Using Machine Learning to Predict Outcomes Following Transfemoral Carotid Artery Stenting.

BACKGROUND: Transfemoral carotid artery stenting (TFCAS) carries important perioperative risks. Outcome prediction tools may help guide clinical decision-making but remain limited. We developed machine learning algorithms that predict 1-year stroke or death following TFCAS. METHODS AND RESULTS: The VQI (Vascular Quality Initiative) database was used to identify patients who underwent TFCAS for carotid artery stenosis between 2005 and 2024. We identified 112 features from the index hospitalization (82 preoperative [demographic/clinical], 13 intraoperative [procedural], and 17 postoperative [in-hospital course/complications]). The primary outcome was 1-year postprocedural stroke or death. The data were divided into training (70%) and test (30%) sets. Six machine learning models were trained using preoperative features with 10-fold cross-validation. The primary model evaluation metric was area under the receiver operating characteristic curve. The algorithm with the best performance was further trained using intra- and postoperative features. Model robustness was assessed using calibration plots and Brier scores. Overall, 35 214 patients underwent TFCAS during the study period and 3257 (9.2%) developed 1-year stroke or death. The best preoperative prediction model was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.93-0.95). In comparison, logistic regression had an AUROC of 0.65 (95% CI, 0.63-0.67). The extreme gradient boosting model maintained excellent performance at the intra- and postoperative stages, with area under the receiver operating characteristic curve values of 0.94 (95% CI, 0.93-0.95) and 0.98 (95% CI, 0.97-0.99), respectively. Calibration plots showed good agreement between predicted/observed event probabilities with Brier scores of 0.11 (preoperative), 0.11 (intraoperative), and 0.09 (postoperative). CONCLUSIONS: Machine learning can accurately predict 1-year stroke or death following TFCAS, performing better than logistic regression.

Colchicine for cardiovascular and limb risk reduction in Medicare beneficiaries with peripheral artery disease: emulation of target trials.

Aims: Recent evidence from randomized trials demonstrates that colchicine can reduce the risk of major adverse cardiovascular events (MACE) in patients with coronary artery disease. Colchicine's effect on lower-extremity peripheral artery disease (PAD) is not known. Methods and results: To make inferences about the real-world effectiveness of colchicine in PAD, we emulated two target trials leveraging the variable prescribing practice of adding colchicine vs. a non-steroidal anti-inflammatory drug (NSAID) to urate-lowering therapy in patients with gout and PAD. Emulated Trial 1 compared colchicine initiators with NSAID initiators. Emulated Trial 2 compared long-term (indefinite) and short-term (3 months) treatment strategies after initiating colchicine. Eligible individuals were those continuously enrolled in Medicare receiving care at a multicentre academic health system between July 2007 and December 2019. The primary outcome for both trials was a 2 year composite of major adverse limb events (MALE), MACE, and all-cause mortality. Secondary outcomes included MALE and death, MACE and death, and individual components of the primary outcome. Inverse probability weighting was used to adjust for confounding. Percentile-based 95% confidence intervals (CIs) were estimated using non-parametric bootstrapping. A total of 1820 eligible patients were included; the mean age was 77 years [standard deviation (SD) 7], 32% were female, and 9% were non-White. The mean (SD) duration of colchicine and NSAID therapy was 247 (345) and 137 (237) days, respectively. In the emulation of Trial 1, the risk of the primary composite outcome of MALE, MACE, and death at 2 years was 29.9% (95% CI 27.2%, 32.3%) in the colchicine group and 31.5% (28.3%, 34.6%) in the NSAID group, with a risk difference of -1.7% (95% CI -6.5%, 3.1%) and a risk ratio of 0.95 (95% CI 0.83, 1.07). Similar findings were noted in the emulation of Trial 2, with a risk of the primary composite outcome at 2 years of 30.7% (95% CI 23.7%, 38.1%) in the long-term colchicine group and 33.4% (95% CI 29.4%, 37.7%) in the short-term group, with a risk difference of -2.7% (95% CI -10.3%, 5.4%) and risk ratio of 0.92 (95% CI 0.70, 1.16). Conclusion: In a real-world sample of patients with PAD and gout, estimates of the effect of colchicine were consistent across two analyses and provided no conclusive evidence that colchicine decreased the risk of adverse cardiovascular or limb events and death. The cardiovascular and limb benefits of colchicine in older, comorbid populations with PAD and advanced systematic atherosclerosis remain uncertain.

Predicting inferior vena cava filter complications using machine learning.

OBJECTIVE: Inferior vena cava (IVC) filter placement is associated with important long-term complications. Predictive models for filter-related complications may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 1-year IVC filter complications using preoperative data. METHODS: The Vascular Quality Initiative database was used to identify patients who underwent IVC filter placement between 2013 and 2024. We identified 77 preoperative demographic and clinical features from the index hospitalization when the filter was placed. The primary outcome was 1-year filter-related complications (composite of filter thrombosis, migration, angulation, fracture, and embolization or fragmentation, vein perforation, new caval or iliac vein thrombosis, new pulmonary embolism, access site thrombosis, or failed retrieval). The data were divided into training (70%) and test (30%) sets. Six ML models were trained using preoperative features with 10-fold cross-validation (Extreme Gradient Boosting, random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was assessed using calibration plot and Brier score. Performance was evaluated across subgroups based on age, sex, race, ethnicity, rurality, median Area Deprivation Index, planned duration of filter, landing site of filter, and presence of prior IVC filter placement. RESULTS: Overall, 14,476 patients underwent IVC filter placement and 584 (4.0%) experienced 1-year filter-related complications. Patients with a primary outcome were younger (59.3 ± 16.7 years vs 63.8 ± 16.0 years; P < .001) and more likely to have thrombotic risk factors including thrombophilia, prior venous thromboembolism (VTE), and family history of VTE. The best prediction model was Extreme Gradient Boosting, achieving an AUROC of 0.93 (95% confidence interval, 0.92-0.94). In comparison, logistic regression had an AUROC of 0.63 (95% confidence interval, 0.61-0.65). Calibration plot showed good agreement between predicted/observed event probabilities with a Brier score of 0.07. The top 10 predictors of 1-year filter-related complications were (1) thrombophilia, (2) prior VTE, (3) antiphospholipid antibodies, (4) factor V Leiden mutation, (5) family history of VTE, (6) planned duration of IVC filter (temporary), (7) unable to maintain therapeutic anticoagulation, (8) malignancy, (9) recent or active bleeding, and (10) age. Model performance remained robust across all subgroups. CONCLUSIONS: We developed ML models that can accurately predict 1-year IVC filter complications, performing better than logistic regression. These algorithms have potential to guide patient selection for filter placement, counselling, perioperative management, and follow-up to mitigate filter-related complications and improve outcomes.

Evaluating the Effectiveness of Systemic Heparin During Arteriovenous Fistula Creation by Emulating a Target Trial.

Most of the 800,000 people living with end-stage kidney disease in the United States rely on a functioning vascular access to provide life-sustaining hemodialysis, yet one-third of arteriovenous fistulas experience early failures. Determining the safety and effectiveness of systemic heparin during fistula creation could improve the quality and quantity of life for these vulnerable patients. In this paper, a pragmatic randomized trial was emulated to assess the effect of systemic heparin administration (vs. none) during radiocephalic arteriovenous fistula creation on early bleeding and thrombosis using data from two international multicenter randomized trials performed between 2014 and 2019. Marginal risks were estimated using inverse probability weighted parametric survival analysis and confidence intervals were generated with bootstrapping. A total of 914 patients were enrolled and 61% received systemic heparin; median (IQR) age was 58 (49, 67) years and 45% were on hemodialysis at enrollment. No difference in the risk of bleeding events was observed, with a risk difference (95% CI) at 14 days of -0.1% (-1.6, 1.4). The risk of access thrombosis was lower in the heparin group, with a risk of 3.7% (2.6, 4.8) after heparin and 5.3% (3.4, 7.4) without heparin at 14 days (risk ratio 0.72, 95% CI 0.50, 0.98).

Descriptive Analysis of Amputation-Free Survival After First Time Infra-Inguinal Bypass Occlusion.

INTRODUCTION: Occlusion after infra-inguinal bypass surgery for peripheral artery disease is a major complication with potentially devastating consequences. In this descriptive analysis, we sought to describe the natural history and explore factors associated with long-term major amputation-free survival following occlusion of a first-time infra-inguinal bypass. METHODS: Using a prospective database from a tertiary care vascular center, we conducted a retrospective cohort study of all patients with peripheral artery disease who underwent a first-time infra-inguinal bypass and subsequently suffered a graft occlusion (1997-2021). The primary outcome was longitudinal rate of major amputation-free survival after bypass occlusion. Cox proportional hazard models were used to generate hazard ratios (HRs) and 95% confidence intervals (CIs) to explore predictors of outcomes. RESULTS: Of the 1318 first-time infra-inguinal bypass surgeries performed over the study period, 255 bypasses occluded and were included in our analysis. Mean age was 66.7 (12.6) years, 40.4% were female, and indication for index bypass was chronic limb threatening ischemia (CLTI) in 89.8% (n = 229). 48.2% (n = 123) of index bypass conduits used great saphenous vein, 29.0% (n = 74) prosthetic graft, and 22.8% (n = 58) an alternative conduit. Median (interquartile range) time to bypass occlusion was 6.8 (2.3-19.0) months, and patients were followed for median of 4.3 (1.7-8.1) years after bypass occlusion. Following occlusion, 38.04% underwent no revascularization, 32.94% graft salvage procedure, 25.1% new bypass, and 3.92% native artery recanalization. Major amputation-free survival following occlusion was 56.9% (50.6%-62.8%) at 1 y, 37.1% (31%-43.3%) at 5 y, and 17.2% (11.9%-23.2%) at 10 y. In multivariable analysis, factors associated with lower amputation-free survival were older age, female sex, advanced cardiorenal comorbidities, CLTI at index procedure, CLTI at time of occlusion, and distal index bypass outflow. Initial treatment after occlusion with both a new surgical bypass (HR 0.44, CI: 0.29-0.67) or a graft salvage procedure (HR 0.56, CI: 0.38-0.82) showed improved amputation-free survival. One-year rate of major amputation or death were 59.8% (50.0%-69.6%) for those who underwent no revascularization, 37.9% (28.7%-49.0%) for graft salvage, and 26.7% (17.6%-39.5%) for new bypass. CONCLUSIONS: Long-term major amputation-free survival is low after occlusion of a first-time infra-inguinal bypass. While several nonmodifiable risk factors were associated with lower amputation-free survival, treatment after graft occlusion with either a new bypass or a graft salvage procedure may improve longitudinal outcomes.

Real-World Vein Mapping Practice Patterns Before Endovascular Treatment of Limb Ischemia.

INTRODUCTION: The Best Endovascular versus Best Surgical Therapy in Patients with Critical Limb Ischemia (BEST-CLI) trial results suggest that in patients with chronic limb-threatening ischemia (CLTI) and adequate single-segment great saphenous vein (SSGSV) by preoperative duplex ultrasonography, a surgical-first treatment strategy is superior to an endovascular-first strategy. However, the utilization of vein mapping prior to endovascular-first revascularization for CLTI in actual clinical practice is not known. METHODS: Data from a multicenter clinical data warehouse (2008-2019) were linked to Medicare claims data for patients undergoing endovascular-first treatment of infra-inguinal CLTI. Only patients who would have otherwise been eligible for enrollment in BEST-CLI were included. Adequate SSGSV was defined as healthy vein >3.0 mm in diameter from the groin through the knee. Logistic regression was used to estimate associations between preprocedure characteristics and vein mapping. Survival methods were used to estimate the risk of major adverse limb events and death. RESULTS: A total of 142 candidates for either surgical or endovascular treatment underwent endovascular-first management of CLTI. Ultrasound assessment for SSGSV was not performed in 76% of patients prior to endovascular-first revascularization. Of those who underwent preprocedure vein mapping, 44% had adequate SSGSV for bypass. Within one year postprocedure, 12.0% (95% confidence interval 7.4-18.0%) of patients underwent open surgical bypass and 54.7% (95% confidence interval 45.3-62.4%) experienced a major adverse limb event or death. CONCLUSIONS: In a real-world cohort of BEST-CLI-eligible patients undergoing endovascular-first intervention for infra-inguinal CLTI, three-quarters of patients had no preprocedure ultrasound assessment of great saphenous vein conduit. Practice patterns for vein conduit assessment in the real-world warrant reconsideration in the context of BEST-CLI trial results.

Comparative Effectiveness of Intravascular Ultrasound Versus Angiography in Abdominal and Thoracic Endovascular Aortic Repair: Systematic Review and Meta-Analysis.

The effectiveness of intravascular ultrasound (IVUS) with angiography compared with angiography guidance alone in treating aortic conditions, such as dissections, aneurysms, and blunt traumatic injuries, remains unclear. This systematic review and meta-analysis evaluates the current literature for IVUS use during thoracic endovascular aortic repair (TEVAR) and abdominal endovascular aortic repair (EVAR). A comprehensive search of MEDLINE, EMBASE, and Cochrane CENTRAL databases was conducted in March 2024 adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Studies comparing outcomes of TEVAR/EVAR with and without IVUS were identified. The outcomes of interest included contrast volume, fluoroscopy and procedural time, perioperative endoleak, and reinterventions and all-cause mortality during follow-up. Data with 95% confidence intervals (CIs) were extracted. Pooled analysis was performed using a random-effect model. Subgroup analysis was performed stratified by the condition being treated. Risk of bias was assessed using the Newcastle-Ottawa Scale for observational studies. A total of 4,219 patients (n = 2,655 IVUS and n = 1,564 non-IVUS) from 9 observational studies were included. The IVUS group exhibited a reduction in contrast agent volume (weighted mean difference -34.65 mL, 95% CI -54.73 to -14.57) and fluoroscopy time (weighted mean difference -6.13 minutes, 95% CI -11.10 to -1.15), with no difference in procedural time. The perioperative type I and III endoleak occurrences were similar (risk ratio 2.36, 95% CI 0.55 to 10.11; risk ratio 0.72, 95% CI 0.09 to 5.77, respectively). Reintervention and mortality during follow-up were comparable (hazard ratio 0.80, 95% CI 0.33 to 1.97; hazard ratio 0.75, 95% CI 0.47 to 1.18, respectively). All the included studies had small risks of bias. In conclusion, this meta-analysis provides evidence that IVUS enables the safe deployment of TEVAR/EVAR with reduced contrast agent and radiation exposure.

Predicting Outcomes Following Lower Extremity Endovascular Revascularization Using Machine Learning.

BACKGROUND: Lower extremity endovascular revascularization for peripheral artery disease carries nonnegligible perioperative risks; however, outcome prediction tools remain limited. Using machine learning, we developed automated algorithms that predict 30-day outcomes following lower extremity endovascular revascularization. METHODS AND RESULTS: The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity endovascular revascularization (angioplasty, stent, or atherectomy) for peripheral artery disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day postprocedural major adverse limb event (composite of major reintervention, untreated loss of patency, or major amputation) or death. 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 model evaluation metric was area under the receiver operating characteristic curve. Overall, 21 886 patients were included, and 30-day major adverse limb event/death occurred in 1964 (9.0%) individuals. The best performing model for predicting 30-day major adverse limb event/death was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI, 0.92-0.94). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.72 (95% CI, 0.70-0.74). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.09. The top 3 predictive features in our algorithm were (1) chronic limb-threatening ischemia, (2) tibial intervention, and (3) congestive heart failure. CONCLUSIONS: Our machine learning models accurately predict 30-day outcomes following lower extremity endovascular revascularization using preoperative data with good discrimination and calibration. Prospective validation is warranted to assess for generalizability and external validity.

Predicting the need for subclavian artery revascularization in thoracic endovascular aortic repair: A systematic review and meta-analysis.

OBJECTIVE: This systematic review and meta-analysis aims to investigate the effectiveness of left subclavian artery revascularization compared with non-revascularization in thoracic endovascular aortic repair, and to summarize the current evidence on its indications. METHODS: A computerized search was conducted across multiple databases, including MEDLINE, SCOPUS, Cochrane Library, and Web of Science, for studies published up to November 2023. Study selection, data abstraction, and quality assessment (using the Newcastle-Ottawa Scale) were independently conducted by two reviewers, with a third author resolving discrepancies. Pooled odds ratios (ORs) with 95% confidence intervals (CIs) were calculated using random-effects models and publication bias was assessed using funnel plots. RESULTS: In the 76 included studies, left subclavian artery revascularization was associated with reduced risks of stroke (OR, 0.67; 95% CI, 0.45-0.98; n = 15,331), spinal cord ischemia (OR, 0.75; 95% CI, 0.56-0.99; n = 11,995), and arm ischemia (OR, 0.09; 95% CI, 0.01-0.59; n = 8438). No significant reduction in paraplegia (OR, 0.56; 95% CI, 0.21-1.47; n = 1802) or mortality (OR, 0.77; 95% CI, 0.53-1.12; n = 11,831) was observed. Moreover, the risk of endoleak was comparable in both groups (OR, 1.25; 95% CI, 0.55-2.84; P = .60; n = 793), whereas the risk of reintervention was significantly higher in the revascularization group (OR, 1.98; 95% CI, 1.03-3.83; P = .04; n = 272). Both groups had similar risks of major (OR, 0.45; 95% CI, 0.19-1.09; P = .08; n = 1113), minor (OR, 0.21; 95% CI, 0.01-3.45; P = .27; n = 183), renal (OR, 0.61; 95% CI, 0.12-3.06; P = .55; n = 310), and pulmonary (OR, 0.59; 95% CI, 0.16-2.15; P = .42; n = 8083) complications. The most frequent indications for left subclavian artery revascularization were primary prevention of spinal cord ischemia, augmentation of the landing zone, and primary stroke prevention. CONCLUSIONS: Left subclavian artery revascularization in thoracic endovascular aortic repair was associated with reduced neurological complications but was not found to impact mortality. The study highlights important indications for revascularization as well as significant predictors of complications, providing a basis for clinical decision-making and future research.

Temporal trends in hemodialysis access creation during the fistula first era.

OBJECTIVE: Although forearm arteriovenous fistulas (AVFs) are the preferred initial vascular access for hemodialysis based on national guidelines, there are no population-level studies evaluating trends in creation of forearm vs upper arm AVFs and arteriovenous grafts (AVGs). The purpose of this study was to report temporal trends in first-time permanent hemodialysis access type, and to assess the effect of national initiatives on rates of AVF placement. METHODS: Retrospective cross-sectional study (2012-2022) utilizing the Vascular Quality Initiative database. All patients older than 18 years with creation of first-time upper extremity surgical hemodialysis access were included. Anatomic location of the AVF or AVG (forearm vs upper arm) was defined based on inflow artery, outflow vein, and presumed cannulation zone. Primary analysis examined temporal trends in rates of forearm vs upper arm AVFs and AVGs using time series analyses (modified Mann-Kendall test). Subgroup analyses examined rates of access configuration stratified by age, sex, race, dialysis, and socioeconomic status. Interrupted time series analysis was performed to assess the effect of the 2015 Fistula First Catheter Last initiative on rates of AVFs. RESULTS: Of the 52,170 accesses, 57.9% were upper arm AVFs, 25.2% were forearm AVFs, 15.4% were upper arm AVGs, and 1.5% were forearm AVGs. From 2012 to 2022, there was no significant change in overall rates of forearm or upper arm AVFs. There was a numerical increase in upper arm AVGs (13.9 to 18.2 per 100; P = .09), whereas forearm AVGs significantly declined (1.8 to 0.7 per 100; P = .02). In subgroup analyses, we observed a decrease in forearm AVFs among men (33.1 to 28.7 per 100; P = .04) and disadvantaged (Area Deprivation Index percentile ≥50) patients (29.0 to 20.7 per 100; P = .04), whereas female (17.2 to 23.1 per 100; P = .03), Black (15.6 to 24.5 per 100; P < .01), elderly (age ≥80 years) (18.7 to 32.5 per 100; P < .01), and disadvantaged (13.6 to 20.5 per 100; P < .01) patients had a significant increase in upper arm AVGs. The Fistula First Catheter Last initiative had no effect on the rate of AVF placement (83.2 to 83.7 per 100; P=.37). CONCLUSIONS: Despite national initiatives to promote autogenous vascular access, the rates of first-time AVFs have remained relatively constant, with forearm AVFs only representing one-quarter of all permanent surgical accesses. Furthermore, elderly, Black, female, and disadvantaged patients saw an increase in upper arm AVGs. Further efforts to elucidate factors associated with forearm AVF placement, as well as potential physician, center, and regional variation is warranted.

Predicting outcomes following lower extremity open revascularization using machine learning.

Lower extremity open revascularization is a treatment option for peripheral artery disease that carries significant peri-operative risks; however, outcome prediction tools remain limited. Using machine learning (ML), we developed automated algorithms that predict 30-day outcomes following lower extremity open revascularization. The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity open revascularization for chronic atherosclerotic disease between 2011 and 2021. Input features included 37 pre-operative demographic/clinical variables. The primary outcome was 30-day major adverse limb event (MALE; composite of untreated loss of patency, major reintervention, or major amputation) or death. Our data were split into training (70%) and test (30%) sets. Using tenfold cross-validation, we trained 6 ML models. Overall, 24,309 patients were included. The primary outcome of 30-day MALE or death occurred in 2349 (9.3%) patients. Our best performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve (95% CI) of 0.93 (0.92-0.94). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.08. Our ML algorithm has potential for important utility in guiding risk mitigation strategies for patients being considered for lower extremity open revascularization to improve outcomes.

Predicting Outcomes Following Endovascular Abdominal Aortic Aneurysm Repair Using Machine Learning.

OBJECTIVE: To develop machine learning (ML) models that predict outcomes following endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA). BACKGROUND: EVAR carries non-negligible perioperative risks; however, there are no widely used outcome prediction tools. METHODS: The National Surgical Quality Improvement Program targeted database was used to identify patients who underwent EVAR for infrarenal AAA between 2011 and 2021. Input features included 36 preoperative variables. The primary outcome was 30-day major adverse cardiovascular event (composite of myocardial infarction, stroke, or death). Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 ML models were trained using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve. Model robustness was evaluated with calibration plot and Brier score. Subgroup analysis was performed to assess model performance based on age, sex, race, ethnicity, and prior AAA repair. RESULTS: Overall, 16,282 patients were included. The primary outcome of 30-day major adverse cardiovascular event occurred in 390 (2.4%) patients. Our best-performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve (95% CI) of 0.95 (0.94-0.96) compared with logistic regression [0.72 [0.70-0.74)]. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.06. Model performance remained robust on all subgroup analyses. CONCLUSIONS: Our newer ML models accurately predict 30-day outcomes following EVAR using preoperative data and perform better than logistic regression. Our automated algorithms can guide risk mitigation strategies for patients being considered for EVAR.

Contemporary outcomes of distal radial artery ligation for access related hand ischemia.

OBJECTIVES: Access related hand ischemia (ARHI) is a rare albeit morbid complication of hemodialysis access creation. Distal radial artery ligation (DRAL) has been described as a strategy to improve perfusion to the hand while maintaining the access. The objective of this study was to report longitudinal outcomes of DRAL for ARHI. METHODS: Retrospective cohort study (2015-2021) of all patients who underwent DRAL for ARHI at a tertiary care vascular center. Subjects were identified using the Mass General Brigham clinical data warehouse and data collection was supplemented with chart adjudication. Outcomes captured included 30-day complications and improvement in ARHI-related symptoms at 1 year. RESULTS: Thirty-one patients were included. Mean (SD) age was 59.9 (14.5) and 67.7% were male. Wrist radial-cephalic (74.2%) and proximal radial-cephalic (9.7%) configurations were most common. ARHI severity was: 9.7% stage 1 (retrograde flow without symptoms); 38.7% stage 2 (pain during exercise or dialysis); 41.9% stage 3 (pain at rest); and 9.7% stage 4 (tissue loss). High flow was present in 35.5% of patients at baseline with median (IQR) flow of 1670 ml/min (1478-1954). After DRAL, median (IQR) flow reduction in the high flow group was 953 ml/min (645-993); concurrent precision banding was performed in 29% to reduce flow. The 30-day risk of complication was 3.2% (n = 1 access thrombosis). During follow-up, 82.1% showed improvement in symptoms and 3.6% of patients needed an additional procedure for ARHI. Carpal tunnel surgery was required for improvement in 7.1% of patients and was suspected as the culprit of symptoms in 7.1%. CONCLUSION: Distal radial artery ligation for ARHI is safe and can improve ischemic symptoms in most patients while salvaging access function. Precision banding can serve as a useful adjunct in high flow accesses. Carpal tunnel syndrome should be considered as part of the differential diagnosis of hand pain in this population.

Predicting recurrent interventions after radiocephalic arteriovenous fistula creation with machine learning and the PREDICT-AVF web app.

OBJECTIVE: Kidney Disease Outcomes Quality Initiative (KDOQI) guidelines discourage ongoing access salvage attempts after two interventions prior to successful use or more than three interventions per year overall. The goal was to develop a tool for prediction of radiocephalic arteriovenous fistula (AVF) intervention requirements to help guide shared decision-making about access appropriateness. METHODS: Prospective cohort study of 914 adult patients in the United States and Canada undergoing radiocephalic AVF creation at one of the 39 centers participating in the PATENCY-1 or -2 trials. Clinical data, including demographics, comorbidities, access history, anatomic features, and post-operative ultrasound measurements at 4-6 and 12 weeks were used to predict recurrent interventions required at 1 year postoperatively. Cox proportional hazards, random survival forest, pooled logistic, and elastic net recurrent event survival prediction models were built using a combination of baseline characteristics and post-operative ultrasound measurements. A web application was created, which generates patient-specific predictions contextualized with the KDOQI guidelines. RESULTS: Patients underwent an estimated 1.04 (95% CI 0.94-1.13) interventions in the first year. Mean (SD) age was 57 (13) years; 22% were female. Radiocephalic AVFs were created at the snuffbox (2%), wrist (74%), or proximal forearm (24%). Using baseline characteristics, the random survival forest model performed best, with an area under the receiver operating characteristic curve (AUROC) of 0.75 (95% CI 0.67-0.82) at 1 year. The addition of ultrasound information to baseline characteristics did not substantially improve performance; however, Cox models using either 4-6- or 12-week post-operative ultrasound information alone had the best discrimination performance, with AUROCs of 0.77 (0.70-0.85) and 0.76 (0.70-0.83) at 1 year. The interactive web application is deployed at https://predict-avf.com. CONCLUSIONS: The PREDICT-AVF web application can guide patient counseling and guideline-concordant shared decision-making as part of a patient-centered end-stage kidney disease life plan.

Predicting Major Adverse Cardiovascular Events Following Carotid Endarterectomy Using Machine Learning.

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.

Predicting outcomes following open revascularization for aortoiliac occlusive disease using machine learning.

OBJECTIVE: Open surgical treatment options for aortoiliac occlusive disease carry significant perioperative risks; however, outcome prediction tools remain limited. Using machine learning (ML), we developed automated algorithms that predict 30-day outcomes following open aortoiliac revascularization. METHODS: The National Surgical Quality Improvement Program (NSQIP) targeted vascular database was used to identify patients who underwent open aortoiliac revascularization for atherosclerotic disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day major adverse limb event (MALE; composite of untreated loss of patency, major reintervention, or major amputation) or death. The 30-day secondary outcomes were individual components of the primary outcome, major adverse cardiovascular event (MACE; composite of myocardial infarction, stroke, or death), individual components of MACE, wound complication, bleeding, other morbidity, non-home discharge, and unplanned readmission. Our data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, we trained six ML models using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score. Variable importance scores were calculated to determine the top 10 predictive features. Performance was assessed on subgroups based on age, sex, race, ethnicity, symptom status, procedure type, and urgency. RESULTS: Overall, 9649 patients were included. The primary outcome of 30-day MALE or death occurred in 1021 patients (10.6%). Our best performing prediction model for 30-day MALE or death was XGBoost, achieving an AUROC of 0.95 (95% confidence interval [CI], 0.94-0.96). In comparison, logistic regression had an AUROC of 0.79 (95% CI, 0.77-0.81). For 30-day secondary outcomes, XGBoost achieved AUROCs between 0.87 and 0.97 (untreated loss of patency [0.95], major reintervention [0.88], major amputation [0.96], death [0.97], MACE [0.95], myocardial infarction [0.88], stroke [0.93], wound complication [0.94], bleeding [0.87], other morbidity [0.96], non-home discharge [0.90], and unplanned readmission [0.91]). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.05. The strongest predictive feature in our algorithm was chronic limb-threatening ischemia. Model performance remained robust on all subgroup analyses of specific demographic/clinical populations. CONCLUSIONS: Our ML models accurately predict 30-day outcomes following open aortoiliac revascularization using preoperative data, performing better than logistic regression. They have potential for important utility in guiding risk-mitigation strategies for patients being considered for open aortoiliac revascularization to improve outcomes.

Comparative effectiveness of bovine carotid artery xenograft and polytetrafluoroethylene in hemodialysis access revision.

BACKGROUND: When hemodialysis arteriovenous accesses fail, autogenous options are often limited. Non-autogenous conduit choices include bovine carotid artery xenografts (BCAG) and expanded polytetrafluoroethylene (PTFE), yet their comparative effectiveness in hemodialysis access revision remains largely unknown. METHODS: A cohort study was performed from a prospectively collected institutional database from August 2010 to July 2021. All patients undergoing an arteriovenous access revision with either BCAG or PTFE were followed for up to 3 years from their index access revision. Revision was defined as graft placement to address a specific problem of an existing arteriovenous access while maintaining one or more of the key components of the original access (e.g. inflow, outflow, and cannulation zone). Outcomes were measured starting at the date of the index revision procedure. The primary outcome was loss of secondary patency at 3 years. Secondary outcomes included loss of post-intervention primary patency, rates of recurrent interventions, and 30-day complications. Pooled logistic regression was used to estimate inverse probability weighted marginal structural models for the time-to-event outcomes of interest. RESULTS: A total of 159 patients were included in the study, and 58% received access revision with BCAG. Common indications for revision included worn out cannulation zones (32%), thrombosis (18%), outflow augmentation (16%), and inflow augmentation (13%). Estimated risk of secondary patency loss at 3 years was lower in the BCAG group (8.6%, 3.9-15.1) compared to the PTFE group (24.8%, 12.4-38.7). Patients receiving BCAG experienced a 60% decreased relative risk of secondary patency loss at 3 years (risk ratio 0.40, 0.14-0.86). Recurrent interventions occurred at similar rates in the BCAG and PTFE groups, with 1.86 (1.31-2.43) and 1.60 (1.07-2.14) interventions at 1 year, respectively (hazard ratio 1.22, 0.74-1.96). CONCLUSIONS: Under the conditions of this contemporary cohort study, use of BCAG in upper extremity hemodialysis access revision decreased access abandonment when compared to PTFE.

Developing Validated Tools to Identify Pulmonary Embolism in Electronic Databases: Rationale and Design of the PE-EHR+ Study.

BACKGROUND: Contemporary pulmonary embolism (PE) research, in many cases, relies on data from electronic health records (EHRs) and administrative databases that use International Classification of Diseases (ICD) codes. Natural language processing (NLP) tools can be used for automated chart review and patient identification. However, there remains uncertainty with the validity of ICD-10 codes or NLP algorithms for patient identification. METHODS: The PE-EHR+ study has been designed to validate ICD-10 codes as Principal Discharge Diagnosis, or Secondary Discharge Diagnoses, as well as NLP tools set out in prior studies to identify patients with PE within EHRs. Manual chart review by two independent abstractors by predefined criteria will be the reference standard. Sensitivity, specificity, and positive and negative predictive values will be determined. We will assess the discriminatory function of code subgroups for intermediate- and high-risk PE. In addition, accuracy of NLP algorithms to identify PE from radiology reports will be assessed. RESULTS: A total of 1,734 patients from the Mass General Brigham health system have been identified. These include 578 with ICD-10 Principal Discharge Diagnosis codes for PE, 578 with codes in the secondary position, and 578 without PE codes during the index hospitalization. Patients within each group were selected randomly from the entire pool of patients at the Mass General Brigham health system. A smaller subset of patients will also be identified from the Yale-New Haven Health System. Data validation and analyses will be forthcoming. CONCLUSIONS: The PE-EHR+ study will help validate efficient tools for identification of patients with PE in EHRs, improving the reliability of efficient observational studies or randomized trials of patients with PE using electronic databases.

Staged autogenous to prosthetic hemodialysis access creation strategy to maximize forearm options.

OBJECTIVE: When an adequate cephalic vein is not available for fistula construction, surgeons often turn to basilic vein or prosthetic constructions. Single-stage forearm prosthetic hemodialysis accesses are associated with poor durability, and upper arm non-autogenous access options are often limited by axillary outflow failure, which inevitably drives transition to the contralateral arm or lower extremity. We hypothesized that initial creation of a modest flow proximal forearm arterial-venous anastomosis to dilate ("develop") inflow and outflow vessels, followed by a planned second-stage procedure to create a cannulation zone with a prosthetic graft in the forearm, would result in reliable and durable hemodialysis access in patients with limited options. METHODS: We performed an institutional cohort study from 2017 to 2021 using a prospectively maintained database supplemented with adjudicated chart review. Patients without traditional autogenous hemodialysis access options in the forearm underwent an initial non-wrist arterial-venous anastomosis creation in the forearm as a first stage, followed by a second-stage interposition graft sewn to the existing inflow and venous outflow segments to create a useable cannulation zone in the forearm while leveraging vascular development. Outcomes included time from second-stage access creation to loss of primary and secondary patency, frequency of subsequent interventions, and perioperative complications. RESULTS: The cohort included 23 patients; first-stage radial artery-based (74%) configurations were more common than brachial artery-based (26%). Mean age was 63 years (standard deviation, 14 years), and 65% were female. Median follow-up was 340 days (interquartile range [IQR], 169-701 days). Median time to cannulation from second-stage procedure was 28 days (IQR, 18-53 days). Primary, primary assisted, and secondary patency at 1 year was 16.7% (95% confidence interval [CI], 5.3%-45.8%), 34.6% (95% CI, 15.2%-66.2%), and 95.7% (95% CI, 81.3%-99.7%), respectively. Subsequent interventions occurred at a rate of 3.02 (IQR, 1.0-4.97) per person-year, with endovascular thrombectomy with or without angioplasty/stenting (70.9%) being the most common. There were no cases of steal syndrome. Infection occurred in two cases and were managed with antibiotics alone. CONCLUSIONS: For patients without adequate distal autogenous access options, staged prosthetic graft placement in the forearm offers few short-term complications and excellent durability with active surveillance while strategically preserving the upper arm for future constructions.