Have a personal or library account? Click to login
Artificial Intelligence in Improving Stroke Diagnosis: Focus on Machine Learning Models and Explainable AI Application Cover

Artificial Intelligence in Improving Stroke Diagnosis: Focus on Machine Learning Models and Explainable AI Application

Open Access
|Feb 2026

Figures & Tables

Figure 1.

The gender distribution in the stroke dataset
The gender distribution in the stroke dataset

Figure 2.

Bar chart illustrating the association between hypertension, age, glucose level, and BMI
Bar chart illustrating the association between hypertension, age, glucose level, and BMI

Figure 3.

Correlation Matrix of the features within the stroke dataset
Correlation Matrix of the features within the stroke dataset

Figure 4.

The Area Under the Curve for all applied models for stroke prediction
The Area Under the Curve for all applied models for stroke prediction

Figure 5:

LIME results of two different scenarios (patient at low risk vs patient at high risk) and the factors influencing the outcome. The higher the absolute amount of weight, the more significant the impact on the projected result.
LIME results of two different scenarios (patient at low risk vs patient at high risk) and the factors influencing the outcome. The higher the absolute amount of weight, the more significant the impact on the projected result.

The overall performance of the six applied ML models

ModelsAccuracyPrecisionRecallF1AUC
Logistic Regression0.7750.7570.8090.7820.846
KNN0.9200.8740.9810.9250.973
SVM0.8940.9060.8780.8920.968
Decision Tree0.9470.9520.9410.9470.947
Random Forest0.9700.9920.9470.9690.994
XGBoost0.9700.9880.9520.9700.992
DOI: https://doi.org/10.2478/eabr-2025-0023 | Journal eISSN: 2956-2090 | Journal ISSN: 2956-0454
Language: English
Page range: 391 - 397
Submitted on: Oct 7, 2025
|
Accepted on: Nov 12, 2025
|
Published on: Feb 25, 2026
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2026 Natacha Usanase, Consolée Uwamahoro, Dilber Uzun Ozsahin, published by University of Kragujevac, Faculty of Medical Sciences
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.