Performance of a machine learning-based decision model to help clinicians decide the extent of lymphadenectomy (D1 vs. D2) in gastric cancer before surgical resection
Controversy still exists on the optimal surgical resection for potentially curable gastric cancer (GC). Use of radiologic evaluation and machine learning algorithms might predict extent of lymphadenectomy to limit unnecessary surgical treatment. We purposed to design a machine learning-based clinical decision-support model for predicting extent of lymphadenectomy (D1 vs. D2) in local advanced GC.
Clinicoradiologic features available from routine clinical assignments in 557 patients with GCs were retrospectively interpreted by an expert panel blinded to all histopathologic information. All patients underwent surgery using standard D2 resection. Decision models were developed with a logistic regression (LR), support vector machine (SVM) and auto-encoder (AE) algorithm in 371 training and tested in 186 test data, respectively. The primary end point was to measure diagnostic performance of decision model and a Japanese gastric cancer treatment guideline version 4th (JPN 4th) criteria for discriminate D1 (pT1 + pN0) versus D2 (≥ pT1 + ≥ pN1) lymphadenectomy.
The decision model with AE analysis produced highest area under ROC curve (train: 0.965, 95% confidence interval (CI) 0.948–0.978; test: 0.946, 95% CI 0.925–0.978), followed by SVM (train: 0.925, 95% CI 0.902–0.944; test: 0.942, 95% CI 0.922–0.973) and LR (train: 0.886, 95% CI 0.858–0.910; test: 0.891, 95% CI 0.891–0.952). By this improvement, overtreatment was reduced from 21.7% (121/557) by treat-all pattern, to 15.1% (84/557) by JPN 4th criteria, and to 0.7–0.9% (4–5/557) by the new approach.
The decision model with machine learning analysis demonstrates high accuracy for identifying patients who are candidates for D1 versus D2 resection. Its approximate 14–20% improvements in overtreatment compared to treat-all pattern and JPN 4th criteria potentially increase the number of patients with local advanced GCs who can safely avoid unnecessary lymphadenectomy.
KeywordsTomography Gastric cancer Machine learning Lymphadenectomy Decision-support model
This study is supported by a Key Social Development Program for the Ministry of Science and Technology of Jiangsu Province (BE2017756, YDZ)
Compliance with ethical standards
Conflict of interest
The authors have nothing to declare.
The study was approved by the Institutional Review Board of the First Affiliated Hospital of Nanjing Medical University.
Written informed consent was waived by the Institutional Review Board.
- 1.Siegel RL, Miller KD, Jemal A (2018) Cancer statistics, 2018. CA: a cancer journal for clinicians; 68(1): 7–30.Google Scholar
- 6.Japanese Gastric Cancer A. Japanese gastric cancer treatment guidelines 2014 (ver. 4). Gastric cancer: official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association 2017; 20(1): 1–19.Google Scholar
- 8.Kim JW, Shin SS, Heo SH et al (2012) Diagnostic performance of 64-section CT using CT gastrography in preoperative T staging of gastric cancer according to 7th edition of AJCC cancer staging manual. Eur. Radiol 22(3): 654–662.Google Scholar
- 14.Maccioni F, Marcelli G, Al Ansari N et al (2010) Preoperative T and N staging of gastric cancer: magnetic resonance imaging (MRI) versus multi detector computed tomography (MDCT). Clin Ter 161(2): e57–62.Google Scholar
- 16.Hwang SH, Kim HI, Song JS, Lee MH, Kwon SJ, Kim MG (2016) The Ratio-Based N Staging System Can More Accurately Reflect the Prognosis of T4 Gastric Cancer Patients with D2 Lymphadenectomy Compared with the 7th American Joint Committee on Cancer/Union for International Cancer Control Staging System. J Gastric Cancer 16(4): 207–214.CrossRefGoogle Scholar
- 25.Hong ZL, Chen QY, Zheng CH et al (2017) A preoperative scoring system to predict the risk of No. 10 lymph node metastasis for advanced upper gastric cancer: a large case report based on a single-center study. Oncotarget 8(45): 80050–80060.Google Scholar
- 31.Kermany DS, Goldbaum M, Cai W et al (2018) Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell 172(5): 1122–31 e9.Google Scholar
- 37.Ozawa Y, Chiba N, Hikita K et al (2017) Long-Term Survival of a Gastric Neuroendocrine Carcinoma Patient with Extra-Regional Lymph Node Metastases. Gan To Kagaku Ryoho 44(4): 333–336.Google Scholar
- 39.Marin Cordova NE, Yan-Quiroz EF, Diaz Plasencia J, Churango Barreto K, Calvanapon Prado P, Salazar Abad S (2017) Prognostic significance of the ratio of lymph node metastatic in 5-year survival after curative gastrectomy for advanced gastric carcinoma. Rev Gastroenterol Peru 37(3): 217–224.Google Scholar