{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T14:24:12Z","timestamp":1787408652543,"version":"build-2736575974"},"reference-count":28,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T00:00:00Z","timestamp":1785628800000},"content-version":"vor","delay-in-days":1,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ascpt.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clinical Translational Sci"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Identification of modifiable risk factors for prescription opioid use disorder (OUD)\u2010related emergency department (ED) visits (ICD\u201010\u2009F11.xx) is a clinical priority; however, most published models remain cross\u2010sectional and lack pharmacogenomic (PGx) enrichment or dual\u2010method feature confirmation. Using Virginia All\u2010Payer Claims Database (APCD) data (2016\u20132019; 6,929,576 patients), we analyzed prescription OUD\u2010related ED visits ( =\u20091,505,138 cases; 5:1 matched controls) across seven age bands. CatBoost, XGBoost, and XGBoost\u2010RF ensembles were trained within four utilization\u2010density strata (25\u2010split MCCV; 2016\u20132018 training; 2019 holdout) using PGx burden and pre\u2010index temporal dynamics. Risk features were identified via a Consensus Filter (SHAP \u2229 FFA) requiring SHAP values \u2265\u200975th percentile and FFA rule support \u2265\u20090.05. Dynamic Time Warping (DTW) characterized pre\u2010index trajectories. On the 2019 low\u2010density holdout, PR\u2010AUC lift over prevalence ranged from 2.3\u00d7 to 3.4\u00d7; the 25\u201344 band achieved an AUROC of 0.800 and 3.3\u00d7 lift ( =\u20094942 holdout cases). Top Consensus\u2010Risk features included gabapentin, long\u2010term opioid use (Z79.891), and pgx_num_drugs. DTW yielded three utilization archetypes in the 25\u201344 band ( =\u200959,813), with a mean pre\u2010index time\u2010to\u2010target of 6.8\u2009months. While SHAP\/FFA specify\n                    <jats:italic>how<\/jats:italic>\n                    to intervene (medication and care targets), DTW specifies\n                    <jats:italic>when<\/jats:italic>\n                    to act (surveillance window). These findings provide an observational risk\u2010attribution framework for Consensus\u2010Risk priority features and pre\u2010index trajectory windows in claims\u2010based prescription OUD\u2010related ED care rather than identified causal treatment effects. We maintain the association\u2010versus\u2010causation distinction to support safer clinical use and preserve a path to prospective causal validation.\n                  <\/jats:p>","DOI":"10.1111\/cts.70690","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T04:20:38Z","timestamp":1785730838000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal Drivers of Opioid\u2010Related\n                    <scp>ED<\/scp>\n                    Visits: An Ensemble Machine Learning Study With Consensus\u2010Based Feature Attribution"],"prefix":"10.1111","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8622-0597","authenticated-orcid":false,"given":"R. Jerome","family":"Dixon","sequence":"first","affiliation":[{"name":"Department of Pharmacotherapy and Outcomes Science, School of Pharmacy Virginia Commonwealth University  Richmond Virginia USA"},{"name":"Ph.D. Program in Integrative Life Sciences, School of Life Sciences and Sustainability Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6046-7540","authenticated-orcid":false,"given":"Elvin T.","family":"Price","sequence":"additional","affiliation":[{"name":"Department of Pharmacotherapy and Outcomes Science, School of Pharmacy Virginia Commonwealth University  Richmond Virginia USA"},{"name":"ConvergenceLabs@VCU\u2014Health Outcomes Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,2]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.mm7006a4"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.mm6709e1"},{"key":"e_1_2_13_4_1","unstructured":"Virginia Department of Health Drug overdose data: Fatal drug overdose trends 2022accessed at March 1 2025 https:\/\/www.vdh.virginia.gov\/drug\u2010overdose\u2010data\/."},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002922"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107573"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.0968"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0235981"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.2149"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_13_11_1","first-page":"6638","article-title":"CatBoost: Unbiased boosting with categorical features","volume":"31","author":"Prokhorenkova L.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169\u20107439(00)00122\u20102"},{"key":"e_1_2_13_14_1","first-page":"4765","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg S. M.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_13_15_1","article-title":"On Formal Feature Attribution and Its Approximation","author":"Ignatiev A.","year":"2023","journal-title":"arXiv:2307.03380"},{"issue":"16","key":"e_1_2_13_16_1","first-page":"359","article-title":"Using Dynamic Time Warping to Find Patterns in Time Series","volume":"10","author":"Berndt D. J.","year":"1994","journal-title":"KDD Workshop on Knowledge Discovery in Databases"},{"key":"e_1_2_13_17_1","unstructured":"W.Meert K.Hendrickx andT.van Craenendonck dtaidistance v2.0.0 2020accessed at June 2 2026 https:\/\/doi.org\/10.5281\/zenodo.3981067."},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1200\/JOP.19.00149"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.7326\/M14\u20100697"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001381"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/ehjcvp\/pvac005"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"e_1_2_13_23_1","volume-title":"Causal Inference: What If","author":"Hern\u00e1n M. A.","year":"2020"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256\u2010020\u20100197\u2010y"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.rr7103a1"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev\u2010pharmtox\u2010010814\u2010124835"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/clpt.2010.279"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2014.18514"},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.3153"}],"container-title":["Clinical and Translational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cts.70690","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cts.70690","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cts.70690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:38:42Z","timestamp":1787405922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/10.1111\/cts.70690"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":28,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1111\/cts.70690"],"URL":"https:\/\/doi.org\/10.1111\/cts.70690","archive":["Portico"],"relation":{},"ISSN":["1752-8054","1752-8062"],"issn-type":[{"value":"1752-8054","type":"print"},{"value":"1752-8062","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"2026-04-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70690"}}