Computer Science & Engineering

Permanent URI for this collection

https://ir.oauife.edu.ng/handle/123456789/4337

Browse

Browsing Computer Science & Engineering by Title

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Open Access
    Development of a lifestyle therapy model for hypersion management
    (THE DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING, FACULTY OF TECHNOLOGY, OBAFEMI AWOLOWO UNIVERSITy., 2022) AKHAINE joy ese
    This study elicited medical data and analyzed risk factors for hypertension, formulated and designed a predictive model for the classification of hypertension, implemented the designed model in a clinical decision support system, and evaluated the performance of the system. These were with a view to proffering lifestyle therapy recommendations for the management of early onset hypertension. Structured questionnaires issued to 303 young adults at the General Out-patient Department of General Hospital, Kubwa, FCT-Abuja was used to collect clinical and lifestyle risk factors that are associated with the early onset of hypertension. Information obtained from medical experts, the Federal Ministry of Health (FMoH) and Nigerian Hypertension Society (NHS) were used to create specific lifestyle management recommendation classes for the different risk factors. The random forest classification algorithm was used to formulate a computational model for the classification of hypertension risk and lifestyle recommendations. Two additional lifestyle therapy models formulated with extreme gradient (XG) boost and support vector machine (SVM) machine learning algorithms were also developed. The performance for all the three models were evaluated for accuracy, precision, recall, f1-score, mean absolute percentage error, mean absolute error, mean square error, and mean root square error. The random forest model was used as a base model for comparison. Unified modelling (UML) tools were used to design the random forest model, after which the designs were implemented as a web-based clinical information system. The system was developed using HyperText Markup Language (HTML), javascript (js), and Cascading Style Sheets (CSS) for the front-end development, structured query language (MySQL) for the backend development and Hypertext Preprocessor (PHP) to connect the front-end to the backend. The system was also evaluated using the developed reference standard.