Predictive model analysis of stroke disease based on machine learning

Xiangchu Sun

doi:10.1117/12.2669554

24 March 2023 Predictive model analysis of stroke disease based on machine learning

Xiangchu Sun

Proceedings Volume 12611, Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022); 126115P (2023) https://doi.org/10.1117/12.2669554
Event: International Conference on Biological Engineering and Medical Science (ICBioMed2022), 2022, Oxford, United Kingdom

Abstract

Brain stroke is a disease caused by a sudden rupture of cerebral blood vessels or brain tissue damage caused by vascular occlusion, with three characteristics of high morbidity, high recurrence, and high mortality. Brain stroke is currently the second leading cause of death in the global population and a leading cause of disability. Due to the short treatment period for brain stroke patients, a timely condition assessment and rapid diagnosis and treatment are crucial to the prognosis of patients. This paper compares the performance of brain stroke prediction models constructed by multiple supervised machine learning models and selects the optimal algorithm and important risk factors. Based on the decision tree, random forest, Gaussian Bayes, and other algorithms, a brain stroke prediction model was constructed to verify the model efficacy, and identify the risk factors of stroke. In conclusion, the performance of the random forest model is the best at present. Of all the risk factors, age is the most influential factor; among all possible risk factors, identifying the glucose level in the body is an important risk factor for stroke.

Citation Download Citation

Xiangchu Sun "Predictive model analysis of stroke disease based on machine learning", Proc. SPIE 12611, Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022), 126115P (24 March 2023); https://doi.org/10.1117/12.2669554

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available