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
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Shin-ei Kudo
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Yuichi Mori
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Masashi Misawa
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Shingo Matsudaira
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Yuta Kouyama
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Toshiyuki Baba
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Eiji Hidaka
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Kunihiko Wakamura
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Takemasa Hayashi
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Toyoki Kudo
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Tomoyuki Ishigaki
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Yusuke Yagawa
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Hiroki Nakamura
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Kenichi Takeda
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Amyn Haji
2  King’s Institute of Therapeutic Endoscopy, King’s College Hospital, London, United Kingdom
,
Shigeharu Hamatani
3  Department of Pathology, Jikei University School of Medicine, Tokyo, Japan
,
Kensaku Mori
4  Information and Communications, Nagoya University, Nagoya, Japan
,
Fumio Ishida
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
,
Hideyuki Miyachi
1  Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan
5  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