Endoscopy 2018; 50(03): 230-240
DOI: 10.1055/s-0043-122385
Original article
© Georg Thieme Verlag KG Stuttgart · New York

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

Katsuro Ichimasa
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Shin-ei Kudo
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Yuichi Mori
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Masashi Misawa
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Shingo Matsudaira
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Yuta Kouyama
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Toshiyuki Baba
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Eiji Hidaka
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Kunihiko Wakamura
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Takemasa Hayashi
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Toyoki Kudo
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Tomoyuki Ishigaki
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Yusuke Yagawa
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Hiroki Nakamura
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Kenichi Takeda
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Amyn Haji
King’s Institute of Therapeutic Endoscopy, King’s College Hospital, London, United Kingdom
,
Shigeharu Hamatani
Department of Pathology, Jikei University School of Medicine, Tokyo, Japan
,
Kensaku Mori
Information and Communications, Nagoya University, Nagoya, Japan
,
Fumio Ishida
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Hideyuki Miyachi
Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
Miyachi Clinic, Kakogawa, Japan
› Author Affiliations
TRIAL REGISTRATION: Retrospective Study UMIN000026552 at http://www.umin.ac.jp.
Further Information

Publication History

submitted 16 May 2017

accepted after revision 21 September 2017

Publication Date:
22 December 2017 (eFirst)

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.

Supplemental material