Retrospective studies have shown artificial intelligence (AI) to be at least as accurate as radiologists in detecting breast cancer in screening mammograms. This prospective randomized trial similarly demonstrated that AI readings were as accurate as double readings by radiologists, but with a significantly reduced workload.

Research has shown a robust safety culture improves patient outcomes, reduces length of hospital stay, and increases patient and staff satisfaction. As such, safety culture is increasingly being measured by healthcare organizations. This review sought to identify the factors measured by safety culture instruments in hospitals. The Hospital Survey on Patient Safety Culture and Safety Attitudes Questionnaire were the most frequently used instruments. Important factors include organizational, professional, and patient and family participation, although none of the instruments measured all three.

Identifying and preventing drug-drug interactions (DDI) is critical to patient safety, but the usual method of detecting DDI and other errors - manual chart review - is resource intensive. This study describes the use of an e-trigger to pre-select charts for review that are more likely to include one of three DDIs, thus reducing the overall number of charts needing review. Two of the DDI e-triggers had high positive predictive values (0.76 and 0.57), demonstrating that e-triggers can be a useful method to pre-selecting charts for manual review.

Clinician skills can decrease with age. This retrospective analysis of 1.9 million preliminary interpretations of radiology imaging findings examined the relationship between radiologist age and diagnostic errors. While the overall mean error rate for all radiologists was low (0.5%), increasing age was associated with increased relative risk of diagnostic errors.

The transition from hospital to home is a vulnerable time as patients may have changes in medications or care needs, or difficulties accessing follow up with an outpatient provider. To reduce adverse events (AE), rehospitalizations, and emergency department visits, this hospital developed a structured discharge bundle based on the I-PASS tool used for inpatient handoffs. AE, rehospitalizations, and emergency department visits were all reduced following implementation of the I-PASS bundle.

Electronic health records (EHR) with computerized provider order entry (CPOE) help prevent many types of medication errors but poor user design can hinder these benefits. Using scores from the National Quality Forum Leapfrog Health IT Safety Measure and the ARCH Collaborative EHR User experience survey, this study compares safety scores and physician perceptions of usability. Results indicate a positive association between safety performance and user experience, affirming the importance of user-centered design.

A study conducted in 2011 concluded that pharmacy students identified more prescribing errors than their medical or nursing counterparts. This study replicates the 2011 study with first- and second-year physician assistant (PA) students. The results suggest PA students, regardless of year, identified prescribing errors at similar rates to medical and nursing students, although identification rates were low for all three student groups.

Parents of children with medical complexity can offer unique perspectives on hospital quality and safety. Prior to their child's discharge, parents were surveyed about their child's care, medications, safety, and other concerns experienced during their stay. Parents reported experiencing miscommunication with the providers and providers seemingly not communicating with each other. They also reported inconsistency in care/care plans, unmet expectations, lack of transparency, and a desire for their expertise to be taken seriously.

Improving diagnosis in pediatrics is an ongoing patient safety focus. This retrospective study included 129 pediatric emergency transfer cases and examined the relationship between missed opportunity for improvement in diagnosis (MOID; determined using SaferDx) and patient outcomes. Researchers found that MOID occurred in 29% of emergency transfer cases and it was associated with higher risk of mortality and longer post-transfer length of stay.

Patients who experience life-changing adverse events due to errors, and their families, typically want disclosure of the error and appropriate accountability. This systematic review identified 41 studies exploring the views of those affected by adverse events. Four themes were identified: transparency, person-centeredness, trustworthiness, and restorative justice. Applying these themes to investigations may result in ensuring the process and outcomes are experienced as "fair" to those impacted.

Fatigue and sleep deprivation of anesthesia providers can result in decreased non-technical skills and psychomotor functioning. This study of 1,200 anesthesia and intensive care trainees in Europe describes the impact of work-related fatigue on well-being, commuting, and potential for medical errors. Two-thirds of respondents reported making or nearly making a medical error after working long hours. In addition to implementing shorter work schedules, the authors also encourage a culture where it is acceptable to admit fatigue, and where resting is encouraged.

A simulation study in 2017 showed anesthesia residents performed worse when sleep-deprived after working a night shift. In this quantitative study of more than 5,000 European anesthesiologists, participants reported that working night shifts reduced their quality of life and put their patients at risk. Few reported institutional support (e.g., training, fatigue monitoring) for night shift workers. Importantly, this study reports on perceived risk to patients, not actual patient risk.

Pharmacists play a critical role in medication safety. This article evaluated the impact of a pharmacist-led information technology intervention (PINCER) among a retrospective cohort of 56.8 million National Health Service (NHS) patients across 6,367 general practices between September 2019 and September 2021. Findings indicate that potentially dangerous prescribing (i.e., prescribing medications to patients without associated blood test monitoring, co-prescribing medications with adverse indications, prescribing medications to patients with certain comorbidities) was largely unaffected by the COVID-19 pandemic.

Pediatric patients are at particularly high risk for medication errors. This article describes the STAMP initiative (Safe Treatment and Administration of Medicine in Pediatrics) which aims to reduce pediatric inpatient prescribing and administration errors. The authors summarize the STAMP interventions originally implemented in 2017 and discuss the new interventions implemented during the COVID-19 pandemic (between July 2020 and August 2021), which led to sustained reductions in prescribing errors.

Families can offer a unique perspective to improve patient care. This study describes ways families keep patients safe from suicide during crisis resolution home treatment in the UK. Families increased safety by hiding medications or distracting patients who were in crisis. Challenges to involving families are detailed, as well as ways organizations can overcome those challenges.

Electronic health records (EHR) are essential for recording patients' clinical data but may also perpetuate stigma, particularly for people of color. This article describes how the EHR can perpetuate individual, organizational, and structural racism and ways organizations, researchers, practitioners, and vendors can address racism.

… technology infrastructure to continue making progress. … Bates DW, Williams EA. Quality and Safety: Learning from the …

Prediction models are increasingly used in healthcare to identify potential patient safety events. This systematic review including 25 articles identified several challenges related to electronic health record (EHR)-based prediction models for adverse drug event diagnosis or prognosis, including adherence to reporting standards, use of best practices to develop and validate prediction models, and absence of causal prediction modeling.

In situ simulation is a valuable way to uncover latent safety threats (LTS) when implementing new workflows or care locations. This study reports on one New York state emergency department’s in situ simulation of airway control for COVID-19 patients. Across three cycles of Plan-Do-Study-Act, numerous LSTs were identified and resolved. Quarterly airway management simulations have continued and have expanded to additional departments and conditions, suggesting the sustainability of this type of quality improvement project.