There are over 1 million transgender people living in the United States, and 33% report negative experiences with a healthcare provider, many of which are connected to data representation in electronic health records (EHRs). We present recommendations and common pitfalls involving sex- and gender-related data collection in EHRs. Our recommendations leverage the needs of patients, medical providers, and researchers to optimize both individual patient experiences and the efficacy and reproducibility of EHR population-based studies. We also briefly discuss adequate additions to the EHR considering name and pronoun usage. We add the disclaimer that these questions are more complex than commonly assumed. We conclude that collaborations between local transgender and gender-diverse persons and medical providers as well as open inclusion of transgender and gender-diverse individuals on terminology and standards boards is crucial to shifting the paradigm in transgender and gender-diverse health.

Training GPs with the reattribution training package appears to be extremely cost-effective.

Objectives To assess fairness and bias of a previously validated machine learning opioid misuse classifier. Materials & Methods Two experiments were conducted with the classifier’s original (n = 1000) and external validation (n = 53 974) datasets from 2 health systems. Bias was assessed via testing for differences in type II error rates across racial/ethnic subgroups (Black, Hispanic/Latinx, White, Other) using bootstrapped 95% confidence intervals. A local surrogate model was estimated to interpret the classifier’s predictions by race and averaged globally from the datasets. Subgroup analyses and post-hoc recalibrations were conducted to attempt to mitigate biased metrics. Results We identified bias in the false negative rate (FNR = 0.32) of the Black subgroup compared to the FNR (0.17) of the White subgroup. Top features included “heroin” and “substance abuse” across subgroups. Post-hoc recalibrations eliminated bias in FNR with minimal changes in other subgroup error metrics. The Black FNR subgroup had higher risk scores for readmission and mortality than the White FNR subgroup, and a higher mortality risk score than the Black true positive subgroup (P < .05). Discussion The Black FNR subgroup had the greatest severity of disease and risk for poor outcomes. Similar features were present between subgroups for predicting opioid misuse, but inequities were present. Post-hoc mitigation techniques mitigated bias in type II error rate without creating substantial type I error rates. From model design through deployment, bias and data disadvantages should be systematically addressed. Conclusion Standardized, transparent bias assessments are needed to improve trustworthiness in clinical machine learning models.

No abstract

Objective: In 2017 an academic health center in Chicago launched the multidisciplinary Substance Use Intervention Team (SUIT) to address opioid misuse across 18 inpatient units and in a new outpatient addiction medicine clinic. This report assesses the first five months of implementation and associations with patient health and healthcare utilization. Methods: Patient demographic and screening data were extracted from the administrative data warehouse of the electronic health record infrastructure. Distribution of sample characteristics for positive initial screens for opioid misuse was tested against those of all patients screened using a two-tailed test of proportions (p < 0.05). A second analysis compared length of stay and 30-day readmissions within a cohort of patients with a secondary diagnosis of substance use disorder. Results: Between November 2017-March 2018, 76% of 15,054 unique patients were screened, 578 had positive scores on the AUDIT and DAST, 131 had positive scores for opioid misuse, and 52 patients initiated medication treatment. Patients with a secondary diagnosis of substance use disorder who received a SUIT consult (n = 161), compared to those who did not (n = 612), had a shorter average length of stay (5.91 v. 6.73 days) and lower 30-day readmission rate (13.6% v. 15.7%). Conclusion: Leveraging the electronic health record to conduct standardized screenings and treatment has helped identify an at-risk population, disproportionately younger, black, and male, and treat new cases of opioid and substance misuse. The intervention indicates trends toward a shortened length of stay, reduced 30-day readmissions, and has linked patients to outpatient care.