Great Lakes Node of the Drug Abuse Clinical Trials Network

PROJECT SUMMARY Individuals with substance use disorders are disproportionately experiencing homelessness, poverty,and chronic medical conditions (diabetes and hypertension), which are emerging risk factors for contractingSARS-CoV-2 (official name for the virus that causes COVID-19). Different types of substance use have beenassociated with development of respiratory infections and progression to severe respiratory failure, also knownas Acute Respiratory Distress Syndrome (ARDS). However, complex syndromes like ARDS and behavioralconditions like substance misuse are difficult to identify from the electronic health record. Clinical notes andradiology reports provide a rich source of information that may be used to identify cases of substance misuseand ARDS. This information is routinely recorded during hospital care, and automated, data-driven solutionswith natural language processing (NLP) can extract semantics and important risk factors from the unstructureddata of clinical notes. The computational methods of NLP derive meaning from clinical notes, from whichmachine learning can predict risk factors for patients leaving AMA or progressing to respiratory failure. Ourteam developed tools with >80% sensitivity/specificity to identify individual types of substance misuse usingNLP with machine learning (ML). Our single-center models delineated risk factors embedded in the notes (e.g.,mental health conditions, socioeconomic indicators). Further, we have developed and externally validated amachine learning tool to identify cases of ARDS with high accuracy for early treatment. We aim to expand thiswork by pooling data across health systems and build a generalizable and comprehensive classifier thatcaptures multiple types of substance misuse for use in risk stratification and prognostication during the COVIDpandemic. We hypothesize that a single-model NLP substance misuse classifier will provide a standardized,interoperable, and accurate approach for universal analysis of hospitalized patients, and that such informationcan be used to identify those at risk for disrupted care and those at risk for respiratory failure. We aim to trainand test our substance misuse classifiers at Rush in a retrospective dataset of over 60,000 hospitalizationsthat have been manually screened with the universal screen, AUDIT, and DAST. This AdministrativeSupplement will allow us to examine the correlations between substances of misuse and risk for COVID-19 aswell as development of Acute Respiratory Distress Syndrome (ARDS) in the context of these phenomena.