Artificial intelligence may help in predicting the need for additional surgery after endoscopic resection of T1 colorectal cancer

Abstract

Background and study aims Decisions concerning additional surgery after endoscopic resection of T1 colorectal cancer (CRC) are difficult because preoperative prediction of lymph node metastasis (LNM) is problematic. We investigated whether artificial intelligence can predict LNM presence, thus minimizing the need for additional surgery.

Patients and methods Data on 690 consecutive patients with T1 CRCs that were surgically resected in 2001 – 2016 were retrospectively analyzed. We divided patients into two groups according to date: data from 590 patients were used for machine learning for the artificial intelligence model, and the remaining 100 patients were included for model validation. The artificial intelligence model analyzed 45 clinicopathological factors and then predicted positivity or negativity for LNM. Operative specimens were used as the gold standard for the presence of LNM. The artificial intelligence model was validated by calculating the sensitivity, specificity, and accuracy for predicting LNM, and comparing these data with those of the American, European, and Japanese guidelines.

Results Sensitivity was 100 % (95 % confidence interval [CI] 72 % to 100 %) in all models. Specificity of the artificial intelligence model and the American, European, and Japanese guidelines was 66 % (95 %CI 56 % to 76 %), 44 % (95 %CI 34 % to 55 %), 0 % (95 %CI 0 % to 3 %), and 0 % (95 %CI 0 % to 3 %), respectively; and accuracy was 69 % (95 %CI 59 % to 78 %), 49 % (95 %CI 39 % to 59 %), 9 % (95 %CI 4 % to 16 %), and 9 % (95 %CI 4 % – 16 %), respectively. The rates of unnecessary additional surgery attributable to misdiagnosing LNM-negative patients as having LNM were: 77 % (95 %CI 62 % to 89 %) for the artificial intelligence model, and 85 % (95 %CI 73 % to 93 %; P < 0.001), 91 % (95 %CI 84 % to 96 %; P < 0.001), and 91 % (95 %CI 84 % to 96 %; P < 0.001) for the American, European, and Japanese guidelines, respectively.

Conclusions Compared with current guidelines, artificial intelligence significantly reduced unnecessary additional surgery after endoscopic resection of T1 CRC without missing LNM positivity.

• References

• 1 Overwater A, Kessels K, Elias SG. et al. Endoscopic resection of high-risk T1 colorectal carcinoma prior to surgical resection has no adverse effect on long-term outcomes. Gut 2016;
• 2 Bosch SL, Teerenstra S, de Wilt JH. et al. Predicting lymph node metastasis in pT1 colorectal cancer: a systematic review of risk factors providing rationale for therapy decisions. Endoscopy 2013; 45: 827-834
• 3 Miyachi H, Kudo SE, Ichimasa K. et al. Management of T1 colorectal cancers after endoscopic treatment based on the risk stratification of lymph node metastasis. J Gastroenterol Hepatol 2016; 31: 1126-1132
• 4 Nascimbeni R, Burgart LJ, Nivatvongs S. et al. Risk of lymph node metastasis in T1 carcinoma of the colon and rectum. Dis Colon Rectum 2002; 45: 200-206
• 5 Wada H, Shiozawa M, Katayama K. et al. Systematic review and meta-analysis of histopathological predictive factors for lymph node metastasis in T1 colorectal cancer. J Gastroenterol 2015; 50: 727-734
• 6 National Comprehensive Cancer Network. NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines^®) Rectal Cancer (Version 1.2017). 2017 Available from: https://www.nccn.org/professionals/physician_gls/f_guidelines.asp
• 7 National Comprehensive Cancer Network. NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines^®) Colon Cancer (Version 1.2017). 2017 Available from: https://www.nccn.org/professionals/physician_gls/f_guidelines.asp
• 8 Labianca R, Nordlinger B, Beretta GD. et al. Early colon cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol 2013; 24 (Suppl. 06) vi64-72
• 9 Glimelius B, Tiret E, Cervantes A. et al. Rectal cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol 2013; 24 (Suppl. 06) vi81-88
• 10 Watanabe T, Muro K, Ajioka Y. et al. Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines 2016 for the treatment of colorectal cancer. Int J Clin Oncol 2017;
• 11 Tanaka S, Haruma K, Teixeira CR. et al. Endoscopic treatment of submucosal invasive colorectal carcinoma with special reference to risk factors for lymph node metastasis. J Gastroenterol 1995; 30: 710-717
• 12 Kobayashi H, Mochizuki H, Morita T. et al. Characteristics of recurrence after curative resection for T1 colorectal cancer: Japanese multicenter study. J Gastroenterol 2011; 46: 203-211
• 13 Coverlizza S, Risio M, Ferrari A. et al. Colorectal adenomas containing invasive carcinoma. Pathologic assessment of lymph node metastatic potential. Cancer 1989; 64: 1937-1947
• 14 Kitamura K, Taniguchi H, Yamaguchi T. et al. Clinical outcome of surgical treatment for invasive early colorectal cancer in Japan. Hepatogastroenterology 1997; 44: 108-115
• 15 Tateishi Y, Nakanishi Y, Taniguchi H. et al. Pathological prognostic factors predicting lymph node metastasis in submucosal invasive (T1) colorectal carcinoma. Modern Pathol 2010; 23: 1068-1072
• 16 Iversen LH, Nielsen H, Pedersen L. et al. Seasonal variation in short-term mortality after surgery for colorectal cancer?. Colorectal Dis 2010; 12: e31-36
• 17 Paulson EC, Mitra N, Sonnad S. et al. National Cancer Institute designation predicts improved outcomes in colorectal cancer surgery. Ann Surg 2008; 248: 675-686
• 18 Moons KG, Altman DG, Reitsma JB. et al. New guideline for the reporting of studies developing, validating, or updating a multivariable clinical prediction model: the TRIPOD statement. Adv Anat Pathol 2015; 22: 303-305
• 19 Kobayashi Y, Kudo SE, Miyachi H. et al. Clinical usefulness of pit patterns for detecting colonic lesions requiring surgical treatment. Int J Colorectal Dis 2011; 26: 1531-1540
• 20 Bosman FT, Carneiro F, Hruban RH, Theise ND. WHO classification of tumours of the digestive system, 4th edn. Lyon, France: 2010
• 21 Beaton C, Twine CP, Williams GL. et al. Systematic review and meta-analysis of histopathological factors influencing the risk of lymph node metastasis in early colorectal cancer. Colorectal Dis 2013; 15: 788-797
• 22 Wada H, Shiozawa M, Sugano N. et al. Lymphatic invasion identified with D2-40 immunostaining as a risk factor of nodal metastasis in T1 colorectal cancer. Int J Clin Oncol 2013; 18: 1025-1031
• 23 Macias-Garcia F, Celeiro-Munoz C, Lesquereux-Martinez L. et al. A clinical model for predicting lymph node metastasis in submucosal invasive (T1) colorectal cancer. Int J Colorectal Dis 2015; 30: 761-768
• 24 Ichimasa K, Kudo SE, Miyachi H. et al. 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: 517-524
• 25 Takeuchi Y, Uedo N, Ishihara R. et al. Efficacy of an endo-knife with a water-jet function (Flushknife) for endoscopic submucosal dissection of superficial colorectal neoplasms. Am J Gastroenterol 2010; 105: 314-322
• 26 Lee W, Lee D, Choi S. et al. Transanal endoscopic microsurgery and radical surgery for T1 and T2 rectal cancer. Surg Endosc 2003; 17: 1283-1287
• 27 Wu HY, Gong CS, Lin SP. et al. Predicting postoperative vomiting among orthopedic patients receiving patient-controlled epidural analgesia using SVM and LR. Sci Rep 2016; 6: 27041
• 28 Mori Y, Kudo SE, Wakamura K. et al. Novel computer-aided diagnostic system for colorectal lesions by using endocytoscopy (with videos). Gastrointest Endosc 2015; 81: 621-629
• 29 Yang HX, Feng W, Wei JC. et al. Support vector machine-based nomogram predicts postoperative distant metastasis for patients with oesophageal squamous cell carcinoma. Br J Cancer 2013; 109: 1109-1116
• 30 Misawa M, Kudo SE, Mori Y. et al. Characterization of colorectal lesions using a computer-aided diagnostic system for narrow-band imaging endocytoscopy. Gastroenterology 2016; 150: 1531-1532 e1533
• 31 Mourao-Miranda J, Bokde AL, Born C. et al. Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional MRI data. Neuroimage 2005; 28: 980-995