Machine-Learning-Derived Model for the Stratification of Cardiovascular risk in Patients with Ischemic Stroke
George Ntaios1, Dimitrios Sagris1, Athanasios Kallipolitis2
1Department of Internal Medicine, University of Thessaly, Greece.
Insights
A new machine-learning model predicts cardiovascular risk in ischemic stroke patients using readily available data. This tool aids in stratifying risk and informing patient management strategies for better outcomes.
Area of Science:
- Cardiology
- Neurology
- Data Science
Background:
- Accurate cardiovascular risk stratification is crucial for managing patients post-ischemic stroke.
- Identifying high-risk individuals can guide personalized treatment strategies and improve prognoses.
Purpose of the Study:
- To develop and validate a machine-learning-derived prognostic model for predicting cardiovascular risk in ischemic stroke patients.
- To identify key clinical and demographic factors associated with major adverse cardiovascular events after stroke.
Main Methods:
- Utilized two prospective stroke registries for training, validation, and testing datasets.
- Employed machine learning algorithms including XGBoost, Random Forest, and Support Vector Machines.
- Assessed major adverse cardiovascular events (stroke, myocardial infarction, cardiovascular death) over a 2-year follow-up period.
Main Results:
- The final model incorporated age, gender, atrial fibrillation, heart failure, hypertension, and medication history.
- XGBoost classifier demonstrated the best performance.
- Achieved an area under the curve of 0.648 in the validation dataset and 0.59 in the test dataset.
Conclusions:
- An externally validated machine-learning model for cardiovascular risk estimation in ischemic stroke patients has been developed.
- The model utilizes easily accessible parameters, facilitating its clinical application.
- This prognostic tool can aid clinicians in risk stratification and management decisions for stroke survivors.
Abstract:
Background Stratification of cardiovascular risk in patients with ischemic stroke is important as it may inform management strategies. We aimed to develop a machine-learning-derived prognostic model for the prediction of cardiovascular risk in ischemic stroke patients.
Materials And Methods:
Two prospective stroke registries with consecutive acute ischemic stroke patients were used as training/validation and test datasets. The outcome assessed was major adverse cardiovascular event, defined as non-fatal stroke, non-fatal myocardial infarction, and cardiovascular death during 2-year follow-up. The variables selection was performed with the LASSO technique. The algorithms XGBoost (Extreme Gradient Boosting), Random Forest and Support Vector Machines were selected according to their performance. The evaluation of the classifier was performed by bootstrapping the dataset 1000 times and performing cross-validation by splitting in 60% for the training samples and 40% for the validation samples.
Results:
The model included age, gender, atrial fibrillation, heart failure, peripheral artery disease, arterial hypertension, statin treatment before stroke onset, prior anticoagulant treatment (in case of atrial fibrillation), creatinine, cervical artery stenosis, anticoagulant treatment at discharge (in case of atrial fibrillation), and statin treatment at discharge. The best accuracy was measured by the XGBoost classifier. In the validation dataset, the area under the curve was 0.648 (95%CI:0.619-0.675) and the balanced accuracy was 0.58 ± 0.14. In the test dataset, the corresponding values were 0.59 and 0.576.
Conclusions:
We propose an externally validated machine-learning-derived model which includes readily available parameters and can be used for the estimation of cardiovascular risk in ischemic stroke patients.
More Related Videos
05:32Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model
Published on: August 11, 2023
09:11Performing Permanent Distal Middle Cerebral with Common Carotid Artery Occlusion in Aged Rats to Study Cortical Ischemia with Sustained Disability
Published on: February 23, 2016
