Key result
CatBoost ML model outperforms revised cardiac index score for perioperative stroke prediction, achieving AUC ~0.87.
Why the study?
Current risk stratification methods for perioperative stroke prediction lack accuracy and practicality.
Does a machine learning-based prediction model improve the accuracy of predicting perioperative stroke in surgical patients compared to traditional cardiovascular scores?
Cohort (n=36,906)
Yes
Does a machine learning-based prediction model improve the accuracy of predicting perioperative stroke in surgical patients compared to traditional cardiovascular scores?
Absolute Event Rate: 0.867% vs 0.528%
p-value: p=<0.000
A CatBoost-based machine learning model using preoperative features significantly improves the prediction of 30-day perioperative stroke compared to traditional cardiovascular risk scores.
May aid perioperative stroke risk stratification; hypothesis-generating and requires prospective validation before clinical use.
Perioperative stroke significantly impacts postoperative outcomes. Current risk stratification methods for perioperative stroke prediction lack accuracy and practicality. We aimed to develop a machine learning (ML) model that improves both accuracy and usability for predicting perioperative strokes. Data from 36,502 patients at Seoul National University Hospital (SNUH) were utilized to develop and internally validate. An external validation was conducted using data from 404 patients at Boramae Medical Center (BMC). Perioperative stroke was defined as a brain infarction of ischemic etiology, occurring within 30 days post-surgery. We developed ML-based prediction models comprising preoperative features and compared them with cardiovascular scores. Additionally, we developed a compact model utilizing the 10 most significant features of the best-performing model. The CatBoost-based prediction model showed the best discriminatory power for high-risk patients and outperformed cardiovascular scores in the external validation set (area under the receiver operating characteristics curve [AUC], 0.867 [95% CI: 0.830–0.896]; revised cardiac index score, 0.528 [95% CI: 0.497–0.575; p < 0.000]; CHA2DS2VASc score, 0.706 [95% CI: 0.659–0.748; p < 0.000]. The compactmodel also improved performance (AUC of 0.875 [95% CI: 0.860–0.952]). Our ML-based perioperative stroke prediction model improves accuracy and clinical usability.
No takes yet. Share an insight, caveat, or question.
Oh et al. (2025) conducted a cohort in Perioperative stroke (n=36,906). CatBoost-based machine learning prediction model vs. Revised cardiac index score was evaluated on Area under the receiver operating characteristics curve (AUC) for perioperative stroke prediction (95% CI 0.830-0.896, p=<0.000). The CatBoost-based machine learning model outperformed the revised cardiac index score in predicting perioperative stroke, achieving an AUC of 0.867 versus 0.528.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: