Skip to main content
Erschienen in: Annals of Surgical Oncology 5/2018

01.03.2018 | Gastrointestinal Oncology

Prediction of Overall Survival and Novel Classification of Patients with Gastric Cancer Using the Survival Recurrent Network

verfasst von: Sung Eun Oh, MD, Sung Wook Seo, MD, PhD, Min-Gew Choi, MD, Tae Sung Sohn, MD, Jae Moon Bae, MD, Sung Kim, MD

Erschienen in: Annals of Surgical Oncology | Ausgabe 5/2018

Einloggen, um Zugang zu erhalten

Abstract

Background

Artificial neural networks (ANNs) have been applied to many prediction and classification problems, and could also be used to develop a prediction model of survival outcomes for cancer patients.

Objective

The aim of this study is to develop a prediction model of survival outcomes for patients with gastric cancer using an ANN.

Methods

This study enrolled 1243 patients with stage IIA–IV gastric cancer who underwent D2 gastrectomy from January 2007 to June 2010. We used a recurrent neural network (RNN) to make the survival recurrent network (SRN), and patients were randomly sorted into a training set (80%) and a test set (20%). Fivefold cross-validation was performed with the training set, and the optimized model was evaluated with the test set. Receiver operating characteristic (ROC) curves and area under the curves (AUCs) were evaluated, and we compared the survival curves of the American Joint Committee on Cancer (AJCC) 8th stage groups with those of the groups classified by the SRN-predicted survival probability.

Results

The test data showed that the ROC AUC of the SRN was 0.81 at the fifth year. The SRN-predicted survival corresponded closely with the actual survival in the calibration curve, and the survival outcome could be more discriminately classified by using the SRN than by using the AJCC staging system.

Conclusion

SRN was a more powerful tool for predicting the survival rates of gastric cancer patients than conventional TNM staging, and may also provide a more flexible and expandable method when compared with fixed prediction models such as nomograms.
Anhänge
Nur mit Berechtigung zugänglich
Literatur
2.
Zurück zum Zitat Parkin DM, Bray F, Ferlay J, Pisani P. Global cancer statistics, 2002. CA Cancer J Clin. 2005;55:74–108.CrossRefPubMed Parkin DM, Bray F, Ferlay J, Pisani P. Global cancer statistics, 2002. CA Cancer J Clin. 2005;55:74–108.CrossRefPubMed
3.
Zurück zum Zitat Washington K. 7th edition of the AJCC cancer staging manual: stomach. Ann Surg Oncol. 2010;17:3077–3079.CrossRefPubMed Washington K. 7th edition of the AJCC cancer staging manual: stomach. Ann Surg Oncol. 2010;17:3077–3079.CrossRefPubMed
4.
Zurück zum Zitat Japanese Gastric Cancer Association. Japanese classification of gastric carcinoma: 3rd English edition. Gastric Cancer. 2011;14:101–112. Japanese Gastric Cancer Association. Japanese classification of gastric carcinoma: 3rd English edition. Gastric Cancer. 2011;14:101–112.
5.
Zurück zum Zitat Chen D, Jiang B, Xing J, et al. Validation of the memorial Sloan-Kettering Cancer Center nomogram to predict disease-specific survival after R0 resection in a Chinese gastric cancer population. PLoS One. 2013;8:e76041.CrossRefPubMedPubMedCentral Chen D, Jiang B, Xing J, et al. Validation of the memorial Sloan-Kettering Cancer Center nomogram to predict disease-specific survival after R0 resection in a Chinese gastric cancer population. PLoS One. 2013;8:e76041.CrossRefPubMedPubMedCentral
6.
Zurück zum Zitat Kattan MW, Karpeh MS, Mazumdar M, Brennan MF. Postoperative nomogram for disease-specific survival after an R0 resection for gastric carcinoma. J Clin Oncol. 2003;21:3647–3650.CrossRefPubMed Kattan MW, Karpeh MS, Mazumdar M, Brennan MF. Postoperative nomogram for disease-specific survival after an R0 resection for gastric carcinoma. J Clin Oncol. 2003;21:3647–3650.CrossRefPubMed
7.
Zurück zum Zitat Baxt WG. Application of artificial neural networks to clinical medicine. Lancet. 1995;346:1135–1138.CrossRefPubMed Baxt WG. Application of artificial neural networks to clinical medicine. Lancet. 1995;346:1135–1138.CrossRefPubMed
8.
Zurück zum Zitat Grossi E, Mancini A, Buscema M. International experience on the use of artificial neural networks in gastroenterology. Dig Liver Dis. 2007;39:278–285.CrossRefPubMed Grossi E, Mancini A, Buscema M. International experience on the use of artificial neural networks in gastroenterology. Dig Liver Dis. 2007;39:278–285.CrossRefPubMed
9.
Zurück zum Zitat Tu JV. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol. 1996;49:1225–1231.CrossRefPubMed Tu JV. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol. 1996;49:1225–1231.CrossRefPubMed
10.
Zurück zum Zitat Burke HB, Goodman PH, Rosen DB, et al. Artificial neural networks improve the accuracy of cancer survival prediction. Cancer. 1997;79:857–862.CrossRefPubMed Burke HB, Goodman PH, Rosen DB, et al. Artificial neural networks improve the accuracy of cancer survival prediction. Cancer. 1997;79:857–862.CrossRefPubMed
11.
Zurück zum Zitat Biglarian A, Hajizadeh E, Kazemnejad A, Zali MR. Application of artificial neural network in predicting the survival rate of gastric cancer patients. Iran J Public Health. 2011;40:80–86.PubMedPubMedCentral Biglarian A, Hajizadeh E, Kazemnejad A, Zali MR. Application of artificial neural network in predicting the survival rate of gastric cancer patients. Iran J Public Health. 2011;40:80–86.PubMedPubMedCentral
12.
Zurück zum Zitat Zhu L, Luo W, Su M, Wei H, Wei J, Zhang X, et al. Comparison between artificial neural network and Cox regression model in predicting the survival rate of gastric cancer patients. Biomed Rep. 2013;1:757–760.CrossRefPubMedPubMedCentral Zhu L, Luo W, Su M, Wei H, Wei J, Zhang X, et al. Comparison between artificial neural network and Cox regression model in predicting the survival rate of gastric cancer patients. Biomed Rep. 2013;1:757–760.CrossRefPubMedPubMedCentral
13.
Zurück zum Zitat Hush DR, Horne BG. Progress in supervised neural networks. IEEE Signal Process Mag. 1993;10:8–39.CrossRef Hush DR, Horne BG. Progress in supervised neural networks. IEEE Signal Process Mag. 1993;10:8–39.CrossRef
14.
Zurück zum Zitat Larose DT. Discovering knowledge in data: an introduction to data mining. Hoboken, NJ: Wiley, 2005:90–106.CrossRef Larose DT. Discovering knowledge in data: an introduction to data mining. Hoboken, NJ: Wiley, 2005:90–106.CrossRef
15.
Zurück zum Zitat Anguita D, Ghelardoni L, Ghio A, Oneto L, Ridella S. The ‘K’ in K-fold Cross Validation. ESANN 2012 proceedings. ESANN 2012 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 25–27 April 2012; Bruges: pp. 441–446. Anguita D, Ghelardoni L, Ghio A, Oneto L, Ridella S. The ‘K’ in K-fold Cross Validation. ESANN 2012 proceedings. ESANN 2012 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 25–27 April 2012; Bruges: pp. 441–446.
16.
Zurück zum Zitat Lasko TA, Bhagwat JG, Zou KH, Ohno-Machado L. The use of receiver operating characteristic curves in biomedical informatics. J Biomed Inform. 2005;38:404–15.CrossRefPubMed Lasko TA, Bhagwat JG, Zou KH, Ohno-Machado L. The use of receiver operating characteristic curves in biomedical informatics. J Biomed Inform. 2005;38:404–15.CrossRefPubMed
17.
Zurück zum Zitat Peeters KC, Kattan MW, Hartgrink HH, Kranenbarg EK, Karpeh MS, Brennan MF, van de Velde CJ. Validation of a nomogram for predicting disease-specific survival after an R0 resection for gastric carcinoma. Cancer. 2005;103:702–707.CrossRefPubMed Peeters KC, Kattan MW, Hartgrink HH, Kranenbarg EK, Karpeh MS, Brennan MF, van de Velde CJ. Validation of a nomogram for predicting disease-specific survival after an R0 resection for gastric carcinoma. Cancer. 2005;103:702–707.CrossRefPubMed
18.
Zurück zum Zitat AR Novotny, C Schuhmacher, R Busch, MW Kattan, MF Brennan, JR Siewert. Predicting individual survival after gastric cancer resection: validation of a U.S.-derived nomogram at a single high-volume center in Europe. Ann Surg. 2006;243:74–81.CrossRefPubMedPubMedCentral AR Novotny, C Schuhmacher, R Busch, MW Kattan, MF Brennan, JR Siewert. Predicting individual survival after gastric cancer resection: validation of a U.S.-derived nomogram at a single high-volume center in Europe. Ann Surg. 2006;243:74–81.CrossRefPubMedPubMedCentral
19.
Zurück zum Zitat Strong VE, Song KY, Park CH, et al. Comparison of gastric cancer survival following R0 resection in the United States and Korea using an internationally validated nomogram. Ann Surg. 2010;251:640–646.CrossRefPubMed Strong VE, Song KY, Park CH, et al. Comparison of gastric cancer survival following R0 resection in the United States and Korea using an internationally validated nomogram. Ann Surg. 2010;251:640–646.CrossRefPubMed
20.
Zurück zum Zitat Ashfaq A, Kidwell JT, McGhan LJ, et al. Validation of a gastric cancer nomogram using a cancer registry. J Surg Oncol. 2015;112:377–380.CrossRefPubMed Ashfaq A, Kidwell JT, McGhan LJ, et al. Validation of a gastric cancer nomogram using a cancer registry. J Surg Oncol. 2015;112:377–380.CrossRefPubMed
21.
Zurück zum Zitat Kim JH, Kim HS, Seo WY, et al. External validation of nomogram for the prediction of recurrence after curative resection in early gastric cancer. Ann Oncol. 2012;23:361–367.CrossRefPubMed Kim JH, Kim HS, Seo WY, et al. External validation of nomogram for the prediction of recurrence after curative resection in early gastric cancer. Ann Oncol. 2012;23:361–367.CrossRefPubMed
22.
Zurück zum Zitat Song KY, Park YG, Jeon HM, Park CH. A nomogram for predicting individual survival of patients with gastric cancer who underwent radical surgery with extended lymph node dissection. Gastric Cancer. 2014;17:287–293.CrossRefPubMed Song KY, Park YG, Jeon HM, Park CH. A nomogram for predicting individual survival of patients with gastric cancer who underwent radical surgery with extended lymph node dissection. Gastric Cancer. 2014;17:287–293.CrossRefPubMed
23.
Zurück zum Zitat Eom BW, Ryu KW, Nam BH, et al. Survival nomogram for curatively resected Korean gastric cancer patients: multicenter retrospective analysis with external validation. PLoS One. 2015;10:e0119671.CrossRefPubMedPubMedCentral Eom BW, Ryu KW, Nam BH, et al. Survival nomogram for curatively resected Korean gastric cancer patients: multicenter retrospective analysis with external validation. PLoS One. 2015;10:e0119671.CrossRefPubMedPubMedCentral
24.
Zurück zum Zitat Brennan MF. Current status of surgery for gastric cancer: a review. Gastric Cancer. 2005;8:64–70.CrossRefPubMed Brennan MF. Current status of surgery for gastric cancer: a review. Gastric Cancer. 2005;8:64–70.CrossRefPubMed
25.
Zurück zum Zitat Fondevila C, Metges JP, Fuster J, et al. p53 and VEGF expression are independent predictors of tumour recurrence and survival following curative resection of gastric cancer. Br J Cancer. 2004;90:206–215.CrossRefPubMedPubMedCentral Fondevila C, Metges JP, Fuster J, et al. p53 and VEGF expression are independent predictors of tumour recurrence and survival following curative resection of gastric cancer. Br J Cancer. 2004;90:206–215.CrossRefPubMedPubMedCentral
Metadaten
Titel
Prediction of Overall Survival and Novel Classification of Patients with Gastric Cancer Using the Survival Recurrent Network
verfasst von
Sung Eun Oh, MD
Sung Wook Seo, MD, PhD
Min-Gew Choi, MD
Tae Sung Sohn, MD
Jae Moon Bae, MD
Sung Kim, MD
Publikationsdatum
01.03.2018
Verlag
Springer International Publishing
Erschienen in
Annals of Surgical Oncology / Ausgabe 5/2018
Print ISSN: 1068-9265
Elektronische ISSN: 1534-4681
DOI
https://doi.org/10.1245/s10434-018-6343-7

Weitere Artikel der Ausgabe 5/2018

Annals of Surgical Oncology 5/2018 Zur Ausgabe

Health Services Research and Global Oncology

Denis Parsons Burkitt, an Overlooked Surgical Oncologist

Update Chirurgie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

S3-Leitlinie „Diagnostik und Therapie des Karpaltunnelsyndroms“

CME: 2 Punkte

Prof. Dr. med. Gregor Antoniadis Das Karpaltunnelsyndrom ist die häufigste Kompressionsneuropathie peripherer Nerven. Obwohl die Anamnese mit dem nächtlichen Einschlafen der Hand (Brachialgia parästhetica nocturna) sehr typisch ist, ist eine klinisch-neurologische Untersuchung und Elektroneurografie in manchen Fällen auch eine Neurosonografie erforderlich. Im Anfangsstadium sind konservative Maßnahmen (Handgelenksschiene, Ergotherapie) empfehlenswert. Bei nicht Ansprechen der konservativen Therapie oder Auftreten von neurologischen Ausfällen ist eine Dekompression des N. medianus am Karpaltunnel indiziert.

Prof. Dr. med. Gregor Antoniadis
Berufsverband der Deutschen Chirurgie e.V.

S2e-Leitlinie „Distale Radiusfraktur“

CME: 2 Punkte

Dr. med. Benjamin Meyknecht, PD Dr. med. Oliver Pieske Das Webinar S2e-Leitlinie „Distale Radiusfraktur“ beschäftigt sich mit Fragen und Antworten zu Diagnostik und Klassifikation sowie Möglichkeiten des Ausschlusses von Zusatzverletzungen. Die Referenten erläutern, welche Frakturen konservativ behandelt werden können und wie. Das Webinar beantwortet die Frage nach aktuellen operativen Therapiekonzepten: Welcher Zugang, welches Osteosynthesematerial? Auf was muss bei der Nachbehandlung der distalen Radiusfraktur geachtet werden?

PD Dr. med. Oliver Pieske
Dr. med. Benjamin Meyknecht
Berufsverband der Deutschen Chirurgie e.V.

S1-Leitlinie „Empfehlungen zur Therapie der akuten Appendizitis bei Erwachsenen“

CME: 2 Punkte

Dr. med. Mihailo Andric
Inhalte des Webinars zur S1-Leitlinie „Empfehlungen zur Therapie der akuten Appendizitis bei Erwachsenen“ sind die Darstellung des Projektes und des Erstellungswegs zur S1-Leitlinie, die Erläuterung der klinischen Relevanz der Klassifikation EAES 2015, die wissenschaftliche Begründung der wichtigsten Empfehlungen und die Darstellung stadiengerechter Therapieoptionen.

Dr. med. Mihailo Andric
Berufsverband der Deutschen Chirurgie e.V.