Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspective

Background: We have developed a model aimed at identifying preoperative predictors of operative mortality in patients who undergo elective, open thoracoabdominal aortic aneurysm (TAAA) repair. We converted this model into an intuitive nomogram to aid preoperative counseling. Methods: We retrospectiv...

Full description

Saved in:
Bibliographic Details
Main Authors: Kyle W. Blackburn, BS, Susan Y. Green, MPH, Allen Kuncheria, BA, Meng Li, PhD, Adel M. Hassan, BA, Brittany Rhoades, PhD, Scott A. Weldon, MA, Subhasis Chatterjee, MD, Marc R. Moon, MD, Scott A. LeMaire, MD, Joseph S. Coselli, MD
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:JTCVS Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S266627362400250X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122061934624768
author Kyle W. Blackburn, BS
Susan Y. Green, MPH
Allen Kuncheria, BA
Meng Li, PhD
Adel M. Hassan, BA
Brittany Rhoades, PhD
Scott A. Weldon, MA
Subhasis Chatterjee, MD
Marc R. Moon, MD
Scott A. LeMaire, MD
Joseph S. Coselli, MD
author_facet Kyle W. Blackburn, BS
Susan Y. Green, MPH
Allen Kuncheria, BA
Meng Li, PhD
Adel M. Hassan, BA
Brittany Rhoades, PhD
Scott A. Weldon, MA
Subhasis Chatterjee, MD
Marc R. Moon, MD
Scott A. LeMaire, MD
Joseph S. Coselli, MD
author_sort Kyle W. Blackburn, BS
collection DOAJ
description Background: We have developed a model aimed at identifying preoperative predictors of operative mortality in patients who undergo elective, open thoracoabdominal aortic aneurysm (TAAA) repair. We converted this model into an intuitive nomogram to aid preoperative counseling. Methods: We retrospectively analyzed data from 2884 elective, open TAAA repairs performed between 1986 and 2023 in a single practice. Using clinical and selected operative variables, we built 4 predictive models: multivariable logistic regression (MLR), random forest, support vector machine, and gradient boosting machine. Each model’s predictive effectiveness was evaluated with the C-statistic. Test C-statistics were computed using an 80:20 cross-validation scheme with 1000 iterations. Results: Operative death occurred in 200 patients (6.9%). Test set C-statistics showed that the MLR model (median, 0.68; interquartile range [IQR], 0.65-0.71) outperformed the machine learning models (0.61 [IQR, 0.59-0.64] for random forest; 0.61 [IQR, 0.58-0.64] for support vector machine; 0.65 [IQR, 0.62-0.67] for gradient boosting machine). The final MLR model was based on 7 characteristics: increasing age (odds ratio [OR], 1.04/y; P < .001), cerebrovascular disease (OR, 1.54; P = .01), chronic kidney disease (OR, 1.53; P = .008), symptomatic aneurysm (OR, 1.42; P = .02), and Crawford extent I (OR, 0.66; P = .08), extent II (OR, 1.61; P = .01), and extent IV (OR, 0.41; P = .002). We converted this model into a nomogram. Conclusions: Using institutional data, we evaluated several models to predict operative mortality in elective TAAA repair, using information available to surgeons preoperatively. We then converted the best predictive model, the MLR model, into an intuitive nomogram to aid patient counseling.
format Article
id doaj-art-33c7d2d6d8a04050a4338be9194d6c75
institution Kabale University
issn 2666-2736
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series JTCVS Open
spelling doaj-art-33c7d2d6d8a04050a4338be9194d6c752024-12-15T06:16:55ZengElsevierJTCVS Open2666-27362024-12-012295103Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspectiveKyle W. Blackburn, BS0Susan Y. Green, MPH1Allen Kuncheria, BA2Meng Li, PhD3Adel M. Hassan, BA4Brittany Rhoades, PhD5Scott A. Weldon, MA6Subhasis Chatterjee, MD7Marc R. Moon, MD8Scott A. LeMaire, MD9Joseph S. Coselli, MD10Division of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Office of Surgical Research, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TexDepartment of Statistics, Rice University, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Office of Surgical Research, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Department of Cardiovascular Surgery, The Texas Heart Institute, Houston, Tex; Department of Cardiovascular Surgery, CHI St Luke’s Health–Baylor St Luke’s Medical Center, Houston, Tex; Cardiovascular Research Institute, Baylor College of Medicine, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Department of Cardiovascular Surgery, The Texas Heart Institute, Houston, Tex; Department of Cardiovascular Surgery, CHI St Luke’s Health–Baylor St Luke’s Medical Center, Houston, Tex; Cardiovascular Research Institute, Baylor College of Medicine, Houston, TexDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Research Institute and Heart &amp; Vascular Institute, Geisinger, Danville, PaDivision of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Tex; Department of Cardiovascular Surgery, The Texas Heart Institute, Houston, Tex; Department of Cardiovascular Surgery, CHI St Luke’s Health–Baylor St Luke’s Medical Center, Houston, Tex; Cardiovascular Research Institute, Baylor College of Medicine, Houston, Tex; Address for reprints: Joseph S. Coselli, MD, Division of Cardiothoracic Surgery, Michael E. DeBakey Department of Surgery, Baylor College of Medicine, One Baylor Plaza, BCM 390, Houston, TX 77030.Background: We have developed a model aimed at identifying preoperative predictors of operative mortality in patients who undergo elective, open thoracoabdominal aortic aneurysm (TAAA) repair. We converted this model into an intuitive nomogram to aid preoperative counseling. Methods: We retrospectively analyzed data from 2884 elective, open TAAA repairs performed between 1986 and 2023 in a single practice. Using clinical and selected operative variables, we built 4 predictive models: multivariable logistic regression (MLR), random forest, support vector machine, and gradient boosting machine. Each model’s predictive effectiveness was evaluated with the C-statistic. Test C-statistics were computed using an 80:20 cross-validation scheme with 1000 iterations. Results: Operative death occurred in 200 patients (6.9%). Test set C-statistics showed that the MLR model (median, 0.68; interquartile range [IQR], 0.65-0.71) outperformed the machine learning models (0.61 [IQR, 0.59-0.64] for random forest; 0.61 [IQR, 0.58-0.64] for support vector machine; 0.65 [IQR, 0.62-0.67] for gradient boosting machine). The final MLR model was based on 7 characteristics: increasing age (odds ratio [OR], 1.04/y; P < .001), cerebrovascular disease (OR, 1.54; P = .01), chronic kidney disease (OR, 1.53; P = .008), symptomatic aneurysm (OR, 1.42; P = .02), and Crawford extent I (OR, 0.66; P = .08), extent II (OR, 1.61; P = .01), and extent IV (OR, 0.41; P = .002). We converted this model into a nomogram. Conclusions: Using institutional data, we evaluated several models to predict operative mortality in elective TAAA repair, using information available to surgeons preoperatively. We then converted the best predictive model, the MLR model, into an intuitive nomogram to aid patient counseling.http://www.sciencedirect.com/science/article/pii/S266627362400250Xaortic aneurysmoperative mortalityclinical decision rulesprognosisnomogramspatient counseling
spellingShingle Kyle W. Blackburn, BS
Susan Y. Green, MPH
Allen Kuncheria, BA
Meng Li, PhD
Adel M. Hassan, BA
Brittany Rhoades, PhD
Scott A. Weldon, MA
Subhasis Chatterjee, MD
Marc R. Moon, MD
Scott A. LeMaire, MD
Joseph S. Coselli, MD
Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspective
JTCVS Open
aortic aneurysm
operative mortality
clinical decision rules
prognosis
nomograms
patient counseling
title Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspective
title_full Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspective
title_fullStr Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspective
title_full_unstemmed Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspective
title_short Predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repairCentral MessagePerspective
title_sort predicting operative mortality in patients who undergo elective open thoracoabdominal aortic aneurysm repaircentral messageperspective
topic aortic aneurysm
operative mortality
clinical decision rules
prognosis
nomograms
patient counseling
url http://www.sciencedirect.com/science/article/pii/S266627362400250X
work_keys_str_mv AT kylewblackburnbs predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT susanygreenmph predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT allenkuncheriaba predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT mengliphd predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT adelmhassanba predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT brittanyrhoadesphd predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT scottaweldonma predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT subhasischatterjeemd predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT marcrmoonmd predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT scottalemairemd predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective
AT josephscosellimd predictingoperativemortalityinpatientswhoundergoelectiveopenthoracoabdominalaorticaneurysmrepaircentralmessageperspective