Optimal Modelling of Stroke Probability Prediction Through Machine Learning

Yuheng Zhu

2023

Abstract

Stroke has always been a significant threat to human health. Predicting the occurrence of stroke plays a very important role in reducing the prevalence and lethality of stroke. With the development of machine learning techniques, using machine learning techniques to assist in medical decision-making has become a new area of research. This paper used the random forest algorithm and the multilayer perceptron algorithm to predict the probability of a patient suffering from stroke based on his physiological indicators and compared the performance of the two models. By analyzing the importance of features in the Random Forest model, the health factors more correlated with the probability of stroke were obtained. The random forest algorithm was found to be a more suitable optimization model for predicting the probability of stroke. Among the common health factors, age, average blood glucose level, and body mass index had a greater effect on stroke probability.

Paper Citation

in Harvard Style

Zhu Y. (2023). Optimal Modelling of Stroke Probability Prediction Through Machine Learning. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 159-163. DOI: 10.5220/0012810000003885

in Bibtex Style

@conference{daml23,
author={Yuheng Zhu},
title={Optimal Modelling of Stroke Probability Prediction Through Machine Learning},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={159-163},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012810000003885},
isbn={978-989-758-705-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Optimal Modelling of Stroke Probability Prediction Through Machine Learning
SN - 978-989-758-705-4
AU - Zhu Y.
PY - 2023
SP - 159
EP - 163
DO - 10.5220/0012810000003885
PB - SciTePress