Azra Bihorac1,2, Tezcan Ozrazgat-Baslanti1,2, Ashkan Ebadi1,2, Amir Motaei1,2, Mohcine Madkour1,2, Panagote M Pardalos3,2, Gloria Lipori4, William R Hogan5,2, Philip A Efron6, Frederick Moore6, Lyle L Moldawer6, Daisy Zhe Wang7,2, Charles E Hobson8,9, Parisa Rashidi10,2, Xiaolin Li11,2, Petar Momcilovic3,2. 1. Department of Medicine, College of Medicine, University of Florida, Gainesville, FL. 2. Precision and Intelligent Systems in Medicine (PRISMA), University of Florida, Gainesville, FL. 3. Department of Industrial and Systems Engineering, College of Engineering, UF. 4. University of Florida Health, UF. 5. Department of Health Outcomes and Policy, UF. 6. Department of Surgery, College of Medicine, UF. 7. Department of Computer and Information Science and Engineering, College of Engineering, UF. 8. Department of Health Services Research, Management and Policy, UF. 9. Department of Surgery, Malcom Randall VAMC, Gainesville, FL. 10. Department of Biomedical Engineering, College of Engineering, UF. 11. Department of Electrical and Computer Engineering, College of Engineering, UF.
Abstract
OBJECTIVE: To accurately calculate the risk for postoperative complications and death after surgery in the preoperative period using machine-learning modeling of clinical data. BACKGROUND: Postoperative complications cause a 2-fold increase in the 30-day mortality and cost, and are associated with long-term consequences. The ability to precisely forecast the risk for major complications before surgery is limited. METHODS: In a single-center cohort of 51,457 surgical patients undergoing major inpatient surgery, we have developed and validated an automated analytics framework for a preoperative risk algorithm (MySurgeryRisk) that uses existing clinical data in electronic health records to forecast patient-level probabilistic risk scores for 8 major postoperative complications (acute kidney injury, sepsis, venous thromboembolism, intensive care unit admission >48 hours, mechanical ventilation >48 hours, wound, neurologic, and cardiovascular complications) and death up to 24 months after surgery. We used the area under the receiver characteristic curve (AUC) and predictiveness curves to evaluate model performance. RESULTS: MySurgeryRisk calculates probabilistic risk scores for 8 postoperative complications with AUC values ranging between 0.82 and 0.94 [99% confidence intervals (CIs) 0.81-0.94]. The model predicts the risk for death at 1, 3, 6, 12, and 24 months with AUC values ranging between 0.77 and 0.83 (99% CI 0.76-0.85). CONCLUSIONS: We constructed an automated predictive analytics framework for machine-learning algorithm with high discriminatory ability for assessing the risk of surgical complications and death using readily available preoperative electronic health records data. The feasibility of this novel algorithm implemented in real time clinical workflow requires further testing.
OBJECTIVE: To accurately calculate the risk for postoperative complications and death after surgery in the preoperative period using machine-learning modeling of clinical data. BACKGROUND: Postoperative complications cause a 2-fold increase in the 30-day mortality and cost, and are associated with long-term consequences. The ability to precisely forecast the risk for major complications before surgery is limited. METHODS: In a single-center cohort of 51,457 surgical patients undergoing major inpatient surgery, we have developed and validated an automated analytics framework for a preoperative risk algorithm (MySurgeryRisk) that uses existing clinical data in electronic health records to forecast patient-level probabilistic risk scores for 8 major postoperative complications (acute kidney injury, sepsis, venous thromboembolism, intensive care unit admission >48 hours, mechanical ventilation >48 hours, wound, neurologic, and cardiovascular complications) and death up to 24 months after surgery. We used the area under the receiver characteristic curve (AUC) and predictiveness curves to evaluate model performance. RESULTS: MySurgeryRisk calculates probabilistic risk scores for 8 postoperative complications with AUC values ranging between 0.82 and 0.94 [99% confidence intervals (CIs) 0.81-0.94]. The model predicts the risk for death at 1, 3, 6, 12, and 24 months with AUC values ranging between 0.77 and 0.83 (99% CI 0.76-0.85). CONCLUSIONS: We constructed an automated predictive analytics framework for machine-learning algorithm with high discriminatory ability for assessing the risk of surgical complications and death using readily available preoperative electronic health records data. The feasibility of this novel algorithm implemented in real time clinical workflow requires further testing.
Authors: Margaret S Pepe; Ziding Feng; Ying Huang; Gary Longton; Ross Prentice; Ian M Thompson; Yingye Zheng Journal: Am J Epidemiol Date: 2007-11-02 Impact factor: 4.897
Authors: Patrick Meybohm; Berthold Bein; Oana Brosteanu; Jochen Cremer; Matthias Gruenewald; Christian Stoppe; Mark Coburn; Gereon Schaelte; Andreas Böning; Bernd Niemann; Jan Roesner; Frank Kletzin; Ulrich Strouhal; Christian Reyher; Rita Laufenberg-Feldmann; Marion Ferner; Ivo F Brandes; Martin Bauer; Sebastian N Stehr; Andreas Kortgen; Maria Wittmann; Georg Baumgarten; Tanja Meyer-Treschan; Peter Kienbaum; Matthias Heringlake; Julika Schön; Michael Sander; Sascha Treskatsch; Thorsten Smul; Ewa Wolwender; Thomas Schilling; Georg Fuernau; Dirk Hasenclever; Kai Zacharowski Journal: N Engl J Med Date: 2015-10-05 Impact factor: 91.245
Authors: Alexander Zarbock; Christoph Schmidt; Hugo Van Aken; Carola Wempe; Sven Martens; Peter K Zahn; Britta Wolf; Ulrich Goebel; Christian I Schwer; Peter Rosenberger; Helene Haeberle; Dennis Görlich; John A Kellum; Melanie Meersch Journal: JAMA Date: 2015-06-02 Impact factor: 56.272
Authors: Katherine R Courtright; Corey Chivers; Michael Becker; Susan H Regli; Linnea C Pepper; Michael E Draugelis; Nina R O'Connor Journal: J Gen Intern Med Date: 2019-07-16 Impact factor: 5.128
Authors: Tyler J Loftus; Patrick J Tighe; Amanda C Filiberto; Philip A Efron; Scott C Brakenridge; Alicia M Mohr; Parisa Rashidi; Gilbert R Upchurch; Azra Bihorac Journal: JAMA Surg Date: 2020-02-01 Impact factor: 14.766
Authors: Alan H Morris; Brian Stagg; Michael Lanspa; James Orme; Terry P Clemmer; Lindell K Weaver; Frank Thomas; Colin K Grissom; Ellie Hirshberg; Thomas D East; Carrie Jane Wallace; Michael P Young; Dean F Sittig; Antonio Pesenti; Michela Bombino; Eduardo Beck; Katherine A Sward; Charlene Weir; Shobha S Phansalkar; Gordon R Bernard; B Taylor Thompson; Roy Brower; Jonathon D Truwit; Jay Steingrub; R Duncan Hite; Douglas F Willson; Jerry J Zimmerman; Vinay M Nadkarni; Adrienne Randolph; Martha A Q Curley; Christopher J L Newth; Jacques Lacroix; Michael S D Agus; Kang H Lee; Bennett P deBoisblanc; R Scott Evans; Dean K Sorenson; Anthony Wong; Michael V Boland; David W Grainger; Willard H Dere; Alan S Crandall; Julio C Facelli; Stanley M Huff; Peter J Haug; Ulrike Pielmeier; Stephen E Rees; Dan S Karbing; Steen Andreassen; Eddy Fan; Roberta M Goldring; Kenneth I Berger; Beno W Oppenheimer; E Wesley Ely; Ognjen Gajic; Brian Pickering; David A Schoenfeld; Irena Tocino; Russell S Gonnering; Peter J Pronovost; Lucy A Savitz; Didier Dreyfuss; Arthur S Slutsky; James D Crapo; Derek Angus; Michael R Pinsky; Brent James; Donald Berwick Journal: J Am Med Inform Assoc Date: 2021-06-12 Impact factor: 4.497
Authors: Khodayar Goshtasbi; Tyler M Yasaka; Mehdi Zandi-Toghani; Hamid R Djalilian; William B Armstrong; Tjoson Tjoa; Yarah M Haidar; Mehdi Abouzari Journal: Head Neck Date: 2020-11-03 Impact factor: 3.147