Citation

Abdelhamid Abdraboh, Naveen Ibrahim (2025) Prediction of Osteoporosis drug adverse event using attribute weighted approach and parameter optimized DBSCAN. PhD thesis, Multimedia University.

Full text not available from this repository.

Abstract

Osteoporosis is a serious bone disease that targets older people worldwide. Various drugs have been prescribed for osteoporosis disease. However, these drugs may be associated with adverse events. Adverse drug events are dangerous reactions occurred due to drug usage and cause death in some cases. Predicting severe adverse drug events can help save patients’ lives and reduce healthcare costs. Classification methods are commonly used to predict the severity of adverse events. However, some methods assume independence of attributes. Although the attribute independence assumption makes it tractable for learning, this assumption may not hold in real-world applications. In this thesis, attribute weighing classification methods, i.e., weighted naïve Bayes and weighted logistic regression are proposed to predict the adverse events of osteoporosis drugs. These methods relax the assumption of independence among the attributes. Besides classification, clustering methods, such as DBSCAN, can also be used to detect groups of individuals that may react badly to certain drugs. However, the performance of DBSCAN is sensitive to the choice of the parameters’ values. In this thesis, a new DBSCAN-based clustering method is proposed for personalized treatment of osteoporosis patients. Our method optimized the parameters of DBSCAN for varied-density datasets. We evaluated our methods on the osteoporosis adverse events data obtained from the United States Food and Drug Administration databases. For the proposed weighted naïve Bayes, our method performed equally well compared to the baseline methods. The results of weighted logistic regression showed a higher recognition performance and outperformed the baseline methods. Our proposed DBSCAN clustering method showed an improved performance when compared to the baseline methods.

Item Type:	Thesis (PhD)
Additional Information:	Call No.: Q325.5 .A23 2025
Uncontrolled Keywords:	Machine learning—Industrial applications
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	15 Apr 2026 08:09
Last Modified:	15 Apr 2026 08:09
URII:	http://shdl.mmu.edu.my/id/eprint/15704

Downloads

Edit (login required)