Reimagining Merit and Representation: Promoting Equity and Reducing Bias in GME Through Holistic Review.

OBJECTIVE: This study aims to evaluate the capacity of a holistic review process in comparison with non-holistic approaches to facilitate mission-driven recruitment in residency interview screening and selection, with particular attention to the promotion of race equity for applicants underrepresented in medicine (URM). METHODS: Five hundred forty-seven applicants to a psychiatry residency program from US allopathic medical schools were evaluated for interview selection via three distinct screening rubrics-one holistic approach (Holistic Review; HR) and two non-holistic processes: Traditional (TR) and Traditional Modified (TM). Each applicant was assigned a composite score corresponding to each rubric, and the top 100 applicants in each rubric were identified as selected for interview. Odds ratios (OR) of selection for interview according to URM status and secondary outcomes, including clinical performance and lived experience, were measured by analysis of group composition via univariate logistic regression. RESULTS: Relative to Traditional, Holistic Review significantly increased the odds of URM applicant selection for interview (TR-OR: 0.35 vs HR-OR: 0.84, p < 0.01). Assigning value to lived experience and de-emphasizing USMLE STEP1 scores contributed to the significant changes in odds ratio of interview selection for URM applicants. CONCLUSIONS: Traditional interview selection methods systematically exclude URM applicants from consideration without due attention to applicant strengths or potential contribution to clinical care. Conversely, holistic screening represents a structural intervention capable of critically examining measures of merit, reducing bias, and increasing URM representation in residency recruitment, screening, and selection.

High-Risk Phenotypes of Early Psychiatric Readmission in Bipolar Disorder With Comorbid Medical Illness.

BACKGROUND: Individuals with co-existing serious mental illness and non-psychiatric medical illness are at high risk of acute care utilization. Mining of electronic health record data can help identify and categorize predictors of psychiatric hospital readmission in this population. OBJECTIVE: This study aimed to identify modifiable predictors of psychiatric readmission among individuals with comorbid bipolar disorder and medical illness. This goal was accomplished by applying objective variable selection via machine learning techniques. METHOD: This was a retrospective analysis of electronic health record data derived from 77,296 episodes of care from 2006 to 2016 within the University of California Health Care System. Data included 1,250 episodes of care involving patients with bipolar disorder and serious comorbid medical illnesses (defined by transfer between medicine and psychiatry services or concomitant primary medical and psychiatric admission diagnoses). Machine learning (classification trees) was used to identify potential predictors of 30-day psychiatric readmission across hospital encounters. Predictors included demographics, medical and psychiatric diagnoses, medication regimen, and disposition. The algorithm was internally validated using 10-fold cross-validation. RESULTS: The model predicted 30-day readmission with high accuracy (98% unbalanced model, 88% balanced model). Modifiable predictors of readmission were length of stay, transfers between medical and psychiatric services, discharge disposition to home, and all-cause acute health service utilization in the year before the index hospitalization. CONCLUSION: Among bipolar disorder patients with comorbid medical conditions, characteristics of the index hospitalization (e.g., duration, transfer, and disposition) emerged as more predictive than static properties of the patient (e.g., sociodemographic factors and psychiatric comorbidity burden). Findings identified phenotypes of patients at high risk for rehospitalization and suggest potential ways of modifying the risk of early readmission.

Predicting suicidal behavior and self-harm after general hospitalization of adults with serious mental illness.

Individuals with psychiatric disorders are vulnerable to adverse mental health outcomes following physical illness. This longitudinal cohort study defined risk profiles for readmission for suicidal behavior and self-harm after general hospitalization of adults with serious mental illness. Structured electronic health record data were analyzed from 15,644 general non-psychiatric index hospitalizations of individuals with depression, bipolar, and psychotic disorders admitted to an urban health system in the southwestern United States between 2006 and 2017. Using data from one-year prior to and including index hospitalization, supervised machine learning was implemented to predict risk of readmission for suicide attempt and self-harm in the following year. The Classification and Regression Tree algorithm produced a classification prediction with an area under the receiver operating curve (AUC) of 0.86 (95% confidence interval (CI) 0.74-0.97). Incidence of suicide-related behavior was highest after general non-psychiatric hospitalizations of individuals with prior suicide attempt or self-harm (18%; 69 cases/389 hospitalizations) and lowest after hospitalizations associated with very high medical morbidity burden (0 cases/3090 hospitalizations). Predictor combinations, rather than single risk factors, explained the majority of risk, including concomitant alcohol use disorder with moderate medical morbidity, and age ≤55-years-old with low medical morbidity. Findings suggest that applying an efficient and highly interpretable machine learning algorithm to electronic health record data may inform general hospital clinical decision support, resource allocation, and preventative interventions for medically ill adults with serious mental illness.

Hierarchical Models for Multiple, Rare Outcomes Using Massive Observational Healthcare Databases.

Clinical trials often lack power to identify rare adverse drug events (ADEs) and therefore cannot address the threat rare ADEs pose, motivating the need for new ADE detection techniques. Emerging national patient claims and electronic health record databases have inspired post-approval early detection methods like the Bayesian self-controlled case series (BSCCS) regression model. Existing BSCCS models do not account for multiple outcomes, where pathology may be shared across different ADEs. We integrate a pathology hierarchy into the BSCCS model by developing a novel informative hierarchical prior linking outcome-specific effects. Considering shared pathology drastically increases the dimensionality of the already massive models in this field. We develop an efficient method for coping with the dimensionality expansion by reducing the hierarchical model to a form amenable to existing tools. Through a synthetic study we demonstrate decreased bias in risk estimates for drugs when using conditions with different true risk and unequal prevalence. We also examine observational data from the MarketScan Lab Results dataset, exposing the bias that results from aggregating outcomes, as previously employed to estimate risk trends of warfarin and dabigatran for intracranial hemorrhage and gastrointestinal bleeding. We further investigate the limits of our approach by using extremely rare conditions. This research demonstrates that analyzing multiple outcomes simultaneously is feasible at scale and beneficial.