STROKE PREDICTION USING MACHINE LEARNING TECHNIQUES - Thesis

Aug 2, 2026

Health and lifestyle factors increasingly contribute to stroke risk, making early detection and prediction critical to prevent progression and reduce burden on patients. This thesis investigates stroke prediction using five supervised machine learning classifiers—Decision Tree, Random Forest, Support Vector Machine, Naïve Bayes, and K-Nearest Neighbor—trained on a preprocessed dataset of 5110 items with 10 attributes. Model performance is assessed using a confusion matrix and, with 95.8% accuracy, the Random Forest approach performs best. The results support more effective clinical estimation when combined with medical background and physical activity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages38

Reading Time1 h 36 min

AccessFree to download

1 INTRODUCTION

2 LITERATURE REVIEW

3 METHODOLOGIES

3.1 Data Description

3.2 Data Preprocessing

3.3 Machine Learning Algorithms

3.4 Evaluation Metrics

3.5 Working Flowchart

4 RESULTS AND ANALYSIS

4.1 Correlation Results

4.2 Graphical Representation

4.3 Confusion Matrix Results

5 CONCLUSION

REFERENCES

Mohammad Rahman STROKE PREDICTION USING MACHINE LEARNING TECHNIQUES Thesis CENTRIA UNIVERSITY OF APPLIED SCIENCES INFORMATION TECHNOLOGY DECEMBER 2023 ABSTRACT | Centria University of Applied Sciences | Date
December 2023 | Author
Mohammad Rahman | | --- | --- | --- | | Degree programme
Information Technology | | | | Name of thesis
STROKE PREDICTION USING MACHINE LEARNING TECHNIQUES | | | | Centria supervisor
Aliasghar Khavasi | | Pages
33 + 6 | | People today are affected by a wide range of diseases as an impact of the current state of the environment and human lifestyle choices. Early detection and prediction of such diseases are necessary to prevent them from progressing to their final stages. Stroke, a cerebrovascular illness, is one of the leading causes of death and a significant financial burden on patients. Health-related behavior, which is becoming an increasingly important focus of prevention, is oneof the major risk factors for stroke. The risk of stroke has been predicted using a variety of machine learning algorithms, which also include predictors such as lifestyle variables to automatically diagnose stroke. Five supervised machine learning classifiers, including Decision Tree, Random Forest, Support Vector Machine, Naïve Bayes, and K-Nearest Neighbor Algorithm are utilized in this study to predict strokes. The dataset, consisting of 5110 items with 10 attributes, is preprocessed to make it suitable for prediction, after which the aforementioned classifiers are trained on the data, and the confusion matrix is used to evaluate the performance of the classifiers. With an accuracy of 95.8%, the RF algorithm outperformed all others in the used dataset for predicting strokes based on several physiological parameters. The clinical estimation of stroke using machine learning algorithms can be more effective when compared toa person's medical background and physical activity. In addition to all of these diagnoses, stroke patients require ongoing intensive care, which can be offered by an interdisciplinary team. | | | Keywords Confusion Matrix, Machine Learning, Random Forest Classifier, Stroke LIST OF ABBREVIATIONS AI Artificial Intelligence ANN Artificial Neural Network AUC Area Under the ROC Curve DT Decision Tree DNN Deep Neural Network EMG Electromyography HANN Hybrid Artificial Neural Network KNN K-Nearest Neighbor LR Logistic Regression LSTM Long Short-Term Memory ML Machine Learning NB Naïve Bayes RF Random Forest RLR Regularized Logistic Regression SVM Support Vector Machine XAI Explainable Artificial Intelligence Contents 1 INTRODUCTION..................................................................................................................................... 1 2 LITERATURE REVIEW......................................................................................................................... 5 3 METHODOLOGIES.......................................................................................................................... 12 3.1 Data Description .......................................................................................................................... 12 3.2 Data Preprocessing...................................................................................................................... 13 3.3 Machine Learning Algorithms ................................................................................................... 14 3.4 Evaluation Metrics ...................................................................................................................... 18 3.5 Working Flowchart ..................................................................................................................... 20 4 RESULTS AND ANALYSIS .............................................................................................................. 21 4.1 Correlation Results............

FAQs

What problem does this thesis address?

The thesis targets early detection and prediction of stroke to help prevent it from progressing to advanced stages.

Which machine learning models are used for stroke prediction?

Five supervised classifiers are used: Decision Tree, Random Forest, Support Vector Machine, Naïve Bayes, and K-Nearest Neighbor.

How is model performance evaluated?

Performance is evaluated using a confusion matrix and reported metrics such as accuracy, with Random Forest achieving 95.8% in the described dataset.

Aug 2, 2026

Uploaded by Olivia Brown