Literature Collection

BACKGROUND: Integrating advanced machine-learning (ML) algorithms into clinical practice is challenging and requires interdisciplinary collaboration to develop transparent, interpretable, and ethically sound clinical decision support (CDS) tools. We aimed to design a ML-driven CDS tool to predict opioid overdose risk and gather feedback for its integration into the University of Florida Health (UFHealth) electronic health record (EHR) system. METHODS: We used user-centered design methods to integrate the ML algorithm into the EHR system. The backend and UI design sub-teams collaborated closely, both informed by user feedback sessions. We conducted seven user feedback sessions with five UF Health primary care physicians (PCPs) to explore aspects of CDS tools, including workflow, risk display, and risk mitigation strategies. After customizing the tool based on PCPs' feedback, we held two rounds of one-on-one usability testing sessions with 8 additional PCPs to gather feedback on prototype alerts. These sessions informed iterative UI design and backend processes, including alert frequency and reappearance circumstances. RESULTS: The backend process development identified needs and requirements from our team, information technology, UFHealth, and PCPs. Thirteen PCPs (male = 62%, White = 85%) participated across 7 user feedback sessions and 8 usability testing sessions. During the user feedback sessions, PCPs (n = 5) identified flaws such as the term "high risk" of overdose potentially leading to unintended consequences (e.g., immediate addiction services referrals), offered suggestions, and expressed trust in the tool. In the first usability testing session, PCPs (n = 4) emphasized the need for natural risk presentation (e.g., 1 in 200) and suggested displaying the alert multiple times yearly for at-risk patients. Another 4 PCPs in the second usability testing session valued the UFHealth-specific alert for managing new or unfamiliar patients, expressed concerns about PCPs' workload when prescribing to high-risk patients, and recommended incorporating the details page into training sessions to enhance usability. CONCLUSIONS: The final backend process for our CDS alert aligns with PCP needs and UFHealth standards. Integrating feedback from PCPs in the early development phase of our ML-driven CDS tool helped identify barriers and facilitators in the CDS integration process. This collaborative approach yielded a refined prototype aimed at minimizing unintended consequences and enhancing usability.

The opioid epidemic was declared a national public health emergency in 2017. In Georgia, standing orders for the opioid antagonist, naloxone, have been implemented to reduce mortality from opioid overdoses. Service industry workers in the Atlanta, Georgia, inner-city community of Little Five Points (L5P) have access to naloxone, potentially expanding overdose rescue efforts in the community setting. To explore the issues facing L5P, our research brings together qualitative descriptive inquiry, ethnography, community-based research, a community advisory board, and a local artist to maximize community dissemination of research findings through a graphic novel that describes encountering an opioid overdose. This format was chosen due to the ethical responsibility to disseminate in participants' language and for its potential to empower and educate readers. This article describes the process of working on this study with the community and a local artist to create sample pages that will be tested for clarity of the message in a later phase. Working with an artist has revealed that while dissemination and implementation for collaboration begin before findings are ready, cross-collaboration with the artist requires early engagement, substantial funding, artist education in appropriate content, and member checking to establish community acceptability altering illustrations that reinforce negative stereotypes. By sharing the experiences of actions taken during an opioid overdose in L5P through a graphic novel, we can validate service industry workers' experiences, acknowledge their efforts to contribute to harm reduction, and provide much-needed closure to those who encounter opioid overdoses in the community.

BACKGROUND: Drug overdose deaths involving stimulants, including cocaine and psychostimulants with abuse potential (e.g., methamphetamine), have been increasing, partly because of co-involvement with opioids. Stimulant-involved overdose deaths have disproportionately increased among non-Hispanic Black (Black) and non-Hispanic American Indian/Alaskan Native (AI/AN) persons; however, the role of opioids in exacerbating disproportionate stimulant-involved death rates is unclear. METHODS: Analysis of National Vital Statistics System multiple cause-of-death mortality files examined age-adjusted cocaine- and psychostimulant-involved death rates. Analyses of death rates stratified by racial and ethnic group and opioid co-involvement included: 1) Joinpoint regression of 2004-2019 trends, 2) changes in rates from 2018 to 2019, and 3) demographic and geographic characteristics of 2019 deaths. RESULTS: From 2004 to 2019, cocaine and psychostimulant-involved death rates were higher for Black and AI/AN persons, respectively. Among all groups, increases in cocaine-involved overdose rates were largely driven by opioid co-involvement, particularly after 2013. From 2004 to 2019, rates for psychostimulant-involved deaths increased with and without opioid co-involvement. Rates for overdoses co-involving cocaine and synthetic opioids increased from 2018 to 2019 for Hispanic, non-Hispanic White (White), and Black persons. Psychostimulant-involved overdose rates with and without synthetic opioid co-involvement increased among Hispanic, White, and Black persons. In 2019, Black and AI/AN persons continued to experience higher cocaine- and psychostimulant-involved death rates, respectively. CONCLUSIONS: Stimulant-involved deaths continue to increase, and the role of opioids in driving these deaths varies by race and ethnicity. Ensuring equitable access to proven prevention and treatment interventions and incorporating social determinants of health into future research around effective pharmacotherapies may help reduce stimulant-involved overdose deaths.