Mining comorbidities of opioid use disorder from FDA adverse event reporting system and patient electronic health records

• DOI: 10.1186/s12911-022-01869-8
• Publication Date: 2022-06-16T15:51:46Z
• Authors: Yiheng Pan; Rong Xu
• Keywords: United States Food and Drug Administration; Research; Computer applications to medicine. Medical informatics; R858-859.7; Comorbidity; Opioid-Related Disorders; United States; 3. Good health; 03 medical and health sciences; 0302 clinical medicine; Diabetes Mellitus, Type 2; Hypothyroidism; Statistical analysis; Opioid use disorder; Electronic Health Records; Humans; Biomedical informatics; Network analysis; Data mining

Abstract Background Opioid use disorder (OUD) has become an urgent health problem. People with OUD often experience comorbid medical conditions. Systematical approaches to identifying co-occurring conditions of can facilitate a deeper understanding mechanisms and drug discovery. This study presents integrated approach combining data mining, network construction ranking, hypothesis-driven case–control studies using patient electronic records (EHRs). Methods First, we mined comorbidities from the US Food Drug Administration Adverse Event Reporting System (FAERS) 12 million unique case reports frequent pattern-growth algorithm. The performance comorbidity mining was measured by precision recall manually curated known comorbidities. We then constructed disease association rules further prioritized Last, novel were independently tested EHRs 75 patients. Results achieves 38.7% 78.2 Based on rules, global DCN 1916 nodes 32,175 edges. network-based ranking result shows that 43 55 in first decile 78.2%. Hypothyroidism type 2 diabetes two top-ranked identified algorithms. EHR-based studies, showed patients had significantly increased risk for hyperthyroidism (AOR = 1.46, 95% CI 1.43–1.49, p value < 0.001), hypothyroidism 1.45, 1.42–1.48, 2-diabetes 1.28, 1.26–1.29, compared individuals without OUD. Conclusion Our developed validating 87 (12 discovery validation), which offer new opportunities mechanism understanding, discovery, multi-component service delivery among