A Survey to Assess the Need for a National Registry to Track Physician Suicide.

Physician suicide is a growing public health crisis that affects the medical community and patients. Literature on physician suicide has been published since 1903. However, the epidemiology of physician suicide including incidence is unclear due to a lack of accurate data. Lack of reliable data can lead to barriers in developing effective physician suicide prevention programs and creating policies to address the issue. Data are often collected from multiple data sources that each have limitations resulting in crude estimates of incidence and persistent barriers to surveillance. The aim of this study was to survey the medical community to determine the perceived usefulness of a physician suicide registry, with an accompanying data warehouse, to collect and store information about suicides reported from the community. Physicians at all stages of their training and careers would be key stakeholders contributing information to the registry and therefore their perception of such a tool to track physician suicides is important. Results show that 70.0% of respondents expressed that they somewhat to strongly agree with the approach; and 74.2% agreed with a statement that more research is needed on physician suicide. The proposed registry to better track physician suicide is a possible solution to better address physician suicide that has garnered initial support from the medical community as reflected by the survey results.

Predictability of buprenorphine-naloxone treatment retention: A multi-site analysis combining electronic health records and machine learning.

BACKGROUND AND AIMS: Opioid use disorder (OUD) and opioid dependence lead to significant morbidity and mortality, yet treatment retention, crucial for the effectiveness of medications like buprenorphine-naloxone, remains unpredictable. Our objective was to determine the predictability of 6-month retention in buprenorphine-naloxone treatment using electronic health record (EHR) data from diverse clinical settings and to identify key predictors. DESIGN: This retrospective observational study developed and validated machine learning-based clinical risk prediction models using EHR data. SETTING AND CASES: Data were sourced from Stanford University's healthcare system and Holmusk's NeuroBlu database, reflecting a wide range of healthcare settings. The study analyzed 1800 Stanford and 7957 NeuroBlu treatment encounters from 2008 to 2023 and from 2003 to 2023, respectively. MEASUREMENTS: Predict continuous prescription of buprenorphine-naloxone for at least 6 months, without a gap of more than 30 days. The performance of machine learning prediction models was assessed by area under receiver operating characteristic (ROC-AUC) analysis as well as precision, recall and calibration. To further validate our approach's clinical applicability, we conducted two secondary analyses: a time-to-event analysis on a single site to estimate the duration of buprenorphine-naloxone treatment continuity evaluated by the C-index and a comparative evaluation against predictions made by three human clinical experts. FINDINGS: Attrition rates at 6 months were 58% (NeuroBlu) and 61% (Stanford). Prediction models trained and internally validated on NeuroBlu data achieved ROC-AUCs up to 75.8 (95% confidence interval [CI] = 73.6-78.0). Addiction medicine specialists' predictions show a ROC-AUC of 67.8 (95% CI = 50.4-85.2). Time-to-event analysis on Stanford data indicated a median treatment retention time of 65 days, with random survival forest model achieving an average C-index of 65.9. The top predictor of treatment retention identified included the diagnosis of opioid dependence. CONCLUSIONS: US patients with opioid use disorder or opioid dependence treated with buprenorphine-naloxone prescriptions appear to have a high (∼60%) treatment attrition by 6 months. Machine learning models trained on diverse electronic health record datasets appear to be able to predict treatment continuity with accuracy comparable to that of clinical experts.

Predicting premature discontinuation of medication for opioid use disorder from electronic medical records.

Medications such as buprenorphine-naloxone are among the most effective treatments for opioid use disorder, but limited retention in treatment limits long-term outcomes. In this study, we assess the feasibility of a machine learning model to predict retention vs. attrition in medication for opioid use disorder (MOUD) treatment using electronic medical record data including concepts extracted from clinical notes. A logistic regression classifier was trained on 374 MOUD treatments with 68% resulting in potential attrition. On a held-out test set of 157 events, the full model achieved an area under the receiver operating characteristic curve (AUROC) of 0.77 (95% CI: 0.64-0.90) and AUROC of 0.74 (95% CI: 0.62-0.87) with a limited model using only structured EMR data. Risk prediction for opioid MOUD retention vs. attrition is feasible given electronic medical record data, even without necessarily incorporating concepts extracted from clinical notes.

Women Physicians in Transition Learning to Navigate the Pipeline from Early to Mid-Career: Protocol for a Qualitative Study.

BACKGROUND: Women physicians face unique obstacles while progressing through their careers, navigating career advancement and seeking balance between professional and personal responsibilities. Systemic changes, along with individual and institutional changes, are needed to overcome obstacles perpetuating physician gender inequities. Developing a deeper understanding of women physicians' experiences during important transition points could reveal both barriers and opportunities for recruitment, retention, and promotion, and inform best practices developed based on these experiences. OBJECTIVE: The aim is to learn from the experiences and perspectives of women physicians as they transition from early to mid-career, then develop best practices that can serve to support women physicians as they advance through their careers. METHODS: Semistructured interviews were conducted with women physicians in the United States in 2020 and 2021. Eligibility criteria included self-identification as a woman who is in the process of transitioning or who recently transitioned from early to mid-career stage. Purposeful sampling facilitated identification of participants who represented diversity in career pathway, practice setting, specialty, and race/ethnicity. Each participant was offered compensation for their participation. Interviews were audio-recorded and professionally transcribed. Interview questions were open-ended, exploring participants' perceptions of this transition. Qualitative thematic analysis will be performed. We will use an open coding and grounded theory approach on interview transcripts. RESULTS: The Ethics Review Committee of the Faculty of Health, Medicine, and Life Sciences at Maastricht University approved the study; Stanford University expedited review approved the study; and the University of California, San Diego certified the study as exempt from review. Twelve in-depth interviews of 50-100 minutes in duration were completed. Preliminary analyses indicate one key theme is a tension resulting from finite time divided between demands from a physician career and demands from family needs. In turn, this results in constant boundary control between these life domains that are inextricable and seemingly competing against each other within a finite space; family needs impinge on planned career goals, if the boundary between them is not carefully managed. To remedy this, women sought resources to help them redistribute home responsibilities, freeing themselves to have more time, especially for children. Women similarly sought resources to help with career advancement, although not with regard to time directly, but to first address foundational knowledge gaps about career milestones and how to achieve them. CONCLUSIONS: Preliminary results provide initial insights about how women identify or activate a career shift and how they marshaled resources and support to navigate barriers they faced. Further analyses are continuing as of March 2022 and are expected to be completed by June 2022. The dissemination plan includes peer-reviewed open-access journal publication of the results and presentation at the annual meeting of the American Medical Association's Women Physicians Section.