Explore the vast range of titles available.

BackgroundSuicide rates have increased over the last couple of decades globally, particularly in the United States and among populations with lower economic status who present at safety-net healthcare systems. Recently, predictive models for suicide risk have shown promise; however, a model for this specific population does not exist.ObjectiveTo develop a predictive risk model of suicide and intentional self-harm (ISH) for patients presenting at the psychiatric emergency department (ED) of JPS Health Network, a safety net medical and mental healthcare system in Texas.MethodsThe study used structured and unstructured electronic medical record (EMR) data (2015–2019) and local medical examiner data (2015–2020) to create predictors and outcome variables. All psychiatric ED notes during calendar years 2018 and 2019 were reviewed using natural language processing to identify presentations for any level of self-harm and subsequent manual review of identified visits to accurately classify ED presentations for treatment of an act of intentional self-harm meeting study criteria. Data from 15 987 patients were used to develop and validate a machine learning-based predictive model that leverages rolling window methodology to predict risk repeatedly across a patient’s trajectory. Feature engineering played a prominent role in defining new predictors.FindingsThe best model (XGBoost) achieved the area under the receiver operating characteristic curve of 0.81 for 30-day predictions and demonstrated concentration of ISH and suicide attempt events in high-risk quantiles of risk (65% had events in top 0.1% quantile). The predicted risk can be translated into a propensity of events (80% at the highest predicted risk) to facilitate clinical interpretation.ConclusionsMachine learning-based models can be used with standard EMRs to identify patients presenting at the psychiatric ED with a high risk of ISH and suicide attempts within the next 30 days.Clinical implicationsIntegration of a predictive model can significantly aid clinical decision-making in safety-net psychiatric EDs.

Purpose: We describe the impact of screening on outcomes of patients diagnosed with hepatocellular carcinoma (HCC) in an urban safety-net healthcare system compared to a non-screened cohort diagnosed with HCC. Methods: Patients diagnosed with HCC at John Peter Smith Health Network were identified by querying the hospital tumor registry and allocated to the screened cohort if they had undergone any liver imaging within one year prior to HCC diagnosis, while the remainder were allocated to the non-screened cohort. Kaplan–Meier methods and log-rank tests were used to compare 3-year survival curves from an index date of HCC diagnosis. Cox proportional hazard models were used to calculate unadjusted and adjusted hazard ratios (HRs) and 95% confidence intervals (CIs). The Duffy adjustment was used to address lead-time bias. Results: A total of 158 patients were included (n = 53 screened, n = 105 non-screened). The median overall survival (OS) for the screened cohort was 19.0 months (95% CI: 9.9–NA) and that for the non-screened cohort was 5.4 months (95% CI: 3.7–8.5) [HR death (non-screened vs. screened) = 2.4, 95% CI: 1.6-3.6; log rank p < 0.0001]. The benefit of screening remained after adjusting for lead-time bias (HR 2.19, 95% CI 1.4–3.3, p = 0.0002). Conclusions: In an urban safety-net population, screening for HCC was associated with improved outcomes compared to patients diagnosed with HCC outside of a screening protocol.

As fellowships become more prevalent for nurse practitioners and physician assistants, the outcomes and quality of these programs require careful evaluation. This article describes a 1-year postgraduate program in which nurse practitioners and physician assistants rotate through key areas in behavioral health, attend didactics, and participate in a structured mentorship program. The fellowship was formally developed in 2018 and subsequently evaluated in 2020–2021 using knowledge assessment and participant satisfaction as outcome metrics. The process of fellowship development, implementation, and evaluation demonstrates a successful training path by which experienced clinicians and educators may lead and develop participants to become excellent providers. •The authors describe key elements of program development, implementation, and evaluation for a postgraduate fellowship.•Structured evaluations of fellowships for nurse practitioners and physician assistants provide valuable information to leadership and support the quality and sustainability of the program.

  Purpose Three-dimensional surgical planning (3-DSP) is becoming commonplace in the management of benign and malignant disease for oral and maxillofacial surgery practice within the last decade. Surgeons utilize a virtual “wrap” to preoperatively delineate and define maxillofacial tumor resection margins. The investigators hypothesized that the use of a wrap is a predictable method to obtain negative bony margins. Methods The investigators implemented a retrospective chart review. The sample was composed of patients over the age of 18 treated at John Peter Smith Health Network and Parkland/UT Southwestern Medical Center who obtained 3-DSP for the pathology of the head and neck, involving the bone, with a virtual wrap utilized for bony margins. The proportion of cases was calculated, descriptive statistics were reported, and binomial exact calculation was performed for confidence intervals. The primary variable analyzed was bony margin status on final histopathology, involved or uninvolved, based on the pathology report. Results The sample was composed of 39 cases, one of which was excluded due to aborting the preplanned 3-DSP. Of the 38 included cases, one had involved bony margin on final histopathology (2.6%; 95% confidence limits, 0.1%, 13.8%). There were 16 malignant cases (42%) and 22 benign cases (58%). When stratified by pathology, 1 out of the 16 malignant cases (6.3%; 95% confidence interval, 0.2%, 30%) and 0 out of the 22 benign cases (95% confidence interval, 0%, 15.4%) had an involved bony margin on final histopathology. Conclusion The results of this preliminary study suggest three-dimensional surgical planning with wrap margins is a predictable method to obtain negative bony margins in benign and malignant disease of the maxillofacial complex. Further studies will focus on compiling prospective data to solidify the accuracy and predictability of using a wrap to obtain negative bony margins.