โก Quick Summary
This study utilized explainable artificial intelligence (AI) to analyze systolic blood pressure (SBP) trajectories following endovascular thrombectomy (EVT), revealing that integrating SBP metrics significantly enhances the prediction of functional outcomes. The deep neural network model achieved an impressive AUC of 0.86, outperforming traditional clinical variable models.
๐ Key Details
- ๐ Dataset: 288 patients from the OPTIMAL-BP trial
- ๐งฉ Features used: Clinical variables and SBP metrics
- โ๏ธ Technology: Deep neural network and SHAP analysis
- ๐ Performance: AUC of 0.86 for the best model
๐ Key Takeaways
- ๐ Machine learning can enhance BP management post-EVT.
- ๐ Deep neural networks showed superior predictive performance.
- ๐ก SBP metrics are crucial for predicting functional independence.
- ๐งช SHAP analysis identified key SBP features influencing outcomes.
- ๐ฅ Study conducted across 19 centers in South Korea.
- ๐ Trial period: June 2020 to November 2022.
- ๐ ClinicalTrials.gov Identifier: NCT04205305.
๐ Background
Managing blood pressure (BP) effectively after successful reperfusion from EVT is essential for achieving favorable clinical outcomes. Traditional methods of BP management may not be sufficient, prompting the need for more individualized approaches. The integration of machine learning into clinical practice offers a promising avenue for enhancing predictive modeling and improving patient outcomes.
๐๏ธ Study
This retrospective analysis was part of the OPTIMAL-BP trial, which aimed to compare intensive versus conventional BP management in patients who underwent EVT. The study included data from 288 patients, focusing on the development of machine learning models to predict functional independence at 90 days post-procedure, utilizing both clinical variables and SBP metrics.
๐ Results
The deep neural network model that incorporated SBP metrics achieved an AUC of 0.86, significantly outperforming the model that used only clinical variables, which had an AUC of 0.80 (P = .037). SHAP analysis highlighted the time rate of SBP and minimum SBP as critical predictors, with the time rate being more influential in the intensive management group.
๐ Impact and Implications
The findings from this study underscore the potential of explainable AI in clinical settings, particularly in the management of BP after EVT. By integrating SBP metrics into predictive models, healthcare providers can achieve more accurate forecasts of patient outcomes, ultimately leading to improved individualized care strategies. This approach could pave the way for enhanced decision-making in acute stroke management and beyond.
๐ฎ Conclusion
This study highlights the transformative potential of machine learning in predicting functional outcomes after EVT. By leveraging SBP trajectories, healthcare professionals can enhance their predictive capabilities, leading to better patient management and outcomes. The integration of AI in clinical practice is a promising frontier that warrants further exploration and validation.
๐ฌ Your comments
What are your thoughts on the use of AI in predicting patient outcomes post-EVT? We would love to hear your insights! ๐ฌ Join the conversation in the comments below or connect with us on social media:
Prognostic Modeling Based on Post-Endovascular Thrombectomy Systolic Blood Pressure Trajectories Using Explainable Artificial Intelligence: A Secondary Analysis of the OPTIMAL-BP Trial.
Abstract
Blood pressure (BP) management following successful reperfusion after endovascular thrombectomy (EVT) is critical in achieving favorable clinical outcomes. Individualized BP management using predictive modeling by machine learning may further improve prediction of functional outcomes. This study was a retrospective analysis of data from the Outcome in Patients Treated with Intra-Arterial Thrombectomy-Optimal Blood Pressure Control (OPTIMAL-BP) trial, a randomized controlled trial comparing between intensive and conventional BP management during the 24ย h after successful recanalization by EVT from June 18, 2020, to November 28, 2022. The trial was conducted across 19 centers in South Korea. Machine learning models were developed to predict functional independence (90-day modified Rankin Scale 0 to 2). Model performance was compared between clinical variables only and systolic blood pressure (SBP) metrics in addition to clinical variables. In addition, the Shapley additive explanations (SHAP) analysis was performed to provide model explanation and understand the importance of SBP metrics. A total of 288 patients (61.1% men, median age 75 years [interquartile range, 65-81]) were included. Among the six algorithms, the deep neural network model incorporating SBP metrics performed best on validation, achieving an area under the curve of 0.86 (95% confidence interval, 0.76-0.92) which was significantly better than the model using only clinical variables (area under the curve 0.80 [95% confidence interval, 0.69-0.88], P = .037). Among SBP metrics, SHAP analysis identified time rate of SBP and minimum SBP as important features, with time rate showing greater influence in the intensive group and minimum SBP in the conventional group. Integrating SBP metrics with clinical variables significantly improved machine learning performance in predicting functional outcomes after successful EVT. Explainable artificial intelligence (AI) identified time rate and minimum SBP as key predictors of outcome. Trial Registration Information: ClinicalTrials.gov (NCT04205305; registered December 17, 2019).
Author: [‘Yu R’, ‘Heo J’, ‘Park E’, ‘Joo H’, ‘Jung JW’, ‘Kim KH’, ‘Yun J’, ‘Lee H’, ‘Choi JK’, ‘Lee IH’, ‘Lim IH’, ‘Hong SH’, ‘Baik M’, ‘Kim BM’, ‘Kim DJ’, ‘Shin NY’, ‘Cho BH’, ‘Ahn SH’, ‘Park H’, ‘Sohn SI’, ‘Hong JH’, ‘Song TJ’, ‘Chang Y’, ‘Kim GS’, ‘Seo KD’, ‘Lee K’, ‘Chang JY’, ‘Seo JH’, ‘Lee S’, ‘Baek JH’, ‘Cho HJ’, ‘Shin DH’, ‘Kim J’, ‘Yoo J’, ‘Jung YH’, ‘Hwang YH’, ‘Kim CK’, ‘Kim JG’, ‘Lee CJ’, ‘Park S’, ‘Lee HS’, ‘Kwon SU’, ‘Bang OY’, ‘Heo JH’, ‘Kim YD’, ‘Nam HS’, ‘OPTIMAL-BP trial investigators’]
Journal: J Med Syst
Citation: Yu R, et al. Prognostic Modeling Based on Post-Endovascular Thrombectomy Systolic Blood Pressure Trajectories Using Explainable Artificial Intelligence: A Secondary Analysis of the OPTIMAL-BP Trial. Prognostic Modeling Based on Post-Endovascular Thrombectomy Systolic Blood Pressure Trajectories Using Explainable Artificial Intelligence: A Secondary Analysis of the OPTIMAL-BP Trial. 2026; 50:(unknown pages). doi: 10.1007/s10916-026-02362-9