Search for: All records

The soaring drug overdose crisis in the United States has claimed more than half a million lives in the past decade and remains a major public health threat. The ability to predict drug overdose deaths at the county level can help local communities develop action plans in response to emerging changes. Applying off-the-shelf machine learning algorithms for prediction can be challenging due to the heterogeneous risk profiles of the counties and suppressed data in common publicly available data sources. To fill these gaps, we develop a cluster-aware supervised learning (CASL) framework to enhance the prediction of county-level drug overdose deaths. This CASL model simultaneously clusters counties into groups based on geographical and socioeconomic characteristics and minimizes the loss function that accounts for suppressed values and cluster-specific regularization. Our computational study uses real-world data from 2010 to 2021, focusing on the ten states most severely impacted by the drug overdose crisis. The results demonstrate that our proposed CASL framework significantly outperforms state-of-the-art methods by achieving a superior balance in prediction accuracy for both unsuppressed and suppressed observations. The proposed model also identifies different clusters of counties, capturing heterogeneous patterns of overdose mortality among counties of diverse characteristics. 

The ongoing opioid epidemic has been met with the inadequate use of data-informed approaches to respond to the crisis. Although data relevant to opioid and substance use do exist and have been utilized for research in the literature and practice, they have not been prepared for cross-sector coordination and for providing practical intelligence to inform policy planning directly. In this article, we share our views on how data can better serve the purposes of informing policy and planning to maximize population health and safety benefits. Based on our experience in advising state policymakers on developing settlement allocation strategies based on empirical data, we discuss several issues in the data, including coverage, specificity in drug types, time relevance, geographic units, and access, which may hinder data-informed policymaking. Following these discussions, we envision a coordinated data and policy framework as an ideal case to ensure access to meaningful and timely data and harness the full potential of the data to inform policy to combat the continuing epidemic.