JMIR Public Health and Surveillance 2022;8(12):e38158. [doi: 10.2196/38158]
Thompson, Hale M. | Sharma, Brihat | Smith, Dale | Bhalla, Sameer | Erondu, Iluoma | Hazra, Aniruddha | Ilyas, Yousaf | Pachwicewicz, Paul | Sheth, Neeral K. | Chhabra, Neeraj | Karnik, Niranjan S. | Afshar, Majid
This is the primary outcomes paper for CTN-0111. The COVID-19 pandemic has exacerbated health inequities in the United States. People with unhealthy opioid use (UOU) may face disproportionate challenges with COVID-19 precautions, and the pandemic has disrupted access to opioids and UOU treatments. Unhealthy opioid use impairs the immunological, cardiovascular, pulmonary, renal, and neurological systems and may increase severity of outcomes for COVID-19. This study, NIDA-CTN-0111 (COVID-19 and Substance Misuse Case Identification Using Data Science: A Retrospective Cohort Study), aimed to apply machine learning techniques in order to explore clinical presentations of hospitalized patients with UOU and COVID-19 and to test the association between UOU and COVID-19 disease severity.
This retrospective, cross-sectional cohort study was conducted based on data from 4,110 electronic health record patient encounters at an academic health center in Chicago between January 1, 2020, and December 31, 2020. Inclusion criteria were unplanned admissions for patients =18 years of age; encounters were counted as COVID-19-positive if there was a positive test for COVID-19 or two COVID-19 ICD-10 codes recorded in the encounter. Using a predefined cutoff with optimal sensitivity and specificity to identify UOU, we ran a machine learning UOU classifier on the data for patients with COVID-19 to estimate the subcohort of patients with UOU. Topic modeling was used to explore and compare the clinical presentations documented for two subgroups: encounters with UOU and COVID-19 and those with no-UOU and COVID-19. Mixed effects logistic regression accounted for multiple encounters for some patients and tested the association between UOU and COVID-19 outcome severity. Severity was measured with three utilization metrics: low - unplanned admission, medium - unplanned admission and receiving mechanical ventilation, and high - unplanned admission with in-hospital death. All models controlled for age, sex, race/ethnicity, insurance status, and body mass index (BMI).
Topic modeling yielded ten topics per subgroup and highlighted unique comorbidities associated with UOU and COVID-19 (e.g., HIV) and no-UOU and COVID-19 (e.g., diabetes). In regression analysis, each incremental increase in the classifier's predicted probability of UOU was associated with 1.16 higher odds of COVID-19 outcome severity (odds ratio 1.16, 95% CI 1.04-1.29, P=.009).
Conclusions: Among patients hospitalized with COVID-19, UOU is an independent risk factor associated with greater outcome severity, including in-hospital death. Social determinants of health and opioid-related overdose are unique comorbidities in the clinical presentation of the UOU patient subgroup. Additional research is needed on the role of COVID-19 therapeutics and inpatient management of acute COVID-19 pneumonia for patients with UOU. Further research is needed to test associations between expanded evidence-based harm reduction strategies for UOU and vaccination rates, hospitalizations, and risks for overdose and death among people with UOU and COVID-19. Machine learning techniques may offer more exhaustive means for cohort discovery and a novel mixed methods approach to population health.
Keywords: CTN primary outcomes | COVID-19 | Opioid use disorder | Health inequities | Machine learning | JMIR Public Health and Surveillance (journal)
Document No: 1541 ; PMID: 36265163 ; PMCID: PMC9746674
Submitted by: Jack Blaine, NIDA (11/11/2022)
