Using Artificial Intelligence in Predicting Ischemic Stroke Events After Percutaneous Coronary Intervention
Chieh-Ju Chao, Pradyumna Agasthi, Timothy Barry
1Associate Professor of Medicine, Director, Echocardiography Lab, Department of Cardiovascular Diseases, Mayo Clinic Arizona, Scottsdale, Arizona. arsanjani.reza@mayo.edu.
Insights
A new machine learning model accurately predicts ischemic stroke (IS) risk after percutaneous coronary intervention (PCI). This random forest model outperforms traditional logistic regression, aiding in better patient management and reducing stroke incidence.
Area of Science:
- Cardiology
- Neurology
- Machine Learning in Medicine
Background:
- Ischemic stroke (IS) is a severe complication following percutaneous coronary intervention (PCI).
- Current risk prediction models for post-PCI IS are lacking.
- This complication leads to significant morbidity and economic burden.
Purpose of the Study:
- To develop and validate a machine learning (ML) model for predicting IS after PCI.
- To compare the performance of an ML model against traditional logistic regression.
Main Methods:
- Utilized data from the Mayo Clinic CathPCI registry (2003-2018).
- Developed a random forest (RF) model and a logistic regression (LR) model.
- Assessed model performance using receiver operator characteristic (ROC) analysis at multiple time points (6 months to 5 years).
Main Results:
- Included 17,356 patients; 1.5% experienced IS within 5 years post-PCI.
- The RF model demonstrated superior predictive accuracy compared to the LR model.
- Periprocedural stroke was identified as the strongest predictor of subsequent IS.
Conclusions:
- The developed RF model accurately predicts both short- and long-term IS risk post-PCI.
- Machine learning offers improved prediction over logistic regression for post-PCI IS.
- Early identification and aggressive management of periprocedural stroke may mitigate future IS risk.
Background:
Ischemic stroke (IS) is an uncommon but severe complication in patients undergoing percutaneous coronary intervention (PCI). Despite significant morbidity and economic cost associated with post PCI IS, a validated risk prediction model is not currently available.
Aims:
We aim to develop a machine learning model that predicts IS after PCI.
Methods:
We analyzed data from Mayo Clinic CathPCI registry from 2003 to 2018. Baseline clinical and demographic data, electrocardiography (ECG), intra/post-procedural data, and echocardiographic variables were abstracted. A random forest (RF) machine learning model and a logistic regression (LR) model were developed. The receiver operator characteristic (ROC) analysis was used to assess model performance in predicting IS at 6-month, 1-, 2-, and 5-years post-PCI.
Results:
A total of 17,356 patients were included in the final analysis. The mean age of this cohort was 66.9 ± 12.5 years, and 70.7% were male. Post-PCI IS was noted in 109 patients (.6%) at 6 months, 132 patients (.8%) at 1 year, 175 patients (1%) at 2 years, and 264 patients (1.5%) at 5 years. The area under the curve of the RF model was superior to the LR model in predicting ischemic stroke at 6 months, 1-, 2-, and 5-years. Periprocedural stroke was the strongest predictor of IS post discharge.
Conclusions:
The RF model accurately predicts short- and long-term risk of IS and outperforms logistic regression analysis in patients undergoing PCI. Patients with periprocedural stroke may benefit from aggressive management to reduce the future risk of IS.
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
10:28Interventional Diagnostic Procedure: A Practical Guide for the Assessment of Coronary Vascular Function
Published on: March 15, 2022