Jacob Nudel1,2, Andrew M Bishara3,4, Susanna W L de Geus1, Prasad Patil5, Jayakanth Srinivasan2, Donald T Hess1, Jonathan Woodson6. 1. Department of Surgery, Boston University School of Medicine, Boston, MA, USA. 2. Institute for Health System Innovation and Policy, Boston University, 601, 656 Beacon Street, Boston, MA, 02215, USA. 3. Department of Anesthesia, University of California, San Francisco, San Francisco, CA, USA. 4. Bakar Computational Health Sciences Institute, University of California San Francisco, San Francisco, CA, USA. 5. Department of Biostatistics, Boston University School of Public Health, Boston, MA, USA. 6. Institute for Health System Innovation and Policy, Boston University, 601, 656 Beacon Street, Boston, MA, 02215, USA. jwoodson@bu.edu.
Abstract
BACKGROUND: Postoperative gastrointestinal leak and venous thromboembolism (VTE) are devastating complications of bariatric surgery. The performance of currently available predictive models for these complications remains wanting, while machine learning has shown promise to improve on traditional modeling approaches. The purpose of this study was to compare the ability of two machine learning strategies, artificial neural networks (ANNs), and gradient boosting machines (XGBs) to conventional models using logistic regression (LR) in predicting leak and VTE after bariatric surgery. METHODS: ANN, XGB, and LR prediction models for leak and VTE among adults undergoing initial elective weight loss surgery were trained and validated using preoperative data from 2015 to 2017 from Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program database. Data were randomly split into training, validation, and testing populations. Model performance was measured by the area under the receiver operating characteristic curve (AUC) on the testing data for each model. RESULTS: The study cohort contained 436,807 patients. The incidences of leak and VTE were 0.70% and 0.46%. ANN (AUC 0.75, 95% CI 0.73-0.78) was the best-performing model for predicting leak, followed by XGB (AUC 0.70, 95% CI 0.68-0.72) and then LR (AUC 0.63, 95% CI 0.61-0.65, p < 0.001 for all comparisons). In detecting VTE, ANN, and XGB, LR achieved similar AUCs of 0.65 (95% CI 0.63-0.68), 0.67 (95% CI 0.64-0.70), and 0.64 (95% CI 0.61-0.66), respectively; the performance difference between XGB and LR was statistically significant (p = 0.001). CONCLUSIONS: ANN and XGB outperformed traditional LR in predicting leak. These results suggest that ML has the potential to improve risk stratification for bariatric surgery, especially as techniques to extract more granular data from medical records improve. Further studies investigating the merits of machine learning to improve patient selection and risk management in bariatric surgery are warranted.
BACKGROUND: Postoperative gastrointestinal leak and venous thromboembolism (VTE) are devastating complications of bariatric surgery. The performance of currently available predictive models for these complications remains wanting, while machine learning has shown promise to improve on traditional modeling approaches. The purpose of this study was to compare the ability of two machine learning strategies, artificial neural networks (ANNs), and gradient boosting machines (XGBs) to conventional models using logistic regression (LR) in predicting leak and VTE after bariatric surgery. METHODS: ANN, XGB, and LR prediction models for leak and VTE among adults undergoing initial elective weight loss surgery were trained and validated using preoperative data from 2015 to 2017 from Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program database. Data were randomly split into training, validation, and testing populations. Model performance was measured by the area under the receiver operating characteristic curve (AUC) on the testing data for each model. RESULTS: The study cohort contained 436,807 patients. The incidences of leak and VTE were 0.70% and 0.46%. ANN (AUC 0.75, 95% CI 0.73-0.78) was the best-performing model for predicting leak, followed by XGB (AUC 0.70, 95% CI 0.68-0.72) and then LR (AUC 0.63, 95% CI 0.61-0.65, p < 0.001 for all comparisons). In detecting VTE, ANN, and XGB, LR achieved similar AUCs of 0.65 (95% CI 0.63-0.68), 0.67 (95% CI 0.64-0.70), and 0.64 (95% CI 0.61-0.66), respectively; the performance difference between XGB and LR was statistically significant (p = 0.001). CONCLUSIONS: ANN and XGB outperformed traditional LR in predicting leak. These results suggest that ML has the potential to improve risk stratification for bariatric surgery, especially as techniques to extract more granular data from medical records improve. Further studies investigating the merits of machine learning to improve patient selection and risk management in bariatric surgery are warranted.
Authors: Ali Aminian; Amin Andalib; Zhamak Khorgami; Derrick Cetin; Bartolome Burguera; John Bartholomew; Stacy A Brethauer; Philip R Schauer Journal: Ann Surg Date: 2017-01 Impact factor: 12.969
Authors: Dana A Telem; Jie Yang; Maria Altieri; Wendy Patterson; Brittany Peoples; Hao Chen; Mark Talamini; Aurora D Pryor Journal: Ann Surg Date: 2016-05 Impact factor: 12.969
Authors: Jarrod D Frizzell; Li Liang; Phillip J Schulte; Clyde W Yancy; Paul A Heidenreich; Adrian F Hernandez; Deepak L Bhatt; Gregg C Fonarow; Warren K Laskey Journal: JAMA Cardiol Date: 2017-02-01 Impact factor: 14.676
Authors: Jun S Kim; Robert K Merrill; Varun Arvind; Deepak Kaji; Sara D Pasik; Chuma C Nwachukwu; Luilly Vargas; Nebiyu S Osman; Eric K Oermann; John M Caridi; Samuel K Cho Journal: Spine (Phila Pa 1976) Date: 2018-06-15 Impact factor: 3.241
Authors: Kevin A Chen; Chinmaya U Joisa; Karyn B Stitzenberg; Jonathan Stem; Jose G Guillem; Shawn M Gomez; Muneera R Kapadia Journal: J Gastrointest Surg Date: 2022-09-07 Impact factor: 3.267
Authors: Mustafa Bektaş; Beata M M Reiber; Jaime Costa Pereira; George L Burchell; Donald L van der Peet Journal: Obes Surg Date: 2022-06-17 Impact factor: 3.479
Authors: Kevin A Chen; Matthew E Berginski; Chirag S Desai; Jose G Guillem; Jonathan Stem; Shawn M Gomez; Muneera R Kapadia Journal: J Gastrointest Surg Date: 2022-05-04 Impact factor: 3.267
Authors: Robert T van Kooten; Renu R Bahadoer; Bouwdewijn Ter Buurkes de Vries; Michel W J M Wouters; Rob A E M Tollenaar; Henk H Hartgrink; Hein Putter; Johan L Dikken Journal: J Surg Oncol Date: 2022-05-03 Impact factor: 2.885