NORMA eResearch @NCI Library

Stroke Detection and Prediction Using Deep Learning Techniques and Machine Learning Algorithms

Chandramohan, Ripu Murdhan (2022) Stroke Detection and Prediction Using Deep Learning Techniques and Machine Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (748kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (443kB) | Preview


A stroke is one of the major causes of mortality in the World, contributing for the death of more individuals in each and every year. The medical industry has made significant strides in curing strokes; nonetheless, a stroke can occur at any time, and its rate of damage is so high that even if it is treated, it can still result in lifelong disability. Using datasets that are available to the public, the purpose of this study is to identify patients who are at risk of having a stroke. This may be done by constructing six separate categorization models as predictors. The Six classification techniques are assessed using two distinct sampling approaches i.e., Adaptive Synthetic Sampling (ADASYN) and Synthetic Minority Oversampling Technique (SMOTE) since medical datasets tend to be very unbalanced. Based on the assessments and conclusions provided in the report, SMOTE and ADASYN fared identically on Accuracy (except for the Neural Network model, where ADASYN did somewhat better than SMOTE). Similarly, approaches performed fairly similarly for Random Forest (SMOTE Accuracy = 76.9, ADASYN Accuracy =77.3), Decision Tree (SMOTE Accuracy = 54.6, ADASYN Accuracy = 56.5), Adaboost (SMOTE Accuracy =55.8, ADASYN Accuracy=55.2), SVC (SMOTE Accuracy =50, ADASYN Accuracy =50). The acquired results are encouraging and have effectively helped towards the solution of the stroke detection problem in the medical business.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > R Medicine (General)
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 19 Jan 2023 16:03
Last Modified: 06 Mar 2023 15:40

Actions (login required)

View Item View Item