Using decision tree models and comprehensive statewide data to predict opioid overdoses following prison release.

PURPOSE: Identifying predictors of opioid overdose following release from prison is critical for opioid overdose prevention. METHODS: We leveraged an individually linked, state-wide database from 2015-2020 to predict the risk of opioid overdose within 90 days of release from Massachusetts state prisons. We developed two decision tree modeling schemes: a model fit on all individuals with a single weight for those that experienced an opioid overdose and models stratified by race/ethnicity. We compared the performance of each model using several performance measures and identified factors that were most predictive of opioid overdose within racial/ethnic groups and across models. RESULTS: We found that out of 44,246 prison releases in Massachusetts between 2015-2020, 2237 (5.1%) resulted in opioid overdose in the 90 days following release. The performance of the two predictive models varied. The single weight model had high sensitivity (79%) and low specificity (56%) for predicting opioid overdose and was more sensitive for White non-Hispanic individuals (sensitivity = 84%) than for racial/ethnic minority individuals. CONCLUSIONS: Stratified models had better balanced performance metrics for both White non-Hispanic and racial/ethnic minority groups and identified different predictors of overdose between racial/ethnic groups. Across racial/ethnic groups and models, involuntary commitment (involuntary treatment for alcohol/substance use disorder) was an important predictor of opioid overdose.

The MI-PHOTOS Project: Understanding the Health and Wellbeing of Rural Historically Marginalized Mothers Through Photovoice.

Despite the persistent health inequities faced by rural women in the United States, few researchers have partnered with women in rural communities to co-create sustainable change. To fill this gap, Mothers Improving Pregnancy and Postpartum Health Outcomes Through stOry Sharing (MI-PHOTOS) employed a community-based participatory research (CBPR) approach by partnering with mothers, community leaders, and community-based organizations in Robeson County, North Carolina, a rural, racially diverse county. The project's aims were (a) to promote maternal health by listening to mothers' stories of having and raising children in their community and (b) to develop a shared understanding of these mothers' strengths and challenges. MI-PHOTOS utilized photovoice, an exploratory and qualitative CBPR methodology. Grounded theory guided data analysis. During photovoice discussions, conversation focused on maternal experiences and evoked strengths, facilitators, and barriers impacting maternal health. Themes focused on (a) MI-PHOTOS serving as a social support group for the community and family stressors that mothers faced and (b) the necessity of professional support programs. Three overarching findings emerged during this process: (a) MI-PHOTOS as an informal support group, (b) mental health stigmatization, and (c) the need to bridge home visiting programs with peer and confidential therapeutic services. Future work should incorporate mothers' and communities' strengths into program development by drawing on existing home visiting programs, identifying opportunities for peer-support, and creating referral networks for individual, confidential therapeutic services. Through continued community partnership, we can generate fuller understandings of mothers' experiences of having and raising children and ultimately promote health equity among rural mothers.