V Lin1, A Tsouchnika2, E Allakhverdiiev2, A W Rosen2, M Gögenur2, J S R Clausen2, K B Bräuner2, J S Walbech2, P Rijnbeek3, I Drakos2, I Gögenur2. 1. Center for Surgical Science, Department of Surgery, Zealand University Hospital Køge, Lykkebækvej 1, 4600, Køge, Denmark. vial@regionsjaelland.dk. 2. Center for Surgical Science, Department of Surgery, Zealand University Hospital Køge, Lykkebækvej 1, 4600, Køge, Denmark. 3. Department of Medical Informatics, Erasmus University Medical Centre, Rotterdam, The Netherlands.
Abstract
BACKGROUND: The occurrence of postoperative complications and anastomotic leakage are major drivers of mortality in the immediate phase after colorectal cancer surgery. We trained prediction models for calculating patients' individual risk of complications based only on preoperatively available data in a multidisciplinary team setting. Knowing prior to surgery the probability of developing a complication could aid in improving informed decision-making by surgeon and patient and individualize surgical treatment trajectories. METHODS: All patients over 18 years of age undergoing any resection for colorectal cancer between January 1, 2014 and December 31, 2019 from the nationwide Danish Colorectal Cancer Group database were included. Data from the database were converted into Observational Medical Outcomes Partnership Common Data Model maintained by the Observation Health Data Science and Informatics initiative. Multiple machine learning models were trained to predict postoperative complications of Clavien-Dindo grade ≥ 3B and anastomotic leakage within 30 days after surgery. RESULTS: Between 2014 and 2019, 23,907 patients underwent resection for colorectal cancer in Denmark. A Clavien-Dindo complication grade ≥ 3B occurred in 2,958 patients (12.4%). Of 17,190 patients that received an anastomosis, 929 experienced anastomotic leakage (5.4%). Among the compared machine learning models, Lasso Logistic Regression performed best. The predictive model for complications had an area under the receiver operating characteristic curve (AUROC) of 0.704 (95%CI 0.683-0.724) and an AUROC of 0.690 (95%CI 0.655-0.724) for anastomotic leakage. CONCLUSIONS: The prediction of postoperative complications based only on preoperative variables using a national quality assurance colorectal cancer database shows promise for calculating patient's individual risk. Future work will focus on assessing the value of adding laboratory parameters and drug exposure as candidate predictors. Furthermore, we plan to assess the external validity of our proposed model.
BACKGROUND: The occurrence of postoperative complications and anastomotic leakage are major drivers of mortality in the immediate phase after colorectal cancer surgery. We trained prediction models for calculating patients' individual risk of complications based only on preoperatively available data in a multidisciplinary team setting. Knowing prior to surgery the probability of developing a complication could aid in improving informed decision-making by surgeon and patient and individualize surgical treatment trajectories. METHODS: All patients over 18 years of age undergoing any resection for colorectal cancer between January 1, 2014 and December 31, 2019 from the nationwide Danish Colorectal Cancer Group database were included. Data from the database were converted into Observational Medical Outcomes Partnership Common Data Model maintained by the Observation Health Data Science and Informatics initiative. Multiple machine learning models were trained to predict postoperative complications of Clavien-Dindo grade ≥ 3B and anastomotic leakage within 30 days after surgery. RESULTS: Between 2014 and 2019, 23,907 patients underwent resection for colorectal cancer in Denmark. A Clavien-Dindo complication grade ≥ 3B occurred in 2,958 patients (12.4%). Of 17,190 patients that received an anastomosis, 929 experienced anastomotic leakage (5.4%). Among the compared machine learning models, Lasso Logistic Regression performed best. The predictive model for complications had an area under the receiver operating characteristic curve (AUROC) of 0.704 (95%CI 0.683-0.724) and an AUROC of 0.690 (95%CI 0.655-0.724) for anastomotic leakage. CONCLUSIONS: The prediction of postoperative complications based only on preoperative variables using a national quality assurance colorectal cancer database shows promise for calculating patient's individual risk. Future work will focus on assessing the value of adding laboratory parameters and drug exposure as candidate predictors. Furthermore, we plan to assess the external validity of our proposed model.
Authors: Matteo Frasson; Pablo Granero-Castro; José Luis Ramos Rodríguez; Blas Flor-Lorente; Mariela Braithwaite; Eva Martí Martínez; Jose Antonio Álvarez Pérez; Antonio Codina Cazador; Alejandro Espí; Eduardo Garcia-Granero Journal: Int J Colorectal Dis Date: 2015-08-28 Impact factor: 2.571
Authors: Pierre A Clavien; Jeffrey Barkun; Michelle L de Oliveira; Jean Nicolas Vauthey; Daniel Dindo; Richard D Schulick; Eduardo de Santibañes; Juan Pekolj; Ksenija Slankamenac; Claudio Bassi; Rolf Graf; René Vonlanthen; Robert Padbury; John L Cameron; Masatoshi Makuuchi Journal: Ann Surg Date: 2009-08 Impact factor: 12.969
Authors: Chun Hin Angus Lee; Joseph Cherng Huei Kong; Alexander G Heriot; Satish Warrier; John Zalcberg; Paul Sitzler Journal: Int J Colorectal Dis Date: 2018-09-30 Impact factor: 2.571
Authors: Leonardo C Duraes; Luca Stocchi; Scott R Steele; Matthew F Kalady; James M Church; Emre Gorgun; David Liska; Hermann Kessler; Olga A Lavryk; Conor P Delaney Journal: Ann Surg Oncol Date: 2017-11-07 Impact factor: 5.344
Authors: J W T Dekker; C B M van den Broek; E Bastiaannet; L G M van de Geest; R A E M Tollenaar; G J Liefers Journal: Ann Surg Oncol Date: 2011-03-29 Impact factor: 5.344
Authors: David E Flynn; Derek Mao; Stephanie T Yerkovich; Robert Franz; Harish Iswariah; Andrew Hughes; Ian M Shaw; Diana P L Tam; Manju D Chandrasegaram Journal: PLoS One Date: 2020-12-23 Impact factor: 3.240