This retrospective cohort study sought to determine whether screening for tuberculosis and hepatitis B and C was consistently performed prior to initiating immunosuppressive medications. About a quarter of patients were appropriately screened for all three infections before starting these high-risk medications, demonstrating the need for safety protocols regarding provision of immunosuppressive medication.

California's Medicaid pay-for-performance program requires safety-net health care systems to report and improve upon diverse ambulatory safety measures. Researchers found that participating safety-net hospitals struggled to report accurate data. Systems had more success improving metrics that placed patients at risk of life-threatening harm when compared to metrics that required longer term follow-up or patient engagement.

Machine learning, a type of computing that uses data and statistical methods to enable computers to progressively enhance their prediction or task performance over time, has been widely promoted as a tool to improve health care safety. This commentary describes the potential for machine learning to worsen socioeconomic disparities in health care. Disadvantaged populations are more likely to receive care in multiple health systems. Therefore, relevant data about their health may be missing in an individual health system's records, hindering performance of machine learning algorithms. Racial and ethnic minority patients may not be present in sufficient numbers for accurate prediction. The authors raise concern that implicit bias in the care that disadvantaged populations receive may influence algorithms, which will amplify this bias. They recommend inclusion of sociodemographic characteristics into algorithms, building and testing algorithms in diverse health care systems, and conducting follow-up testing to ensure that machine learning does not perpetuate or exacerbate health care disparities.

Patients in safety-net health systems may face unique patient safety risks. This study sought to use a consensus approach to develop standard measures for tracking safety gaps in ambulatory care in health systems that primarily serve vulnerable populations. The investigators identified nine measures suitable for tracking two high-priority safety gaps: notifying patients of actionable test results and monitoring patients with high-risk conditions.

Electronic health records have both safety benefits and unintended consequences. This review discusses safe management of rheumatoid arthritis in the ambulatory setting and highlights the need to capitalize on tools in electronic health records to enhance medication safety for the patients with rheumatoid arthritis.