학술논문
Machine Learning to Predict Outcomes of Endovascular Intervention for Patients With PAD.
Document Type
Academic Journal
Author
Li B; Department of Surgery, University of Toronto, Toronto, Ontario, Canada.; Division of Vascular Surgery, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Institute of Medical Science, University of Toronto, Toronto, Ontario, Canada.; Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, Ontario, Canada.; Warren BE; Division of Vascular and Interventional Radiology, Department of Medical Imaging, University of Toronto, Toronto, Ontario, Canada.; Eisenberg N; Division of Vascular Surgery, Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada.; Beaton D; Data Science & Advanced Analytics, Unity Health Toronto, University of Toronto, Toronto, Ontario, Canada.; Lee DS; Division of Cardiology, Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada.; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.; ICES, University of Toronto, Toronto, Ontario, Canada.; Aljabri B; Department of Surgery, King Saud University, Riyadh, Kingdom of Saudi Arabia.; Verma R; School of Medicine, Royal College of Surgeons in Ireland, University of Medicine and Health Sciences, Dublin, Ireland.; Wijeysundera DN; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.; ICES, University of Toronto, Toronto, Ontario, Canada.; Department of Anesthesia, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Li Ka Shing Knowledge Institute, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Rotstein OD; Department of Surgery, University of Toronto, Toronto, Ontario, Canada.; Institute of Medical Science, University of Toronto, Toronto, Ontario, Canada.; Li Ka Shing Knowledge Institute, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Division of General Surgery, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; de Mestral C; Department of Surgery, University of Toronto, Toronto, Ontario, Canada.; Division of Vascular Surgery, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.; ICES, University of Toronto, Toronto, Ontario, Canada.; Li Ka Shing Knowledge Institute, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Mamdani M; Institute of Medical Science, University of Toronto, Toronto, Ontario, Canada.; Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, Ontario, Canada.; Data Science & Advanced Analytics, Unity Health Toronto, University of Toronto, Toronto, Ontario, Canada.; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.; ICES, University of Toronto, Toronto, Ontario, Canada.; Li Ka Shing Knowledge Institute, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Leslie Dan Faculty of Pharmacy, University of Toronto, Toronto, Ontario, Canada.; Roche-Nagle G; Department of Surgery, University of Toronto, Toronto, Ontario, Canada.; Division of Vascular and Interventional Radiology, Department of Medical Imaging, University of Toronto, Toronto, Ontario, Canada.; Division of Vascular Surgery, Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada.; Al-Omran M; Department of Surgery, University of Toronto, Toronto, Ontario, Canada.; Division of Vascular Surgery, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Institute of Medical Science, University of Toronto, Toronto, Ontario, Canada.; Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, Ontario, Canada.; Li Ka Shing Knowledge Institute, St Michael's Hospital, Unity Health Toronto, Toronto, Ontario, Canada.; Department of Surgery, King Faisal Specialist Hospital and Research Center, Riyadh, Kingdom of Saudi Arabia.
Source
Publisher: American Medical Association Country of Publication: United States NLM ID: 101729235 Publication Model: Electronic Cited Medium: Internet ISSN: 2574-3805 (Electronic) Linking ISSN: 25743805 NLM ISO Abbreviation: JAMA Netw Open Subsets: MEDLINE
Subject
Language
English
Abstract
Importance: Endovascular intervention for peripheral artery disease (PAD) carries nonnegligible perioperative risks; however, outcome prediction tools are limited.
Objective: To develop machine learning (ML) algorithms that can predict outcomes following endovascular intervention for PAD.
Design, Setting, and Participants: This 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.
Exposures: A 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 Measures: Using 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.
Results: Overall, 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 Relevance: In 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.
Objective: To develop machine learning (ML) algorithms that can predict outcomes following endovascular intervention for PAD.
Design, Setting, and Participants: This 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.
Exposures: A 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 Measures: Using 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.
Results: Overall, 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 Relevance: In 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.