Publication: Detection of drug-associated rhabdomyolysis through data mining techniques
Issued Date
2020-11-04
Resource Type
Other identifier(s)
2-s2.0-85098516718
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
JCSSE 2020 - 17th International Joint Conference on Computer Science and Software Engineering. (2020), 86-91
Suggested Citation
Patratorn Kunakorntham, Oraluck Pattanaprateep, Charungthai Dejthevaporn, Ratchainant Thammasudjarit, Ammarin Thakkinstian Detection of drug-associated rhabdomyolysis through data mining techniques. JCSSE 2020 - 17th International Joint Conference on Computer Science and Software Engineering. (2020), 86-91. doi:10.1109/JCSSE49651.2020.9268229 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/60912
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Detection of drug-associated rhabdomyolysis through data mining techniques
Other Contributor(s)
Abstract
Copyright © JCSSE 2020 - 17th International Joint Conf. on Computer Science and Software Engineering. Rhabdomyolysis (RM) is a life-threatening adverse drug reaction (ADR). Statins are the common drugs causing RM and weakness as well as a combination with other drugs, which increase the level of statins. The estimated cost per QALY of supportive treatment for RM was 69,742.50 USD per year, but the early detection of ADRs can reduce the cost of approximately 1,400.00 USD per patient. RM has a problem of under-reporting in spontaneous reporting systems (SRSs). Detecting RM at the early stage is the crucial task by finding the relationship between drugs and RM from electronic health records (EHRs). The aim of this study is to propose a predictive model for RM analysis by predicting the probability of RM or weakness in patients who used statin alone or combined with other drugs. The proposed model can predict the probability occurrence of RM or weakness with sensitivity equal to 0.66.