogram showed good differentiation and proper calibration. In internal validation tests, a high C-index value of 0.821 was achieved. Decision curve analysis (DCA) and clinical impact curve (CIC) examination showed that compared with the previous score-based models, the LASSO model showed superior clinical relevance.
Conclusions:
In this study, five machine learning methods were developed for in-hospital CS prediction. The LASSO model showed the best predictive performance. This nomogram could provide an accurate prognostic prediction for CS risk in patients with STEMI.
More Related Videos
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
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020