NORMA eResearch @NCI Library

Predicting Stroke at Adulthood Using Machine Learning Techniques

Manjunath, Sudhir Clinton (2023) Predicting Stroke at Adulthood Using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Early identification and primary prevention of stroke is essential because it frequently causes death or severe disability. Hence, the targeted area for this research are the adults aged from 25-64 years. It is crucial to examine the relationships between the risk factors in patients’ medical records and understand how each one contributes to the prediction of strokes, and this is performed by utilising feature selection technique. Since most of the electronic medical records are heavily imbalanced with majority of negative cases, it is hard to train the machine learning models(ML)because they will identify the negative cases most of the time. Hence different sampling techniques are employed to balance the positive and negative cases. The research aims to increase the certainty and dependability of the doctor’s diagnosis. Consequently, a stroke prediction model that integrates ensemble learning in addition to current ML techniques together with the aforementioned approaches is built. Stacking classifier(SC)achieved the best prediction result with 76% recall and an area under the receiver operating curve (AUROC) score of 0.7078, this will aid medical professionals in detecting stroke in its initial
stages using less computing time and effort.

Item Type: Thesis (Masters)
Milosavljevic, Vladimir
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
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 May 2023 16:27
Last Modified: 19 May 2023 16:27

Actions (login required)

View Item View Item