Abstract

Retrospective Study

Exploring the Prognostic Efficacy of Machine Learning Models in Predicting Adenocarcinoma of the Esophagogastric Junction

Kaiji Gao, Tonghui Yang and Changbing Wang and Jianguang Jia*

Published: 07 March, 2024 | Volume 8 - Issue 1 | Pages: 003-013

Objective: To investigate the value of machine learning and traditional Cox regression models in predicting postoperative survivorship in patients with adenocarcinoma of the esophagogastric junction (AEG).
Methods: This study analyzed clinicopathological data from 203 patients. The Cox proportional risk model and four machine learning models were constructed and internally validated. ROC curves, calibration curves, and clinical decision curves (DCA) were generated. Model performance was assessed using the area under the curve (AUC), while calibration curves determined the fit and clinical significance of the model.
Results: The AUC values of the 3-year survival in the validation set for the Cox regression model, extreme gradient boosting, random forest, support vector machine, and multilayer perceptron were 0.870, 0.901, 0.791, 0.832, and 0.725, respectively. The AUC values of 5-year survival in the validation set for each model were 0.915, 0.916, 0.758, 0.905, and 0.737, respectively. The internal validation AUC values for the four machine learning models, extreme gradient boosting, random forest, support vector machine, and multilayer perceptron, were 0.818, 0.772, 0.804, and 0.745, respectively.
Conclusion: Compared with Cox regression models, machine learning models do not need to satisfy the assumption of equal proportionality or linear regression models, can include more influencing variables, and have good prediction performance for 3-year and 5-year survival rates of AEG patients, among which, XGBoost models are the most stable and have significantly better prediction performance than other machine learning methods and are practical and reliable.

Read Full Article HTML DOI: 10.29328/journal.jro.1001059 Cite this Article Read Full Article PDF

Keywords:

Adenocarcinoma of Esophagogastric Union (AEG); Artificial Intelligence (AI); Machine Learning (ML); Cox proportional hazards regression model (Cox-PH); Extreme gradient boosting (XGBoost)

References

  1. Liu K, Yang K, Zhang W, Chen X, Chen X, Zhang B, Chen Z, Chen J, Zhao Y, Zhou Z, Chen L, Hu J. Changes of Esophagogastric Junctional Adenocarcinoma and Gastroesophageal Reflux Disease Among Surgical Patients During 1988-2012: A Single-institution, High-volume Experience in China. Ann Surg. 2016 Jan;263(1):88-95. doi: 10.1097/SLA.0000000000001148. PMID: 25647058; PMCID: PMC4679348.
  2. Imamura Y, Watanabe M, Toihata T, Takamatsu M, Kawachi H, Haraguchi I, Ogata Y, Yoshida N, Saeki H, Oki E, Taguchi K, Yamamoto M, Morita M, Mine S, Hiki N, Baba H, Sano T. Recent Incidence Trend of Surgically Resected Esophagogastric Junction Adenocarcinoma and Microsatellite Instability Status in Japanese Patients. Digestion. 2019;99(1):6-13. doi: 10.1159/000494406. Epub 2018 Dec 14. PMID: 30554205.
  3. Thrift AP, Whiteman DC. The incidence of esophageal adenocarcinoma continues to rise: analysis of period and birth cohort effects on recent trends. Ann Oncol. 2012 Dec;23(12):3155-3162. doi: 10.1093/annonc/mds181. Epub 2012 Jul 30. PMID: 22847812.
  4. Kusano C, Gotoda T, Khor CJ, Katai H, Kato H, Taniguchi H, Shimoda T. Changing trends in the proportion of adenocarcinoma of the esophagogastric junction in a large tertiary referral center in Japan. J Gastroenterol Hepatol. 2008 Nov;23(11):1662-5. doi: 10.1111/j.1440-1746.2008.05572.x. PMID: 19120859.
  5. Cox DR. Regression models and life-table JRoyStat SocSerB. Methodol.1972;34(2):187-220.
  6. Li L. Dimension reduction for high-dimensional data. Methods Mol Biol. 2010;620:417-34. doi: 10.1007/978-1-60761-580-4_14. PMID: 20652514.
  7. Kevin MP. Machine learning: a probabilistic perspective. MIT Press.
  8. Verma AA, Murray J, Greiner R, Cohen JP, Shojania KG, Ghassemi M, Straus SE, Pou-Prom C, Mamdani M. Implementing machine learning in medicine. CMAJ. 2021 Aug 30;193(34):E1351-E1357. doi: 10.1503/cmaj.202434. Epub 2021 Aug 29. PMID: 35213323; PMCID: PMC8432320.
  9. Lynch CM, Abdollahi B, Fuqua JD, de Carlo AR, Bartholomai JA, Balgemann RN, van Berkel VH, Frieboes HB. Prediction of lung cancer patient survival via supervised machine learning classification techniques. Int J Med Inform. 2017 Dec;108:1-8. doi: 10.1016/j.ijmedinf.2017.09.013. Epub 2017 Sep 25. PMID: 29132615; PMCID: PMC5726571.
  10. Zhou CM, Xue Q, Wang Y, Tong J, Ji M, Yang JJ. Machine learning to predict the cancer-specific mortality of patients with primary non-metastatic invasive breast cancer. Surg Today. 2021 May;51(5):756-763. doi: 10.1007/s00595-020-02170-9. Epub 2020 Oct 26. PMID: 33104877.
  11. Ji GW, Fan Y, Sun DW, Wu MY, Wang K, Li XC, Wang XH. Machine Learning to Improve Prognosis Prediction of Early Hepatocellular Carcinoma After Surgical Resection. J Hepatocell Carcinoma. 2021 Aug 10;8:913-923. doi: 10.2147/JHC.S320172. Erratum in: J Hepatocell Carcinoma. 2021 Oct 27;8:1297-1298. PMID: 34414136; PMCID: PMC8370036.
  12. Christopherson KM, Das P, Berlind C, Lindsay WD, Ahern C, Smith BD, Subbiah IM, Koay EJ, Koong AC, Holliday EB, Ludmir EB, Minsky BD, Taniguchi CM, Smith GL. A Machine Learning Model Approach to Risk-Stratify Patients With Gastrointestinal Cancer for Hospitalization and Mortality Outcomes. Int J Radiat Oncol Biol Phys. 2021 Sep 1;111(1):135-142. doi: 10.1016/j.ijrobp.2021.04.019. Epub 2021 Apr 29. PMID: 33933480.
  13. Nagtegaal ID, Odze RD, Klimstra D, Paradis V, Rugge M, Schirmacher P, Washington KM, Carneiro F, Cree IA; WHO Classification of Tumours Editorial Board. The 2019 WHO classification of tumours of the digestive system. Histopathology. 2020 Jan;76(2):182-188. doi: 10.1111/his.13975. Epub 2019 Nov 13. PMID: 31433515; PMCID: PMC7003895.
  14. Ji GW, Jiao CY, Xu ZG, Li XC, Wang K, Wang XH. Development and validation of a gradient boosting machine to predict prognosis after liver resection for intrahepatic cholangiocarcinoma. BMC Cancer. 2022 Mar 11;22(1):258. doi: 10.1186/s12885-022-09352-3. PMID: 35277130; PMCID: PMC8915487.
  15. Camp RL, Dolled-Filhart M, Rimm DL. X-tile: a new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization. Clin Cancer Res. 2004 Nov 1;10(21):7252-9. doi: 10.1158/1078-0432.CCR-04-0713. PMID: 15534099.
  16. Chevallay M, Bollschweiler E, Chandramohan SM, Schmidt T, Koch O, Demanzoni G, Mönig S, Allum W. Cancer of the gastroesophageal junction: a diagnosis, classification, and management review. Ann N Y Acad Sci. 2018 Dec;1434(1):132-138. doi: 10.1111/nyas.13954. Epub 2018 Aug 23. PMID: 30138540.
  17. de Manzoni G, Pedrazzani C, Verlato G, Roviello F, Pasini F, Pugliese R, Cordiano C. Comparison of old and new TNM systems for nodal staging in adenocarcinoma of the gastro-oesophageal junction. Br J Surg. 2004 Mar;91(3):296-303. doi: 10.1002/bjs.4431. PMID: 14991629.
  18. Tytgat GN, Bartelink H, Bernards R, Giaccone G, van Lanschot JJ, Offerhaus GJ, Peters GJ. Cancer of the esophagus and gastric cardia: recent advances. Dis Esophagus. 2004;17(1):10-26. doi: 10.1111/j.1442-2050.2004.00371.x. PMID: 15209736.
  19. Fein M, Fuchs KH, Ritter MP, Freys SM, Heimbucher J, Staab C, Thiede A. Application of the new classification for cancer of the cardia. Surgery. 1998 Oct;124(4):707-13; discussion 713-4. doi: 10.1067/msy.1998.91363. PMID: 9780992.
  20. Rüdiger Siewert J, Feith M, Werner M, Stein HJ. Adenocarcinoma of the esophagogastric junction: results of surgical therapy based on anatomical/topographic classification in 1,002 consecutive patients. Ann Surg. 2000 Sep;232(3):353-61. doi: 10.1097/00000658-200009000-00007. PMID: 10973385; PMCID: PMC1421149.
  21. Ychou M, Boige V, Pignon JP, Conroy T, Bouché O, Lebreton G, Ducourtieux M, Bedenne L, Fabre JM, Saint-Aubert B, Genève J, Lasser P, Rougier P. Perioperative chemotherapy compared with surgery alone for resectable gastroesophageal adenocarcinoma: an FNCLCC and FFCD multicenter phase III trial. J Clin Oncol. 2011 May 1;29(13):1715-21. doi: 10.1200/JCO.2010.33.0597. Epub 2011 Mar 28. PMID: 21444866.
  22. Liu X, Guo W, Shi X, Ke Y, Li Y, Pan S, Jin Y, Wang Y, Ruan Q, Ma H. Construction and verification of prognostic nomogram for early-onset esophageal cancer. Bosn J Basic Med Sci. 2021 Dec 1;21(6):760-772. doi: 10.17305/bjbms.2021.5533. PMID: 33823125; PMCID: PMC8554706.
  23. Tang X, Zhou X, Li Y, Tian X, Wang Y, Huang M, Ren L, Zhou L, Ding Z, Zhu J, Xu Y, Peng F, Wang J, Lu Y, Gong Y. A Novel Nomogram and Risk Classification System Predicting the Cancer-Specific Survival of Patients with Initially Diagnosed Metastatic Esophageal Cancer: A SEER-Based Study. Ann Surg Oncol. 2019 Feb;26(2):321-328. doi: 10.1245/s10434-018-6929-0. Epub 2018 Oct 24. PMID: 30357578.
  24. Buch VH, Ahmed I, Maruthappu M. Artificial intelligence in medicine: current trends and future possibilities. Br J Gen Pract. 2018 Mar;68(668):143-144. doi: 10.3399/bjgp18X695213. PMID: 29472224; PMCID: PMC5819974.
  25. Mofidi R, Deans C, Duff MD, de Beaux AC, Paterson Brown S. Prediction of survival from carcinoma of oesophagus and oesophago-gastric junction following surgical resection using an artificial neural network. Eur J Surg Oncol. 2006 Jun;32(5):533-9. doi: 10.1016/j.ejso.2006.02.020. Epub 2006 Apr 18. PMID: 16618533.
  26. Repetto O, De Re V. Coagulation and fibrinolysis in gastric cancer. Ann N Y Acad Sci. 2017 Sep;1404(1):27-48. doi: 10.1111/nyas.13454. Epub 2017 Aug 22. PMID: 28833193.
  27. Gao A, Wang L, Li J, Li H, Han Y, Ma X, Sun Y. Prognostic Value of Perineural Invasion in Esophageal and Esophagogastric Junction Carcinoma: A Meta-Analysis. Dis Markers. 2016;2016:7340180. doi: 10.1155/2016/7340180. Epub 2016 Mar 8. PMID: 27051075; PMCID: PMC4802032.
  28. Shahbaz Sarwar CM, Luketich JD, Landreneau RJ, Abbas G. Esophageal cancer: an update. Int J Surg. 2010;8(6):417-22. doi: 10.1016/j.ijsu.2010.06.011. Epub 2010 Jun 30. PMID: 20601255.
  29. Yang J, Lu Z, Li L, Li Y, Tan Y, Zhang D, Wang A. Relationship of lymphovascular invasion with lymph node metastasis and prognosis in superficial esophageal carcinoma: systematic review and meta-analysis. BMC Cancer. 2020 Mar 4;20(1):176. doi: 10.1186/s12885-020-6656-3. PMID: 32131772; PMCID: PMC7057611.
  30. Gupta V, Coburn N, Kidane B, Hess KR, Compton C, Ringash J, Darling G, Mahar AL. Survival prediction tools for esophageal and gastroesophageal junction cancer: A systematic review. J Thorac Cardiovasc Surg. 2018 Aug;156(2):847-856. doi: 10.1016/j.jtcvs.2018.03.146. Epub 2018 Apr 12. PMID: 30011772.
  31. van der Ploeg T, Austin PC, Steyerberg EW. Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints. BMC Med Res Methodol. 2014 Dec 22;14:137. doi: 10.1186/1471-2288-14-137. PMID: 25532820; PMCID: PMC4289553.

Figures:

Similar Articles

Recently Viewed

Read More

Most Viewed

Read More

Help ?