Predictive Modeling of Brain Strokes Using Machine Learning

K. M. Govind; S. Kumar Smitha

doi:10.1007/978-981-95-0375-9_17

Predictive Modeling of Brain Strokes Using Machine Learning

K. M. Govind^*
, S. Kumar Smitha

^*Corresponding author for this work

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A stroke, also known as a brain attack, is a life-threatening condition that happens when blood flow to the brain is disrupted either through a blockage in an artery or bleeding in the brain that results in a neurological impairment. This study provides a comprehensive analysis of stroke prediction by using machine learning models on demographic health data and CNN models on CT scanned images. Age, smoking status, hypertension, and gender were identified as strong predictors of stroke risks. XGBoost’s superior recall and F1-score surpassed Random Forest, highlighting its sensitivity to true positive cases. The CNN model achieved 96Future works include expanding the dataset to improve diversity, integrating with Electronic Health Record (EHR) systems, which are digital platforms for storing and managing patients medical information and refining the model through continuous feedback to improve the model prediction across diverse population.

Original language	English
Title of host publication	Information System Design
Subtitle of host publication	AI and ML Applications. ISDIA 2025
Editors	Vikrant Bhateja, Soly Mathew Biju, Siba K. Udgata
Publisher	Springer
Pages	205-219
Number of pages	15
ISBN (Electronic)	9789819503759
ISBN (Print)	9789819503742
DOIs	https://doi.org/10.1007/978-981-95-0375-9_17
Publication status	Published - 2 Jan 2026
Event	9th International Conference on Information System Design and Intelligent Applications 2025 - University of Wollongong, Dubai, United Arab Emirates Duration: 3 Jan 2025 → 4 Jan 2025 Conference number: 9 https://isdia.org/

Publication series

Name	Lecture Notes in Networks and Systems
Volume	1565
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	9th International Conference on Information System Design and Intelligent Applications 2025
Abbreviated title	ISDIA 2025
Country/Territory	United Arab Emirates
City	Dubai
Period	3/01/25 → 4/01/25
Internet address	https://isdia.org/

Keywords

CT scanned image
Random Forest
Stroke prediction
XGBoost

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-981-95-0375-9_17

Cite this

@inproceedings{404fe8e0548c47bab2c6a70cde74e317,

title = "Predictive Modeling of Brain Strokes Using Machine Learning",

abstract = "A stroke, also known as a brain attack, is a life-threatening condition that happens when blood flow to the brain is disrupted either through a blockage in an artery or bleeding in the brain that results in a neurological impairment. This study provides a comprehensive analysis of stroke prediction by using machine learning models on demographic health data and CNN models on CT scanned images. Age, smoking status, hypertension, and gender were identified as strong predictors of stroke risks. XGBoost{\textquoteright}s superior recall and F1-score surpassed Random Forest, highlighting its sensitivity to true positive cases. The CNN model achieved 96Future works include expanding the dataset to improve diversity, integrating with Electronic Health Record (EHR) systems, which are digital platforms for storing and managing patients medical information and refining the model through continuous feedback to improve the model prediction across diverse population.",

keywords = "CT scanned image, Random Forest, Stroke prediction, XGBoost",

author = "Govind, \{K. M.\} and Smitha, \{S. Kumar\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 9th International Conference on Information System Design and Intelligent Applications 2025, ISDIA 2025 ; Conference date: 03-01-2025 Through 04-01-2025",

year = "2026",

month = jan,

day = "2",

doi = "10.1007/978-981-95-0375-9\_17",

language = "English",

isbn = "9789819503742",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "205--219",

editor = "Vikrant Bhateja and Biju, \{Soly Mathew\} and Udgata, \{Siba K.\}",

booktitle = "Information System Design",

url = "https://isdia.org/",

}

Govind, KM & Smitha, SK 2026, Predictive Modeling of Brain Strokes Using Machine Learning. in V Bhateja, SM Biju & SK Udgata (eds), Information System Design: AI and ML Applications. ISDIA 2025. Lecture Notes in Networks and Systems, vol. 1565, Springer, pp. 205-219, 9th International Conference on Information System Design and Intelligent Applications 2025, Dubai, United Arab Emirates, 3/01/25. https://doi.org/10.1007/978-981-95-0375-9_17

Predictive Modeling of Brain Strokes Using Machine Learning. / Govind, K. M.; Smitha, S. Kumar.
Information System Design: AI and ML Applications. ISDIA 2025. ed. / Vikrant Bhateja; Soly Mathew Biju; Siba K. Udgata. Springer, 2026. p. 205-219 (Lecture Notes in Networks and Systems; Vol. 1565).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Predictive Modeling of Brain Strokes Using Machine Learning

AU - Govind, K. M.

AU - Smitha, S. Kumar

N1 - Conference code: 9

PY - 2026/1/2

Y1 - 2026/1/2

N2 - A stroke, also known as a brain attack, is a life-threatening condition that happens when blood flow to the brain is disrupted either through a blockage in an artery or bleeding in the brain that results in a neurological impairment. This study provides a comprehensive analysis of stroke prediction by using machine learning models on demographic health data and CNN models on CT scanned images. Age, smoking status, hypertension, and gender were identified as strong predictors of stroke risks. XGBoost’s superior recall and F1-score surpassed Random Forest, highlighting its sensitivity to true positive cases. The CNN model achieved 96Future works include expanding the dataset to improve diversity, integrating with Electronic Health Record (EHR) systems, which are digital platforms for storing and managing patients medical information and refining the model through continuous feedback to improve the model prediction across diverse population.

AB - A stroke, also known as a brain attack, is a life-threatening condition that happens when blood flow to the brain is disrupted either through a blockage in an artery or bleeding in the brain that results in a neurological impairment. This study provides a comprehensive analysis of stroke prediction by using machine learning models on demographic health data and CNN models on CT scanned images. Age, smoking status, hypertension, and gender were identified as strong predictors of stroke risks. XGBoost’s superior recall and F1-score surpassed Random Forest, highlighting its sensitivity to true positive cases. The CNN model achieved 96Future works include expanding the dataset to improve diversity, integrating with Electronic Health Record (EHR) systems, which are digital platforms for storing and managing patients medical information and refining the model through continuous feedback to improve the model prediction across diverse population.

KW - CT scanned image

KW - Random Forest

KW - Stroke prediction

KW - XGBoost

UR - https://www.scopus.com/pages/publications/105027933028

U2 - 10.1007/978-981-95-0375-9_17

DO - 10.1007/978-981-95-0375-9_17

M3 - Conference contribution

AN - SCOPUS:105027933028

SN - 9789819503742

T3 - Lecture Notes in Networks and Systems

SP - 205

EP - 219

BT - Information System Design

A2 - Bhateja, Vikrant

A2 - Biju, Soly Mathew

A2 - Udgata, Siba K.

PB - Springer

T2 - 9th International Conference on Information System Design and Intelligent Applications 2025

Y2 - 3 January 2025 through 4 January 2025

ER -