Evaluation of the impact of artificial intelligence-assisted image interpretation on the diagnostic performance of clinicians in identifying pneumothoraces on plain chest X-ray: a multi-case multi-reader study.

BACKGROUND: Artificial intelligence (AI)-assisted image interpretation is a fast-developing area of clinical innovation. Most research to date has focused on the performance of AI-assisted algorithms in comparison with that of radiologists rather than evaluating the algorithms' impact on the clinicians who often undertake initial image interpretation in routine clinical practice. This study assessed the impact of AI-assisted image interpretation on the diagnostic performance of frontline acute care clinicians for the detection of pneumothoraces (PTX). METHODS: A multicentre blinded multi-case multi-reader study was conducted between October 2021 and January 2022. The online study recruited 18 clinician readers from six different clinical specialties, with differing levels of seniority, across four English hospitals. The study included 395 plain CXR images, 189 positive for PTX and 206 negative. The reference standard was the consensus opinion of two thoracic radiologists with a third acting as arbitrator. General Electric Healthcare Critical Care Suite (GEHC CCS) PTX algorithm was applied to the final dataset. Readers individually interpreted the dataset without AI assistance, recording the presence or absence of a PTX and a confidence rating. Following a 'washout' period, this process was repeated including the AI output. RESULTS: Analysis of the performance of the algorithm for detecting or ruling out a PTX revealed an overall AUROC of 0.939. Overall reader sensitivity increased by 11.4% (95% CI 4.8, 18.0, p=0.002) from 66.8% (95% CI 57.3, 76.2) unaided to 78.1% aided (95% CI 72.2, 84.0, p=0.002), specificity 93.9% (95% CI 90.9, 97.0) without AI to 95.8% (95% CI 93.7, 97.9, p=0.247). The junior reader subgroup showed the largest improvement at 21.7% (95% CI 10.9, 32.6), increasing from 56.0% (95% CI 37.7, 74.3) to 77.7% (95% CI 65.8, 89.7, p<0.01). CONCLUSION: The study indicates that AI-assisted image interpretation significantly enhances the diagnostic accuracy of clinicians in detecting PTX, particularly benefiting less experienced practitioners. While overall interpretation time remained unchanged, the use of AI improved diagnostic confidence and sensitivity, especially among junior clinicians. These findings underscore the potential of AI to support less skilled clinicians in acute care settings.

Specification, validation, and adherence of quality indicators to optimize the safe use of nonsteroidal anti-inflammatory drugs for knee osteoarthritis pain in the primary care setting.

BACKGROUND: Nonsteroidal anti-inflammatory drugs (NSAIDs) used for osteoarthritis (OA) in primary care may cause gastrointestinal or renal injury. This study estimated adherence to two quality indicators (QIs) to optimize NSAID safety: add proton pump inhibitors (PPI) to NSAIDs for patients with gastrointestinal (GI) risk (QI #1 NSAID-PPI) and avoid oral NSAIDs in chronic kidney disease (CKD) stage G4 or G5 (QI #2 NSAID-CKD). METHODS: This retrospective study included index primary care clinic visits for knee OA at our health system in 2019. The validation cohort consisted of a random sample of 60 patients. The remainder were included in the expanded cohort. Analysis of structured data extracts was validated against chart review of clinic visit notes (validation cohort) and estimated QI adherence (expanded cohort). RESULTS: Among 60 patients in the validation cohort, analysis of data extracts was validated against chart review for QI #1 NSAID-PPI (100% sensitivity and 91% specificity) and QI #2 NSAID-CKD (100% accuracy). Among 335 patients in the expanded cohort, 44% used NSAIDs, 27% used PPIs, 73% had elevated GI risk, and only 2% had CKD stage 4 or 5. Twenty-one percent used NSAIDs and had elevated GI risk but were not using PPIs. Therefore, adherence to QI #1 NSAID-PPI was 79% (95% CI, 74-83%). No patients with CKD stage 4 or 5 used NSAIDs. Therefore, adherence to QI #2 NSAID-CKD was 100%. CONCLUSION: A substantial proportion of knee OA patients with GI risk factors did not receive PPI with NSAID therapy during primary care visits.

Implementation and Use of Risk Evaluation and Mitigation Strategies Programs in Practice: A Scoping Review of the Literature.

BACKGROUND: Risk Evaluation and Mitigation Strategy (REMS) programs intend to improve medication safety but can add significant administrative burdens to providers and health systems. Various stakeholders have made efforts to use technology to improve REMS programs. OBJECTIVES: The objective of this scoping review is to describe studies evaluating workflows, automation, or electronic data exchange related to REMS programs. METHODS: A literature search of PubMed, Embase, and Web of Science was performed for articles published between January 2007 and July 2021. Studies were identified using the relevant Medical Subject Headings terms and related keywords. Articles must have described a workflow change and measured the impact of the workflow change. RESULTS: Of 299 citations initially identified, 7 were included in the final review after removing duplicates and articles not meeting predefined inclusion criteria. Included studies consisted of three manuscripts and four conference abstracts. Electronic health record interventions, such as customized order sets and clinical decision support alerts, were the most common strategy reported. Other strategies included developing a portal to verify REMS enrollment, requiring prescribers to contact the dispensing pharmacy, provider education, and restrictions based on the provider specialty. One study evaluated automated data exchange for REMS program processes in a mock environment. Although only three studies reported baseline metrics for comparison, all studies noted an improvement or benefit to the implemented workflow process changes. CONCLUSION: There is limited evidence describing REMS workflows, automation, and electronic data exchange. Various strategies to address REMS program requirements were reported, but no studies described the use of data exchange standards in a real-world setting despite efforts by the Food and Drug Administration and other stakeholders. Additional efforts are needed to automate REMS programs.

Fetal alcohol spectrum disorder-associated depression: evidence for reductions in the levels of brain-derived neurotrophic factor in a mouse model.

Prenatal ethanol exposure is associated with an increased incidence of depressive disorders in patient populations. However, the mechanisms that link prenatal ethanol exposure and depression are unknown. Several recent studies have implicated reduced brain-derived neurotrophic factor (BDNF) levels in the hippocampal formation and frontal cortex as important contributors to the etiology of depression. In the present studies, we sought to determine whether prenatal ethanol exposure is associated with behaviors that model depression, as well as with reduced BDNF levels in the hippocampal formation and/or medial frontal cortex, in a mouse model of fetal alcohol spectrum disorder (FASD). Compared to control adult mice, prenatal ethanol-exposed adult mice displayed increased learned helplessness behavior and increased immobility in the Porsolt forced swim test. Prenatal ethanol exposure was associated with decreased BDNF protein levels in the medial frontal cortex, but not the hippocampal formation, while total BDNF mRNA and BDNF transcripts containing exons III, IV or VI were reduced in both the medial frontal cortex and the hippocampal formation of prenatal ethanol-exposed mice. These results identify reduced BDNF levels in the medial frontal cortex and hippocampal formation as potential mediators of depressive disorders associated with FASD.

Coronary Revascularization in Cardiogenic Shock.

OPINION STATEMENT: Early revascularization in acute myocardial infarction (MI) complicated by cardiogenic shock (CS) reduces mortality with a life saved for every eight patients treated. Percutaneous coronary intervention (PCI) has become the mainstay of treatment for CS, particularly for ST-segment elevation MI, due to the ability to achieve rapid reperfusion; with coronary artery bypass graft (CABG) operations reserved for patients with mechanical complications or anatomy that poses challenges for timely PCI. Mortality remains high even in patients with successful revascularization, and interventional cardiologists must consider additional treatment options. Recent data supports the performance of multi-vessel PCI to achieve complete revascularization in this setting. In addition, early implementation of a percutaneous hemodynamic support device is recommended in patients in whom shock is profound and unlikely to reverse with culprit lesion PCI.

Association of radial versus femoral access with contrast-induced acute kidney injury in patients undergoing primary percutaneous coronary intervention for ST-elevation myocardial infarction.

BACKGROUND: Patients with ST-elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PCI) are at an increased risk of developing contrast-induced acute kidney injury (CI-AKI). Data on the association between transradial (TRA) vs. transfemoral (TFA) access and the risk of CI-AKI in this setting are limited. METHODS: We analyzed data on 1162 patients undergoing primary PCI for STEMI at two tertiary care centers between 2010 and 2014. Primary outcome was CI-AKI, defined as a relative rise in serum creatinine of ≥25%, or an absolute increase of ≥0.5mg/dL, within 48h of primary PCI. We used multivariable logistic regression and propensity analysis to determine the association between vascular access site and CI-AKI. RESULTS: Of 1162 patients who underwent primary PCI for STEMI, TFA was used in 857 (73.8%), and TRA in 305 (26.2%) patients. In the unmatched cohort, TRA was associated with numerically lower rates of CI-AKI as compared with TFA; however, this difference did not reach statistical significance (5.9% vs. 7.0%; unadjusted OR 0.83, 95%CI 0.48-1.44, p=0.510; adjusted OR 0.84, 95%CI 0.44-1.62, p=0.610). Similar results were seen in a propensity matched cohort of 508 patients (254 TRA and 254 TFA; CI-AKI 5.5% vs. 8.3%, OR 0.65, 95% CI 0.32-1.30, p=0.220). CONCLUSIONS: In patients with STEMI undergoing primary PCI, TRA was not associated with a lower risk of CI-AKI, as compared with TFA. Randomized controlled trials are needed to definitely assess the role of vascular access site in reducing the risk of CI-AKI in patients undergoing primary PCI for STEMI. SUMMARY: In patients with STEMI undergoing primary PCI, the overall incidence of contrast-induced acute kidney injury (CI-AKI) was low (6.7%). Transradial access was not associated with a lower risk of CI-AKI as compared with transfemoral access.

Regional differences in quality of care and outcomes for the treatment of acute coronary syndromes: an analysis from the get with the guidelines coronary artery disease program.

BACKGROUND: Geographic differences in the delivery of guideline-driven care following acute myocardial infarction have been described. The effect of hospital participation in a national performance improvement program on regional variation in quality of care and in-hospital outcomes for acute coronary syndromes (ACS) is unknown. METHODS: We evaluated the variation in conformity to the American Heart Association Get With The Guidelines-Coronary Artery Disease Program quality measures across 4 geographic regions (Northeast, Midwest, South, and East) in 161,236 patients admitted for ACS to 436 Get With The Guidelines hospitals. We evaluated 6 measures (aspirin within 24 hours, aspirin at discharge, ACEI or ARB therapy for left ventricular systolic dysfunction, beta-blocker at discharge, lipid-lowering medication for qualified patients, smoking cessation advice); a binary "all-or-none" process performance measure (primary outcome); an "opportunity-based" overall composite score (secondary outcome); in-hospital length of stay, and in-hospital mortality. Multivariable logistic regression was performed to test the associations between performance measures and short-term outcomes and geographic region. RESULTS: Data were collected from January 2, 2000 to January 2, 2008. There was no significant regional variation in either the "all-or-none" (Northeast: 79.3%; Midwest: 83.2%; South: 78.9%; West: 81.6%) or "opportunity-based" (Northeast: 91.9%; Midwest: 93.6%; South: 91.5%; West: 92.6%) composite performance measures. Both performance measures exhibited significant improvement with participation time irrespective of region. In-hospital mortality was similar among regions. Adjusted hospital length of stay was significantly shorter in the Midwest. CONCLUSION: Quality improvement program participation may help to facilitate high quality, consistent care for patients with ACS.