Risk Prediction of Stroke in Atrial Fibrillation Patients Using Machine Learning
Issued Date
2023-01-01
Resource Type
Scopus ID
2-s2.0-85191424437
Journal Title
International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023
Rights Holder(s)
SCOPUS
Bibliographic Citation
International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023 (2023)
Suggested Citation
Faramnuayphol P., Pattanateepapon A., Looareesuwan P., Lolak S., Theera-Ampornpunt N., Thakkinstian A., Suwatcharangkoon S. Risk Prediction of Stroke in Atrial Fibrillation Patients Using Machine Learning. International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023 (2023). doi:10.1109/ICAIIHI57871.2023.10488980 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/98227
Title
Risk Prediction of Stroke in Atrial Fibrillation Patients Using Machine Learning
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Atrial Fibrillation (AF) independently escalates the risk of stroke, leading to more severe neurological deficits and increased mortality among affected patients. Prior studies on nonvalvular atrial fibrillation (NVAF) and stroke risk often overlooked the use of longitudinal data, where some variables may evolve over time. In our analysis, we constructed three predictive models: Cox proportional hazard regression (CPH), random survival forest (RSF), and XGBoost Survival Embeddings (XGBSE) to estimate time-to-event probabilities for stroke, thromboembolic events, and death in patients, distinguishing between those receiving oral anticoagulants (OACs) and those not receiving them. Consequently, RSF emerged as the top-performing model for stroke outcomes, achieving Harrell's C-Index of 0.80 (CI95%: 0.79-0.81) and 0.71 (CI95%: 0.70-0.72) on the training and testing datasets, respectively. However, for the death outcome, XGBSE demonstrated superior performance, attaining the highest Harrell's C-Index on both datasets, with the value of 0.85 (CI95%: 0.83-0.87) and 0.85 (CI95%: 0.84-0.85), respectively. Moreover, the use of machine learning (ML) in time-to-event data analysis offers several advantages, even when the performance for the overall outcome overlaps.