Jin-On Jung1,2, Nerma Crnovrsanin1, Naita Maren Wirsik1,2, Henrik Nienhüser1, Leila Peters1, Felix Popp2, André Schulze1, Martin Wagner1, Beat Peter Müller-Stich1, Markus Wolfgang Büchler1, Thomas Schmidt3,4. 1. Department of General, Visceral and Transplantation Surgery, University Hospital of Heidelberg, Im Neuenheimer Feld 420, 69120, Heidelberg, Germany. 2. Department of General, Visceral and Cancer Surgery, University Hospital of Cologne, Kerpener Straße 62, 50937, Cologne, Germany. 3. Department of General, Visceral and Transplantation Surgery, University Hospital of Heidelberg, Im Neuenheimer Feld 420, 69120, Heidelberg, Germany. thomas.schmidt1@uk-koeln.de. 4. Department of General, Visceral and Cancer Surgery, University Hospital of Cologne, Kerpener Straße 62, 50937, Cologne, Germany. thomas.schmidt1@uk-koeln.de.
Abstract
PURPOSE: Surgical oncologists are frequently confronted with the question of expected long-term prognosis. The aim of this study was to apply machine learning algorithms to optimize survival prediction after oncological resection of gastroesophageal cancers. METHODS: Eligible patients underwent oncological resection of gastric or distal esophageal cancer between 2001 and 2020 at Heidelberg University Hospital, Department of General Surgery. Machine learning methods such as multi-task logistic regression and survival forests were compared with usual algorithms to establish an individual estimation. RESULTS: The study included 117 variables with a total of 1360 patients. The overall missingness was 1.3%. Out of eight machine learning algorithms, the random survival forest (RSF) performed best with a concordance index of 0.736 and an integrated Brier score of 0.166. The RSF demonstrated a mean area under the curve (AUC) of 0.814 over a time period of 10 years after diagnosis. The most important long-term outcome predictor was lymph node ratio with a mean AUC of 0.730. A numeric risk score was calculated by the RSF for each patient and three risk groups were defined accordingly. Median survival time was 18.8 months in the high-risk group, 44.6 months in the medium-risk group and above 10 years in the low-risk group. CONCLUSION: The results of this study suggest that RSF is most appropriate to accurately answer the question of long-term prognosis. Furthermore, we could establish a compact risk score model with 20 input parameters and thus provide a clinical tool to improve prediction of oncological outcome after upper gastrointestinal surgery.
PURPOSE: Surgical oncologists are frequently confronted with the question of expected long-term prognosis. The aim of this study was to apply machine learning algorithms to optimize survival prediction after oncological resection of gastroesophageal cancers. METHODS: Eligible patients underwent oncological resection of gastric or distal esophageal cancer between 2001 and 2020 at Heidelberg University Hospital, Department of General Surgery. Machine learning methods such as multi-task logistic regression and survival forests were compared with usual algorithms to establish an individual estimation. RESULTS: The study included 117 variables with a total of 1360 patients. The overall missingness was 1.3%. Out of eight machine learning algorithms, the random survival forest (RSF) performed best with a concordance index of 0.736 and an integrated Brier score of 0.166. The RSF demonstrated a mean area under the curve (AUC) of 0.814 over a time period of 10 years after diagnosis. The most important long-term outcome predictor was lymph node ratio with a mean AUC of 0.730. A numeric risk score was calculated by the RSF for each patient and three risk groups were defined accordingly. Median survival time was 18.8 months in the high-risk group, 44.6 months in the medium-risk group and above 10 years in the low-risk group. CONCLUSION: The results of this study suggest that RSF is most appropriate to accurately answer the question of long-term prognosis. Furthermore, we could establish a compact risk score model with 20 input parameters and thus provide a clinical tool to improve prediction of oncological outcome after upper gastrointestinal surgery.
Authors: Karl Y Bilimoria; Yaoming Liu; Jennifer L Paruch; Lynn Zhou; Thomas E Kmiecik; Clifford Y Ko; Mark E Cohen Journal: J Am Coll Surg Date: 2013-09-18 Impact factor: 6.113
Authors: Bernice Lo; Kejian Zhang; Wei Lu; Lixin Zheng; Qian Zhang; Chrysi Kanellopoulou; Yu Zhang; Zhiduo Liu; Jill M Fritz; Rebecca Marsh; Ammar Husami; Diane Kissell; Shannon Nortman; Vijaya Chaturvedi; Hilary Haines; Lisa R Young; Jun Mo; Alexandra H Filipovich; Jack J Bleesing; Peter Mustillo; Michael Stephens; Cesar M Rueda; Claire A Chougnet; Kasper Hoebe; Joshua McElwee; Jason D Hughes; Elif Karakoc-Aydiner; Helen F Matthews; Susan Price; Helen C Su; V Koneti Rao; Michael J Lenardo; Michael B Jordan Journal: Science Date: 2015-07-24 Impact factor: 47.728
Authors: Piotr Kulig; Przemysław Nowakowski; Marek Sierzęga; Radosław Pach; Oliwia Majewska; Anna Markiewicz; Piotr Kołodziejczyk; Jan Kulig; Piotr Richter Journal: Anticancer Res Date: 2021-07 Impact factor: 2.480
Authors: Jared L Katzman; Uri Shaham; Alexander Cloninger; Jonathan Bates; Tingting Jiang; Yuval Kluger Journal: BMC Med Res Methodol Date: 2018-02-26 Impact factor: 4.615