Researchers from the University of Arizona and others, including Daniel Malone, RPh, PhD, FAMCP, and C. Kent Kwoh, MD, recently published a study in the journal JAMA Network Open evaluating the use of machine-learning to predict opioid overdose risk.
Dr. Malone is a professor in the Department of Pharmacy, Practice and Science at the UA College of Pharmacy and Epidemiology and Biostatistics Department at the UA Mel and Enid Zuckerman College of Public Health, and leads the Comparative Effectiveness Research Group at the College of Pharmacy.
Dr. Kwoh is a professor of medicine and medical imaging, chief of the UA Division of Rheumatology in the UA College of Medicine – Tucson, director of the UA Arthritis Center and the Charles A.L. and Suzanne M. Stephens Endowed Chair in Rheumatology at the UA.
They’re listed as co-authors in the article which appears in the March 22, 2019, edition of the journal.
Currently used systems may identify patients who are not truly at high risk, the article notes. With a goal of increasing the accuracy for predicting risk of overdose, the research team used machine-learning methods that were applied using Medicare data. The results suggest machine-learning algorithms could predict overuse and individuals likely to overuse opioids, especially those in low-risk subgroups. These techniques could be implemented by a variety of health-care organizations and payers to prevent deaths due to opioid abuse while not over-alerting for individuals who are not abusing opioids.
The research team also included lead author Wei-Hsuan (Jenny) Lo-Ciganic, PhD, a former UA College of Pharmacy faculty member now with the University of Florida School of Pharmacy, along with additional investigators from the University of Florida, University of Pittsburgh, University of Utah, Carnegie Mellon University, both the Salt Lake City and Pittsburgh Veterans Affairs health-care systems, and the UA.
See the link in the reference below to access the article (or click on the image at right).
Lo-Ciganic W, Huang JL, Zhang HH, et al. "Evaluation of Machine-Learning Algorithms for Predicting Opioid Overdose Risk Among Medicare Beneficiaries With Opioid Prescriptions." JAMA Netw Open. 2019;2(3):e190968. doi: 10.1001/jamanetworkopen.2019.0968
For more information, contact Nicole Brobston | nbrobston@pharmacy.arizona.edu or (520) 626-5883