{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:41:24Z","timestamp":1790109684217,"version":"4.0.1"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:00:00Z","timestamp":1668988800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Predicting 30-day procedure-related mortality risk and 30-day unplanned readmission in patients undergoing lower extremity endovascular interventions for peripheral artery disease (PAD) may assist in improving patient outcomes. Risk prediction of 30-day mortality can help clinicians identify treatment plans to reduce the risk of death, and prediction of 30-day unplanned readmission may improve outcomes by identifying patients who may benefit from readmission prevention strategies. The goal of this study is to develop machine learning models to stratify risk of 30-day procedure-related mortality and 30-day unplanned readmission in patients undergoing lower extremity infra-inguinal endovascular interventions. We used a cohort of 14,444 cases from the American College of Surgeons National Surgical Quality Improvement Program database. For each outcome, we developed and evaluated multiple machine learning models, including Support Vector Machines, Multilayer Perceptrons, and Gradient Boosting Machines, and selected a random forest as the best-performing model for both outcomes. Our 30-day procedure-related mortality model achieved an AUC of 0.75 (95% CI: 0.71\u20130.79) and our 30-day unplanned readmission model achieved an AUC of 0.68 (95% CI: 0.67\u20130.71). Stratification of the test set by race (white and non-white), sex (male and female), and age (\u226565 years and &lt;65 years) and subsequent evaluation of demographic parity by AUC shows that both models perform equally well across race, sex, and age groups. We interpret the model globally and locally using Gini impurity and SHapley Additive exPlanations (SHAP). Using the top five predictors for death and mortality, we demonstrate differences in survival for subgroups stratified by these predictors, which underscores the utility of our model.<\/jats:p>","DOI":"10.1371\/journal.pone.0277507","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T13:39:39Z","timestamp":1669037979000},"page":"e0277507","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":21,"title":["Risk stratification with explainable machine learning for 30-day procedure-related mortality and 30-day unplanned readmission in patients with peripheral arterial disease"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9642-653X","authenticated-orcid":true,"given":"Meredith","family":"Cox","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. C.","family":"Panagides","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Azadeh","family":"Tabari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjeeva","family":"Kalva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayashree","family":"Kalpathy-Cramer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dania","family":"Daye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,11,21]]},"reference":[{"issue":"8","key":"pone.0277507.ref001","doi-asserted-by":"crossref","first-page":"e1020","DOI":"10.1016\/S2214-109X(19)30255-4","article-title":"Global, regional, and national prevalence and risk factors for peripheral artery disease in 2015: an updated systematic review and analysis","volume":"7","author":"P Song","year":"2019","journal-title":"Lancet Glob Health"},{"issue":"1","key":"pone.0277507.ref002","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1161\/CIRCULATIONAHA.110.003954","article-title":"Secondary Prevention and Mortality in Peripheral Artery Disease","volume":"124","author":"RL Pande","year":"2011","journal-title":"Circulation"},{"issue":"4","key":"pone.0277507.ref003","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1016\/j.ejvs.2018.01.019","article-title":"Ten Year Mortality in Different Peripheral Arterial Disease Stages: A Population Based Observational Study on Outcome","volume":"55","author":"F Sartipy","year":"2018","journal-title":"Eur J Vasc Endovasc Surg Off J Eur Soc Vasc Surg"},{"issue":"3","key":"pone.0277507.ref004","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1016\/j.jvs.2017.01.061","article-title":"Regional variation in outcomes for lower extremity vascular disease in the Vascular Quality Initiative","volume":"66","author":"PA Soden","year":"2017","journal-title":"J Vasc Surg"},{"issue":"2","key":"pone.0277507.ref005","doi-asserted-by":"crossref","first-page":"93","DOI":"10.7326\/M17-1058","article-title":"Readmissions After Revascularization Procedures for Peripheral Arterial Disease: A Nationwide Cohort Study","volume":"168","author":"EA Secemsky","year":"2018","journal-title":"Ann Intern Med"},{"key":"pone.0277507.ref006","unstructured":"A Randomized Trial of a Telephone Care-Management Strategy | NEJM [Internet]. [cited 2022 Feb 17]. Available from: https:\/\/www.nejm.org\/doi\/full\/10.1056\/NEJMsa0902321."},{"issue":"6","key":"pone.0277507.ref007","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1097\/JHQ.0000000000000057","article-title":"Meta-Analysis of Clinical Trials That Evaluate the Effectiveness of Hospital-Initiated Postdischarge Interventions on Hospital Readmission","volume":"39","author":"PM Branowicki","year":"2017","journal-title":"J Healthc Qual JHQ"},{"issue":"4","key":"pone.0277507.ref008","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1161\/CIRCOUTCOMES.111.000101","article-title":"Hospital Strategies Associated with 30-Day Readmission Rates for Patients with Heart Failure.","volume":"6","author":"EH Bradley","year":"2013","journal-title":"Circ Cardiovasc Qual Outcomes"},{"issue":"18","key":"pone.0277507.ref009","doi-asserted-by":"crossref","first-page":"1190","DOI":"10.1056\/NEJM199511023331806","article-title":"A multidisciplinary intervention to prevent the readmission of elderly patients with congestive heart failure","volume":"333","author":"MW Rich","year":"1995","journal-title":"N Engl J Med"},{"issue":"3","key":"pone.0277507.ref010","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1016\/j.jvs.2019.01.079","article-title":"A systematic review and meta-analysis of risk factors for and incidence of 30-day readmission after revascularization for peripheral artery disease","volume":"70","author":"SL Smith","year":"2019","journal-title":"J Vasc Surg"},{"issue":"6","key":"pone.0277507.ref011","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1016\/j.jvs.2016.12.121","article-title":"Unplanned return to operating room after lower extremity endovascular intervention is an independent predictor for hospital readmission","volume":"65","author":"TZ Ali","year":"2017","journal-title":"J Vasc Surg"},{"issue":"2","key":"pone.0277507.ref012","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1016\/j.jvs.2016.08.093","article-title":"Risk factors for 30-day unplanned readmission following infrainguinal endovascular interventions","volume":"65","author":"TCF Bodewes","year":"2017","journal-title":"J Vasc Surg"},{"issue":"2","key":"pone.0277507.ref013","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.jvs.2014.02.059","article-title":"Predictive scoring model of mortality after surgical or endovascular revascularization in patients with critical limb ischemia","volume":"60","author":"T Shiraki","year":"2014","journal-title":"J Vasc Surg"},{"issue":"4","key":"pone.0277507.ref014","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1016\/j.jvs.2007.05.060","article-title":"Clinical factors associated with long-term mortality following vascular surgery: Outcomes from The Coronary Artery Revascularization Prophylaxis (CARP) Trial.","volume":"46","author":"EO McFalls","year":"2007","journal-title":"J Vasc Surg"},{"issue":"4","key":"pone.0277507.ref015","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Statistics versus machine learning","volume":"15","author":"D Bzdok","year":"2018","journal-title":"Nat Methods"},{"issue":"9","key":"pone.0277507.ref016","doi-asserted-by":"crossref","first-page":"455","DOI":"10.3390\/medicina56090455","article-title":"Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment","volume":"56","author":"HSR Rajula","year":"2020","journal-title":"Medicina (Mex)."},{"key":"pone.0277507.ref017","unstructured":"K190896.pdf [Internet]. [cited 2022 Jul 20]. Available from: https:\/\/www.accessdata.fda.gov\/cdrh_docs\/pdf19\/K190896.pdf."},{"key":"pone.0277507.ref018","unstructured":"K221314.pdf [Internet]. [cited 2022 Jul 20]. Available from: https:\/\/www.accessdata.fda.gov\/cdrh_docs\/pdf22\/K221314.pdf."},{"key":"pone.0277507.ref019","unstructured":"K221219.pdf [Internet]. [cited 2022 Jul 20]. Available from: https:\/\/www.accessdata.fda.gov\/cdrh_docs\/pdf22\/K221219.pdf."},{"issue":"2","key":"pone.0277507.ref020","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.jamcollsurg.2009.10.021","article-title":"Missing Data in the American College of Surgeons National Surgical Quality Improvement Program Are Not Missing at Random: Implications and Potential Impact on Quality Assessments.","volume":"210","author":"BH Hamilton","year":"2010","journal-title":"J Am Coll Surg"},{"issue":"196","key":"pone.0277507.ref021","first-page":"1","article-title":"From Predictive Methods to Missing Data Imputation: An Optimization Approach.","volume":"18","author":"D Bertsimas","year":"2018","journal-title":"J Mach Learn Res"},{"key":"pone.0277507.ref022","doi-asserted-by":"crossref","first-page":"022022","DOI":"10.1088\/1742-6596\/1168\/2\/022022","article-title":"An Overview of Overfitting and its Solutions","volume":"1168","author":"X. Ying","year":"2019","journal-title":"J Phys Conf Ser"},{"issue":"8","key":"pone.0277507.ref023","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy","volume":"27","author":"H Peng","year":"2005","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0277507.ref024","article-title":"A Review of Class Imbalance Problem. undefined [Internet].","author":"SMA Elrahman","year":"2014"},{"key":"pone.0277507.ref025","unstructured":"He H, Bai Y, Garcia EA, Li S. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence). 2008. p. 1322\u20138."},{"key":"pone.0277507.ref026","volume-title":"In: Advances in Neural Information Processing Systems [Internet].","author":"SM Lundberg","year":"2017"},{"issue":"3","key":"pone.0277507.ref027","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach","volume":"44","author":"ER DeLong","year":"1988","journal-title":"Biometrics"},{"issue":"1","key":"pone.0277507.ref028","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S+ to analyze and compare ROC curves.","volume":"12","author":"X Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"issue":"4","key":"pone.0277507.ref029","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1097\/SLA.0000000000002706","article-title":"MySurgeryRisk: Development and Validation of a Machine-Learning Risk Algorithm for Major Complications and Death after Surgery","volume":"269","author":"A Bihorac","year":"2019","journal-title":"Ann Surg"},{"issue":"6","key":"pone.0277507.ref030","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1001\/jamacardio.2021.0122","article-title":"Use of Machine Learning Models to Predict Death After Acute Myocardial Infarction","volume":"6","author":"R Khera","year":"2021","journal-title":"JAMA Cardiol"},{"issue":"7","key":"pone.0277507.ref031","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1513\/AnnalsATS.201710-787OC","article-title":"Predicting Intensive Care Unit Readmission with Machine Learning Using Electronic Health Record Data","volume":"15","author":"JC Rojas","year":"2018","journal-title":"Ann Am Thorac Soc"},{"issue":"1","key":"pone.0277507.ref032","doi-asserted-by":"crossref","first-page":"2362","DOI":"10.1038\/s41598-019-39071-y","article-title":"Predictive Modeling of the Hospital Readmission Risk from Patients\u2019 Claims Data Using Machine Learning: A Case Study on COPD","volume":"9","author":"X Min","year":"2019","journal-title":"Sci Rep."},{"issue":"6","key":"pone.0277507.ref033","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1161\/CIRCOUTCOMES.116.003039","article-title":"Analysis of Machine Learning Techniques for Heart Failure Readmissions.","volume":"9","author":"BJ Mortazavi","year":"2016","journal-title":"Circ Cardiovasc Qual Outcomes"},{"issue":"1","key":"pone.0277507.ref034","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1038\/s41591-018-0307-0","article-title":"The practical implementation of artificial intelligence technologies in medicine","volume":"25","author":"J He","year":"2019","journal-title":"Nat Med"},{"issue":"6","key":"pone.0277507.ref035","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1056\/NEJM199202063260605","article-title":"Mortality over a period of 10 years in patients with peripheral arterial disease","volume":"326","author":"MH Criqui","year":"1992","journal-title":"N Engl J Med"},{"issue":"6","key":"pone.0277507.ref036","doi-asserted-by":"crossref","first-page":"2246","DOI":"10.1161\/01.CIR.82.6.2246","article-title":"Peripheral arterial disease and subsequent cardiovascular mortality. A strong and consistent association","volume":"82","author":"MH Criqui","year":"1990","journal-title":"Circulation"},{"issue":"1","key":"pone.0277507.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jss.2012.02.048","article-title":"Preoperative risk stratification for thoracic surgery using the American College of Surgeons National Surgical Quality Improvement Program data set: functional status predicts morbidity and mortality","volume":"177","author":"A Tsiouris","year":"2012","journal-title":"J Surg Res"},{"issue":"12","key":"pone.0277507.ref038","doi-asserted-by":"crossref","first-page":"e0207883","DOI":"10.1371\/journal.pone.0207883","article-title":"Decreased preoperative functional status is associated with increased mortality following coronary artery bypass graft surgery","volume":"13","author":"H Ko","year":"2018","journal-title":"PLOS ONE"},{"issue":"5","key":"pone.0277507.ref039","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.1007\/s00464-012-2678-5","article-title":"Perioperative risk factors for 30-day mortality after bariatric surgery: is functional status important?","volume":"27","author":"MA Khan","year":"2013","journal-title":"Surg Endosc"},{"issue":"11","key":"pone.0277507.ref040","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1111\/ctr.12808","article-title":"Functional status predicts postoperative mortality after liver transplantation","volume":"30","author":"NH Dolgin","year":"2016","journal-title":"Clin Transplant"},{"issue":"3","key":"pone.0277507.ref041","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.jamcollsurg.2012.05.024","article-title":"Risk Factors for 30-Day Hospital Readmission among General Surgery Patients.","volume":"215","author":"MT Kassin","year":"2012","journal-title":"J Am Coll Surg"},{"issue":"1","key":"pone.0277507.ref042","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.jvs.2016.02.024","article-title":"Drivers of readmissions in vascular surgery patients","volume":"64","author":"NO Glebova","year":"2016","journal-title":"J Vasc Surg"},{"issue":"11","key":"pone.0277507.ref043","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1001\/jamainternmed.2018.3763","article-title":"Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data.","volume":"178","author":"MA Gianfrancesco","year":"2018","journal-title":"JAMA Intern Med"},{"issue":"11","key":"pone.0277507.ref044","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1056\/NEJMp1714229","article-title":"Implementing Machine Learning in Health Care\u2014Addressing Ethical Challenges","volume":"378","author":"DS Char","year":"2018","journal-title":"N Engl J Med"},{"issue":"12","key":"pone.0277507.ref045","doi-asserted-by":"crossref","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring Fairness in Machine Learning to Advance Health Equity","volume":"169","author":"A Rajkomar","year":"2018","journal-title":"Ann Intern Med"},{"key":"pone.0277507.ref046","article-title":"Inherent Trade-Offs in the Fair Determination of Risk Scores.","author":"J Kleinberg","year":"2016","journal-title":"ArXiv160905807 Cs Stat [Internet]."},{"issue":"5","key":"pone.0277507.ref047","doi-asserted-by":"crossref","first-page":"e221","DOI":"10.1016\/S2589-7500(20)30065-0","article-title":"Ethical limitations of algorithmic fairness solutions in health care machine learning","volume":"2","author":"MD McCradden","year":"2020","journal-title":"Lancet Digit Health"},{"issue":"9","key":"pone.0277507.ref048","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1038\/s41591-019-0548-6","article-title":"Do no harm: a roadmap for responsible machine learning for health care","volume":"25","author":"J Wiens","year":"2019","journal-title":"Nat Med"},{"issue":"5","key":"pone.0277507.ref049","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1080\/15265161.2021.2013977","article-title":"A Research Ethics Framework for the Clinical Translation of Healthcare Machine Learning.","volume":"22","author":"MD McCradden","year":"2022","journal-title":"Am J Bioeth"},{"issue":"5","key":"pone.0277507.ref050","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.1016\/j.surg.2016.04.034","article-title":"Evaluation of hospitals participating in the American College of Surgeons National Surgical Quality Improvement Program","volume":"160","author":"CR Sheils","year":"2016","journal-title":"Surgery"},{"issue":"10","key":"pone.0277507.ref051","doi-asserted-by":"crossref","first-page":"2467","DOI":"10.1002\/sim.8915","article-title":"Selecting the model for multiple imputation of missing data: Just use an IC!","volume":"40","author":"F Noghrehchi","year":"2021","journal-title":"Stat Med"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0277507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T13:40:27Z","timestamp":1669038027000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0277507"}},"subtitle":[],"editor":[{"given":"Tze-Woei","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,11,21]]},"references-count":51,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,11,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0277507","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,21]]}}}