An Artificial Intelligence Prediction Model Outperforms Conventional Guidelines in Predicting Lymph Node Metastasis of T1 Colorectal Cancer

Overview

Journal Front Oncol

Specialty Oncology

Date 2023 Nov 9

PMID 37941556

Authors

Zheng Hua Piao

Rong Ge

Lu Lu

Affiliations

Soon will be listed here.

Abstract

Background: According to guidelines, a lot of patients with T1 colorectal cancers (CRCs) undergo additional surgery with lymph node dissection after being treated by endoscopic resection (ER) despite the low incidence of lymph node metastasis (LNM).

Aim: The aim of this study was to develop an artificial intelligence (AI) model to more effectively identify T1 CRCs at risk for LNM and reduce the rate of unnecessary additional surgery.

Methods: We retrospectively analyzed 651 patients with T1 CRCs. The patient cohort was randomly divided into a training set (546 patients) and a test set (105 patients) (ratio 5:1), and a classification and regression tree (CART) algorithm was trained on the training set to develop a predictive AI model for LNM. The model used 12 clinicopathological factors to predict positivity or negativity for LNM. To compare the performance of the AI model with the conventional guidelines, the test set was evaluated according to the Japanese Society for Cancer of the Colon and Rectum (JSCCR) and National Comprehensive Cancer Network (NCCN) guidelines. Finally, we tested the performance of the AI model using the test set and compared it with the JSCCR and NCCN guidelines.

Results: The AI model had better predictive performance (AUC=0.960) than the JSCCR (AUC=0.588) and NCCN guidelines (AUC=0.850). The specificity (85.8% vs. 17.5%, <0.001), balanced accuracy (92.9% vs. 58.7%, =0.001), and the positive predictive value (36.3% vs. 9.0%, =0.001) of the AI model were significantly better than those of the JSCCR guidelines and reduced the percentage of the high-risk group for LNM from 83.8% (JSCCR) to 20.9%. The specificity of the AI model was higher than that of the NCCN guidelines (85.8% vs. 82.4%, p=0.557), but there was no significant difference between the two. The sensitivity of the NCCN guidelines was lower than that of our AI model (87.5% vs. 100%, p=0.301), and according to the NCCN guidelines, 1.2% of the 105 test set patients had missed diagnoses.

Conclusion: The AI model has better performance than conventional guidelines for predicting LNM in T1 CRCs and therefore could significantly reduce unnecessary additional surgery.

Citing Articles

Preoperative CT lymph node size as a predictor of nodal metastasis in resectable Colon cancer: a retrospective study of 694 patients.

Kawazoe T, Nakanishi R, Ando K, Zaitsu Y, Kudou K, Nakashima Y BMC Gastroenterol. 2025; 25(1):18.

PMID: 39815179 PMC: 11734230. DOI: 10.1186/s12876-025-03602-x.

Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy.

Lee H, Chung J, Yun S, Jung S, Yoon Y, Kim J Diagnostics (Basel). 2024; 14(23).

PMID: 39682614 PMC: 11639788. DOI: 10.3390/diagnostics14232706.

A new clinical model for predicting lymph node metastasis in T1 colorectal cancer.

Wang K, He H, Lin Y, Zhang Y, Chen J, Hu J Int J Colorectal Dis. 2024; 39(1):46.

PMID: 38565736 PMC: 10987358. DOI: 10.1007/s00384-024-04621-y.

Commentary: An artificial intelligence prediction model outperforms conventional guidelines in predicting lymph node metastasis of T1 colorectal cancer.

Ichimasa K, Kudo S, Yeoh K Front Oncol. 2024; 14:1337576.

PMID: 38406818 PMC: 10889107. DOI: 10.3389/fonc.2024.1337576.

References

Watanabe T, Itabashi M, Shimada Y, Tanaka S, Ito Y, Ajioka Y . Japanese Society for Cancer of the Colon and Rectum (JSCCR) Guidelines 2014 for treatment of colorectal cancer. Int J Clin Oncol. 2015; 20(2):207-39. PMC: 4653248. DOI: 10.1007/s10147-015-0801-z. View

Benson A, Venook A, Al-Hawary M, Cederquist L, Chen Y, Ciombor K . Rectal Cancer, Version 2.2018, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Canc Netw. 2018; 16(7):874-901. PMC: 10203817. DOI: 10.6004/jnccn.2018.0061. View

Benson A, Venook A, Al-Hawary M, Arain M, Chen Y, Ciombor K . Colon Cancer, Version 2.2021, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Canc Netw. 2021; 19(3):329-359. DOI: 10.6004/jnccn.2021.0012. View

Kessels K, Backes Y, Elias S, van den Blink A, Offerhaus G, van Bergeijk J . Pedunculated Morphology of T1 Colorectal Tumors Associates With Reduced Risk of Adverse Outcome. Clin Gastroenterol Hepatol. 2018; 17(6):1112-1120.e1. DOI: 10.1016/j.cgh.2018.08.041. View

Kang J, Choi Y, Kim I, Lee H, Kim H, Baik S . LASSO-Based Machine Learning Algorithm for Prediction of Lymph Node Metastasis in T1 Colorectal Cancer. Cancer Res Treat. 2021; 53(3):773-783. PMC: 8291173. DOI: 10.4143/crt.2020.974. View

Matsuda T, Fukuzawa M, Uraoka T, Nishi M, Yamaguchi Y, Kobayashi N . Risk of lymph node metastasis in patients with pedunculated type early invasive colorectal cancer: a retrospective multicenter study. Cancer Sci. 2011; 102(9):1693-7. PMC: 11159017. DOI: 10.1111/j.1349-7006.2011.01997.x. View

Ha R, Han K, Sohn D, Kim B, Hong C, Chang H . Histopathologic risk factors for lymph node metastasis in patients with T1 colorectal cancer. Ann Surg Treat Res. 2017; 93(5):266-271. PMC: 5694718. DOI: 10.4174/astr.2017.93.5.266. View

Miyachi H, Kudo S, Ichimasa K, Hisayuki T, Oikawa H, Matsudaira S . Management of T1 colorectal cancers after endoscopic treatment based on the risk stratification of lymph node metastasis. J Gastroenterol Hepatol. 2015; 31(6):1126-32. DOI: 10.1111/jgh.13257. View

Piao Z, Ge R, Wang C . A proposal for grading the risk of lymph node metastasis after endoscopic resection of T1 colorectal cancer. Int J Colorectal Dis. 2023; 38(1):25. DOI: 10.1007/s00384-023-04319-7. View

10.

Dang H, Dekkers N, le Cessie S, van Hooft J, van Leerdam M, Oldenburg P . Risk and Time Pattern of Recurrences After Local Endoscopic Resection of T1 Colorectal Cancer: A Meta-analysis. Clin Gastroenterol Hepatol. 2020; 20(2):e298-e314. DOI: 10.1016/j.cgh.2020.11.032. View

11.

Kudo S, Ichimasa K, Villard B, Mori Y, Misawa M, Saito S . Artificial Intelligence System to Determine Risk of T1 Colorectal Cancer Metastasis to Lymph Node. Gastroenterology. 2020; 160(4):1075-1084.e2. DOI: 10.1053/j.gastro.2020.09.027. View

12.

Hye Song J, Hong Y, Ran Kim E, Kim S, Sohn I . Utility of artificial intelligence with deep learning of hematoxylin and eosin-stained whole slide images to predict lymph node metastasis in T1 colorectal cancer using endoscopically resected specimens; prediction of lymph node metastasis in T1.... J Gastroenterol. 2022; 57(9):654-666. DOI: 10.1007/s00535-022-01894-4. View

13.

Chang L, Shun C, Lin B, Sanduleanu S, Hsu W, Wu M . Recurrence Outcomes Less Favorable in T1 Rectal Cancer than in T1 Colon Cancer. Oncologist. 2021; 26(9):e1548-e1554. PMC: 8417849. DOI: 10.1002/onco.13815. View

14.

Hashiguchi Y, Muro K, Saito Y, Ito Y, Ajioka Y, Hamaguchi T . Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines 2019 for the treatment of colorectal cancer. Int J Clin Oncol. 2019; 25(1):1-42. PMC: 6946738. DOI: 10.1007/s10147-019-01485-z. View

15.

Ichimasa K, Kudo S, Miyachi H, Kouyama Y, Ishida F, Baba T . Patient gender as a factor associated with lymph node metastasis in T1 colorectal cancer: A systematic review and meta-analysis. Mol Clin Oncol. 2017; 6(4):517-524. PMC: 5374909. DOI: 10.3892/mco.2017.1172. View

16.

Ichimasa K, Kudo S, Miyachi H, Kouyama Y, Mochizuki K, Takashina Y . Current problems and perspectives of pathological risk factors for lymph node metastasis in T1 colorectal cancer: Systematic review. Dig Endosc. 2021; 34(5):901-912. DOI: 10.1111/den.14220. View

17.

Ueno H, Mochizuki H, Hashiguchi Y, Shimazaki H, Aida S, Hase K . Risk factors for an adverse outcome in early invasive colorectal carcinoma. Gastroenterology. 2004; 127(2):385-94. DOI: 10.1053/j.gastro.2004.04.022. View

18.

Kouyama Y, Kudo S, Miyachi H, Ichimasa K, Hisayuki T, Oikawa H . Practical problems of measuring depth of submucosal invasion in T1 colorectal carcinomas. Int J Colorectal Dis. 2015; 31(1):137-46. PMC: 4701783. DOI: 10.1007/s00384-015-2403-7. View

19.

Backes Y, Elias S, Groen J, Schwartz M, Wolfhagen F, Geesing J . Histologic Factors Associated With Need for Surgery in Patients With Pedunculated T1 Colorectal Carcinomas. Gastroenterology. 2018; 154(6):1647-1659. DOI: 10.1053/j.gastro.2018.01.023. View

20.

Ahn J, Kwak M, Lee H, Cha J, Shin H, Jeon J . Development of a Novel Prognostic Model for Predicting Lymph Node Metastasis in Early Colorectal Cancer: Analysis Based on the Surveillance, Epidemiology, and End Results Database. Front Oncol. 2021; 11:614398. PMC: 8029977. DOI: 10.3389/fonc.2021.614398. View