https://www.selleckchem.com/products/Zileuton.html When training on data from a single institution, LR lags behind the rules by 3.5% (F1 score 92.2% 95.7%). Hybrid models, instead, obtain competitive results, with Classifier Confidence outperforming the rules by +0.5% (96.2%). When a larger amount of data from multiple institutions is used, LR improves by +1.5% over the rules (97.2%), whereas hybrid systems obtain +2.2% for Rule as Feature (97.7%) and +2.6% for Classifier Confidence (98.3%). Replacing LR with SVM or XGB yielded similar performance gains. We developed methods to use pre-existing handcrafted rules to inform ML algorithms. These hybrid systems obtain better performance than either rules or ML models alone, even when training data are limited. We developed methods to use pre-existing handcrafted rules to inform ML algorithms. These hybrid systems obtain better performance than either rules or ML models alone, even when training data are limited. With the artificial intelligence (AI) paradigm shift comes momentum toward the development and scale-up of novel AI interventions to aid in opioid use disorder (OUD) care, in the identification of overdose risk, and in the reversal of overdose. As OUD-specific AI interventions are relatively recent, dynamic, and may not yet be captured in the peer-reviewed literature, we conducted a review of the gray literature to identify literature pertaining to OUD-specific AI interventions being developed, implemented and evaluated. Gray literature databases, customized Google searches, and targeted websites were searched from January 2013 to October 2019. Search terms include AI, machine learning, substance use disorder (SUD), and OUD. We also requested recommendations for relevant material from experts in this area. This review yielded a total of 70 unique citations and 29 unique interventions, which can be sub-divided into five categories smartphone applications (n=12); healthcare data-related interventions (nerventions,