Sex differences in factors predicting post‐treatment opioid use

Abstract

Background and aims Several reports have documented risk factors for opioid use following treatment discharge, yet few have assessed sex differences, and no study has assessed risk using contemporary machine learning approaches. The goal of the present paper was to inform treatments for opioid use disorder (OUD) by exploring individual factors for each sex that are most strongly associated with opioid use following treatment. Design Secondary analysis of Global Appraisal of Individual Needs (GAIN) database with follow‐ups at 3, 6 and 12 months post‐OUD treatment discharge, exploring demographic, psychological and behavioral variables that predict post‐treatment opioid use. Setting One hundred and thity‐seven treatment sites across the United States. Participants Adolescents (26.9%), young adults (40.8%) and adults (32.3%) in treatment for OUD. The sample (n = 1,126) was 54.9% male, 66.1% white, 20% Hispanic, 9.8% multi‐race/ethnicity, 2.8% African American and 1.3% other. Measurement Primary outcome was latency to opioid use over 1 year following treatment admission. Results For women, regularized Cox regression indicated that greater withdrawal symptoms [hazard ratio (HR) = 1.31], younger age (HR = 0.88), prior substance use disorder (SUD) treatment (HR = 1.11) and treatment resistance (HR = 1.11) presented the largest hazard for post‐treatment opioid use, while a random survival forest identified and ranked substance use problems [variable importance (VI) = 0.007], criminal justice involvement (VI = 0.006), younger age (VI = 0.005) and greater withdrawal symptoms (VI = 0.004) as the greatest risk factors. For men, Cox regression indicated greater conduct disorder symptoms (HR = 1.34), younger age (HR = 0.76) and multiple SUDs (HR = 1.27) were most strongly associated with post‐treatment opioid use, while a random survival forests ranked younger age (VI = 0.023), greater conduct disorder symptoms (VI = 0.010), having multiple substance use disorders (VI = 0.010) and criminal justice involvement (VI = 0.006) as the greatest risk factors. Conclusion Risk factors for relapse to opioid use following opioid use disorder treatment appear to be, for women, greater substance use problems and withdrawal symptoms and, for men, younger age and histories of conduct disorder and multiple substance use disorder.

Best Practices on Big Data Analytics to Address Sex-Specific Biases in our Understanding of the Etiology, Diagnosis and Prognosis of Diseases

“…Studies have differentiated the risk of suicide attempt and self-harm (53), metabolic syndrome (54) initiation of cannabis use (55), the risks of loneliness (64), obesity (56), musculoskeletal disorders (57) and opioid use post-treatment (58) using EHRs, as well as other datasets.…”

“…The data sources for the studies were varied, with most utilizing information from EHRs or other clinical databases. Within these studies, the majority only included structured data in their models (47, 48, 49, 50, 58, 59, 60, 61, 62) while a few incorporated both structured and unstructured data from these resources (45, 43, 44, 63). Another source of data was surveys, questionnaires, or interviews, where again the majority of studies used only structured data in their models (46, 53, 54, 51, 57), with only one study applying NLP methods and used both structured and unstructured data (64).…”

“…The majority of the included studies employed only machine learning techniques (15/22, 68.2%) to uncover gender disparities. These included traditional machine learning methods such as Support vector machine (SVM) (49, 50, 51), classification tree analysis including random forest (53, 58, 60), XGBoost (59) and C4.5 (47), regression models RIDGE (46) and logistic regression (59, 55) or other regression models, such as Multivariate adaptive regression splines (MARS) (57). Other studies used artificial neural networks, including self-organizing maps (SOM) (48, 61), and AutoCM (54).…”

“…Most of the studies explored the role of sex-specific differences in the creation of classification or prediction models for a variety of conditions including, Alzheimer’s disease (48), autism(51), cancer (59), cardiovascular disease (47, 60, 63), musculoskeletal disorders (57), substance use (44,55, 58), mental illness (43, 52, 62, 64) obesity/physical activity (41, 54) and tinnitus (46). Within these studies, nine developed separate models for males and females finding these models were better able to discriminate sex-specific determinants of the trait of interest.…”

Court-Mandated Treatment Outcomes for Prescribed Opioid Use Disorder: A Gender Based Study

“…Grella (2008) found that males referred to treatment by the criminal justice system, experienced a higher level of support from family and their communities than females. Although opioid use is almost the same for both sexes, females often present with greater psychological stressors and experience poorer quality of life complicated by their substance use (Davis et al, 2021). These sex differences increase stigma for females which manifests in the internalization of guilt and shame hindering successful treatment retention efforts (Howard, 2015).…”