{"id":4570,"date":"2021-08-27T11:30:34","date_gmt":"2021-08-27T15:30:34","guid":{"rendered":"https:\/\/www.bu.edu\/aodhealth\/?p=4570"},"modified":"2021-08-27T11:30:34","modified_gmt":"2021-08-27T15:30:34","slug":"machine-learning-algorithm-predicts-future-mortality-following-non-fatal-opioid-overdose","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/aodhealth\/2021\/08\/27\/machine-learning-algorithm-predicts-future-mortality-following-non-fatal-opioid-overdose\/","title":{"rendered":"Machine-learning Algorithm Predicts Future Mortality Following Non-fatal Opioid Overdose"},"content":{"rendered":"<p>This retrospective cohort study used 2014\u20132016 Pennsylvania Medicaid data to develop a predictive model for all-cause mortality following non-fatal opioid overdose through applied machine learning. The algorithm used 348 predictors for 9686 individuals, including variables at the individual level (socio-demographics, health status, and health service utilization) and community level (e.g., poverty level, suicide rate) from the 180 days that preceded an index overdose. The main outcome was all-cause mortality within 180 days after the index overdose.<\/p>\n<ul>\n<li>Overall, 346 (3.6%) individuals died within 180 days after an index overdose.<\/li>\n<li>Those in the highest-risk group (\u226598<sup>th<\/sup> percentile of risk) had a 180-day mortality rate of 20%; in the lowest-risk group (&lt;25<sup>th<\/sup> percentile), the mortality rate was 1.5%.*<\/li>\n<li>When sensitivity and specificity were balanced, the algorithm\u2019s negative and positive predictive values were 98% and 6.5%, respectively.<\/li>\n<li>Receiving medications for opioid use disorder or risk-mitigation interventions (naloxone, urine drug testing, substance use disorder counseling) after overdose were associated with lower mortality.<\/li>\n<li>Several community-level variables, such as county-level poverty or suicide rates, were important predictors of mortality.<\/li>\n<\/ul>\n<p>* Individuals were stratified into 6 subgroups \u201cat similar risk according to the risk scores (i.e., the individual\u2019s estimated probability of death) generated by the validated machine learning algorithm.\u201d<\/p>\n<p><em>Comments<\/em>: Having a score at the time of non-fatal opioid overdose to estimate future mortality risk could be useful for clinicians, health insurers, or government agencies. However, this algorithm used all-cause mortality as an outcome, which may have placed more emphasis on age and disability as predictors than if overdose mortality was used as the outcome. Even without a risk score, this study reinforces the importance of prescribing naloxone as well as identifying and treating opioid use disorder at the time of an overdose.<\/p>\n<p>Aaron D. Fox, MD<\/p>\n<p><em>Reference<\/em>: Guo J, Lo-Ciganic WH, Yang Q, et al. <a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/33481168\/\">Predicting mortality risk after a hospital or emergency department visit for nonfatal opioid overdose<\/a>. <em>J Gen Intern Med<\/em>. 2021;36(4):908\u2013915.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This retrospective cohort study used 2014\u20132016 Pennsylvania Medicaid data to develop a predictive model for all-cause mortality following non-fatal opioid overdose through applied machine learning. The algorithm used 348 predictors for 9686 individuals, including variables at the individual level (socio-demographics, health status, and health service utilization) and community level (e.g., poverty level, suicide rate) from [&hellip;]<\/p>\n","protected":false},"author":4441,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[134],"tags":[77],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/posts\/4570"}],"collection":[{"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/users\/4441"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/comments?post=4570"}],"version-history":[{"count":1,"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/posts\/4570\/revisions"}],"predecessor-version":[{"id":4571,"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/posts\/4570\/revisions\/4571"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/media?parent=4570"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/categories?post=4570"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/aodhealth\/wp-json\/wp\/v2\/tags?post=4570"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}