Utility of the Vascular Quality Initiative in improving quality of care in Canadian patients undergoing vascular surgery

Liao, Elizabeth; Eisenberg, Naomi; Kaushal, Anish; Montbriand, Janice; Tan, Kiat Tsong; Roche-Nagle, Graham

doi:10.1503/cjs.002218

Cited by 20 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…19 The number of VQI centers has grown considerably from 400 in 2019 to more than 1000 in 2023. 19,57 Therefore, our models have broad and growing utility. A key advantage of our ML models is their ability to provide automated risk predictions, thereby enhancing feasibility in busy clinical settings compared with traditional risk predictors that often require manual input of variables.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning to Predict Outcomes of Endovascular Intervention for Patients With PAD

Li,

Warren,

Eisenberg

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceEndovascular intervention for peripheral artery disease (PAD) carries nonnegligible perioperative risks; however, outcome prediction tools are limited.ObjectiveTo develop machine learning (ML) algorithms that can predict outcomes following endovascular intervention for PAD.Design, Setting, and ParticipantsThis prognostic study included patients who underwent endovascular intervention for PAD between January 1, 2004, and July 5, 2023, with 1 year of follow-up. Data were obtained from the Vascular Quality Initiative (VQI), a multicenter registry containing data from vascular surgeons and interventionalists at more than 1000 academic and community hospitals. From an initial cohort of 262 242 patients, 26 565 were excluded due to treatment for acute limb ischemia (n = 14 642) or aneurysmal disease (n = 3456), unreported symptom status (n = 4401) or procedure type (n = 2319), or concurrent bypass (n = 1747). Data were split into training (70%) and test (30%) sets.ExposuresA total of 112 predictive features (75 preoperative [demographic and clinical], 24 intraoperative [procedural], and 13 postoperative [in-hospital course and complications]) from the index hospitalization were identified.Main Outcomes and MeasuresUsing 10-fold cross-validation, 6 ML models were trained using preoperative features to predict 1-year major adverse limb event (MALE; composite of thrombectomy or thrombolysis, surgical reintervention, or major amputation) or death. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). After selecting the best performing algorithm, additional models were built using intraoperative and postoperative data.ResultsOverall, 235 677 patients who underwent endovascular intervention for PAD were included (mean [SD] age, 68.4 [11.1] years; 94 979 [40.3%] female) and 71 683 (30.4%) developed 1-year MALE or death. The best preoperative prediction model was extreme gradient boosting (XGBoost), achieving the following performance metrics: AUROC, 0.94 (95% CI, 0.93-0.95); accuracy, 0.86 (95% CI, 0.85-0.87); sensitivity, 0.87; specificity, 0.85; positive predictive value, 0.85; and negative predictive value, 0.87. In comparison, logistic regression had an AUROC of 0.67 (95% CI, 0.65-0.69). The XGBoost model maintained excellent performance at the intraoperative and postoperative stages, with AUROCs of 0.94 (95% CI, 0.93-0.95) and 0.98 (95% CI, 0.97-0.99), respectively.Conclusions and RelevanceIn this prognostic study, ML models were developed that accurately predicted outcomes following endovascular intervention for PAD, which performed better than logistic regression. These algorithms have potential for important utility in guiding perioperative risk-mitigation strategies to prevent adverse outcomes following endovascular intervention for PAD.

show abstract

Section: Discussionmentioning

confidence: 99%

“…At a system-wide level, our models can be implemented by the more than 1000 VQI participating centers . The number of VQI centers has grown considerably from 400 in 2019 to more than 1000 in 2023 . Therefore, our models have broad and growing utility.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning to Predict Outcomes of Endovascular Intervention for Patients With PAD

Li,

Warren,

Eisenberg

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

show abstract

“…It joined with the SVS and became national in 2011 and is now composed of 18 regional groups with registry data representing more than 650 community and academic hospitals in the USA and Canada. 9 Entry of data and procedures, now totaling well over 800 000 procedures crossing nine major vascular catagories, is maintained by individual centers and physicians and ensured by annual audits against hospital claims data. 10 Follow-up data are required for 1 year following procedure but, at the discretion of individual centers, can be entered indefinitely.…”

Section: Methodsmentioning

confidence: 99%

“…The Society for Vascular Surgery (SVS) VQI is a patient safety organization initially formed in 2001 as the Vascular Study Group of New England which served as a voluntary cooperative regional database for local quality improvement and expanded yearly thereafter. It joined with the SVS and became national in 2011 and is now composed of 18 regional groups with registry data representing more than 650 community and academic hospitals in the USA and Canada 9. Entry of data and procedures, now totaling well over 800 000 procedures crossing nine major vascular catagories, is maintained by individual centers and physicians and ensured by annual audits against hospital claims data 10.…”

Section: Methodsmentioning

confidence: 99%

Occurrence and outcomes of type 3 endoleaks in endovascular aortic repair within the Vascular Quality Initiative database

Blakeslee-Carter

Beck

Spangler

2020

BMJ Surg Interv Health Technologies

View full text Add to dashboard Cite

ObjectivesType 3 endoleaks (T3ELs) represent a lack of aneurysm protection from systemic pressure. Previous studies have found a ~2% incidence of T3EL after standard infrarenal endovascular aneurysm repair (EVAR); however, no prior studies with new-generation devices have been able to determine an association between T3EL and clinical outcomes. Here we examine T3EL within the Society for Vascular Surgery Vascular Quality Initiative (VQI) to define rates of occurrence, rates and modes of reintervention, and clinical consequences of these endoleaks.Design and settingParticipants receiving infrarenal EVAR in the VQI from January 2003 to September 2018 were analyzed in a retrospective cohort study.ParticipantsOf 42 246 entries in the EVAR procedural registry, 41 604 had complete procedural information and were included in analysis. Of these, 36 082 had long-term follow-up, and 26 422 had follow-up (9–21 months per VQI reporting standards) with complete endoleak data recorded.InterventionsAll patients included in this study underwent an infrarenal EVAR.ResultsWithin the VQI database, the rate of T3EL in infrarenal EVAR during index hospitalization was 0.37% (n=157/41 604), of which 85% were due to midgraft separation and 15% were due to fabric disruptions. Out of the 157 index hospitalization T3ELs, 4.5% (n=7) received procedural reintervention during that hospitalization, which accounted for 1% of all index hospitalization reinterventions. During the 21-month follow-up, the rate of incident T3EL was 0.7% (n=205/26 422), which accounted for 5% of all endoleaks seen during follow-up. Reinterventions for incident T3EL at follow-up were done in 30 patients (rate 0.1%), which accounted for 9% of endoleak reinterventions and 3.3% of all reinterventions. The presence of incident T3EL found during follow-up was associated with a significant decrease in 5-year survival (74% vs 80%, respectively; p=0.041) in Kaplan-Meier analysis.ConclusionT3ELs rates at placement and follow-up remain low; however, the majority reported in long-term follow-up are incident and these incident endoleaks are associated with decreased survival in EVAR.

show abstract

“…Se han desarrollado iniciativas que valorizan la calidad de atención revisando los procesos, seguridad, eficiencia, costos y realizando sugerencias para mejorar los resultados en distintas intervenciones arteriales 89,90 La centralización del tratamiento de AAAR es considerada también una medida de calidad de atención con efecto positivo en la sobrevida 91,92 .…”

Section: Calidad De Atenciónunclassified

Concentración de la cirugía de aneurisma de aorta abdominal roto en centros especializados calificados

et al. 2022

View full text Add to dashboard Cite

Concentrating ruptured abdominal aortic aneurysm surgery in specialized centersRuptured abdominal aortic aneurysm (RAAA) is an arterial emergency with an overall mortality of 80%-90% secondary to massive hemorrhage. If a patient with RAAA presents in a primary hospital without resolution capacity, survival will depend on early transfer to a center with adequately trained specialists. This article reviews the evidence supporting the centralization of AAAR treatment in qualified centers, specifying the criteria used for the selection of referral centers and the role of a coordinating unit. Our current referral system, which is based primarily on costs, is also described. Patients with AAAR who consult in non-resolving centers should be rapidly transferred to a qualified referral center, following a transfer protocol, and guided by a coordinating unit acting according to technical and established criteria based on results, quality, and costs. Qualified referral centers should have an accredited vascular surgeon and a high institutional aortic surgery volume, adequate infrastructure, endovascular resolution capacity, support services (intensive care, hemodialysis, etc.) and specialized personnel permanently available.

show abstract

Utility of the Vascular Quality Initiative in improving quality of care in Canadian patients undergoing vascular surgery

Cited by 20 publications

References 12 publications

Machine Learning to Predict Outcomes of Endovascular Intervention for Patients With PAD

Machine Learning to Predict Outcomes of Endovascular Intervention for Patients With PAD

Occurrence and outcomes of type 3 endoleaks in endovascular aortic repair within the Vascular Quality Initiative database

Concentración de la cirugía de aneurisma de aorta abdominal roto en centros especializados calificados

Contact Info

Product

Resources

About