Muti-Strategy Machine Learning-Driven Muti-Dimensional Dynamic Prediction Model for Stroke Risk

DOI

10.2991/978-94-6463-823-3_51How to use a DOI?

Keywords

Machine Learning; Prediction Model; Stroke Risk

Abstract

Stroke persists as a predominant contributor to global disability and mortality, with its high incidence and adverse outcomes underscoring the clinical urgency for early and precise prediction. Addressing the limitations of conventional prediction models in dynamic data adaptability and cross-population generalizability, this study systematically evaluates the predictive efficacy of three machine learning algorithms—Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR)—based on a multidimensional medical dataset comprising 5,110 cases. Experimental results demonstrate: the Random Forest model achieved superior accuracy (88.13%), though its suboptimal AUC value (58.90%) suggests sensitivity to class imbalance; both SVM (accuracy 76.91%, AUC 70.87%) and LR (accuracy 77.04%, AUC 72.52%) exhibited enhanced clinical discriminative power in ROC analysis. By integrating model advantages through ensemble learning strategies, the developed dynamic prediction system significantly improved prediction stability compared to traditional statistical models (21.6% F1-score enhancement), with its adaptive feature weighting mechanism effectively addressing metabolic parameter heterogeneity across diverse regional populations. This research substantiates the translational value of machine learning in stroke risk stratification, providing an interpretable algorithmic framework for clinical decision support system development.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yiming Guan
PY  - 2025
DA  - 2025/08/31
TI  - Muti-Strategy Machine Learning-Driven Muti-Dimensional Dynamic Prediction Model for Stroke Risk
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 515
EP  - 522
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_51
DO  - 10.2991/978-94-6463-823-3_51
ID  - Guan2025
ER  -