Machine learning (ML) is a rapidly advancing field with increasing utility in health care. We conducted a systematic review and critical appraisal of ML applications in vascular surgery. MEDLINE, Embase, and Cochrane CENTRAL were searched from inception to March 1, 2021. Study screening, data extraction, and quality assessment were performed by two independent reviewers, with a third author resolving discrepancies. All original studies reporting ML applications in vascular surgery were included. Publication trends, disease conditions, methodologies, and outcomes were summarized. Critical appraisal was conducted using the PROBAST risk-of-bias and TRIPOD reporting adherence tools. We included 212 studies from a pool of 2235 unique articles. ML techniques were used for diagnosis, prognosis, and image segmentation in carotid stenosis, aortic aneurysm/dissection, peripheral artery disease, diabetic foot ulcer, venous disease, and renal artery stenosis. The number of publications on ML in vascular surgery increased from 1 (1991–1996) to 118 (2016–2021). Most studies were retrospective and single center, with no randomized controlled trials. The median area under the receiver operating characteristic curve (AUROC) was 0.88 (range 0.61–1.00), with 79.5% [62/78] studies reporting AUROC ≥ 0.80. Out of 22 studies comparing ML techniques to existing prediction tools, clinicians, or traditional regression models, 20 performed better and 2 performed similarly. Overall, 94.8% (201/212) studies had high risk-of-bias and adherence to reporting standards was poor with a rate of 41.4%. Despite improvements over time, study quality and reporting remain inadequate. Future studies should consider standardized tools such as PROBAST and TRIPOD to improve study quality and clinical applicability.

Objective Many studies have analysed gender bias in academic medicine; however, no comprehensive synthesis of the literature has been performed. We conducted a pooled analysis of the difference in the proportion of men versus women with full professorship among academic physicians. Design Systematic review and meta-analysis. Data sources MEDLINE, Embase, Cochrane Central Register of Controlled Trials, Education Resources Information Center and PsycINFO were searched from inception to 3 July 2020. Study selection All original studies reporting faculty rank stratified by gender worldwide were included. Data extraction and synthesis Study screening, data extraction and quality assessment were performed by two independent reviewers, with a third author resolving discrepancies. Meta-analysis was conducted using random-effects models. Results Our search yielded 5897 articles. 218 studies were included with 991 207 academic physician data points. Men were 2.77 times more likely to be full professors (182 271/643 790 men vs 30 349/251 501 women, OR 2.77, 95% CI 2.57 to 2.98). Although men practised for longer (median 18 vs 12 years, p<0.00002), the gender gap remained after pooling seven studies that adjusted for factors including time in practice, specialty, publications, h-index, additional PhD and institution (adjusted OR 1.83, 95% CI 1.04 to 3.20). Meta-regression by data collection year demonstrated improvement over time (p=0.0011); however, subgroup analysis showed that gender disparities remain significant in the 2010–2020 decade (OR 2.63, 95% CI 2.48 to 2.80). The gender gap was present across all specialties and both within and outside of North America. Men published more papers (mean difference 17.2, 95% CI 14.7 to 19.7), earned higher salaries (mean difference $33 256, 95% CI $25 969 to $40 542) and were more likely to be departmental chairs (OR 2.61, 95% CI 2.19 to 3.12). Conclusions Gender inequity in academic medicine exists across all specialties, geographical regions and multiple measures of success, including academic rank, publications, salary and leadership. Men are more likely than women to be full professors after controlling for experience, academic productivity and specialty. Although there has been some improvement over time, the gender disparity in faculty rank persists. PROSPERO registration number CRD42020197414.

Fatty acid binding proteins (FABPs) are proteins found in the cytosol that contribute to disorders related to the cardiovascular system, including atherosclerosis and metabolic syndrome. Functionally, FABPs serve as intracellular lipid chaperones, interacting with hydrophobic ligands and mediating their transportation to sites of lipid metabolism. To date, nine unique members of the FABP family (FABP 1–9) have been identified and classified according to the tissue in which they are most highly expressed. In the literature, FABP3 has been shown to be a promising clinical biomarker for coronary and peripheral artery disease. Given the rising incidence of cardiovascular disease and its associated morbidity/mortality, identifying biomarkers for early diagnosis and treatment is critical. In this review, we highlight key discoveries and recent studies on the role of FABP3 in cardiovascular disorders, with a particular focus on its clinical relevance as a biomarker for peripheral artery disease.

Background: Carotid endarterectomy (CEA) is a major vascular operation for stroke prevention that carries significant perioperative risks; however, outcome prediction tools remain limited. The authors developed machine learning algorithms to predict outcomes following CEA. Methods and Results: The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent CEA between 2011 and 2021. Input features included 36 preoperative demographic/clinical variables. The primary outcome was 30‐day major adverse cardiovascular events (composite of stroke, myocardial infarction, or death). The data were split into training (70%) and test (30%) sets. Using 10‐fold cross‐validation, 6 machine learning models were trained using preoperative features. The primary metric for evaluating model performance was area under the receiver operating characteristic curve. Model robustness was evaluated with calibration plot and Brier score. Overall, 38 853 patients underwent CEA during the study period. Thirty‐day major adverse cardiovascular events occurred in 1683 (4.3%) patients. The best performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve of 0.91 (95% CI, 0.90–0.92). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.62 (95% CI, 0.60–0.64), and existing tools in the literature demonstrate area under the receiver operating characteristic curve values ranging from 0.58 to 0.74. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.02. The strongest predictive feature in our algorithm was carotid symptom status. Conclusions: The machine learning models accurately predicted 30‐day outcomes following CEA using preoperative data and performed better than existing tools. They have potential for important utility in guiding risk‐mitigation strategies to improve outcomes for patients being considered for CEA.