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

被引：128

作者：

Ichimasa, Katsuro ^{[1
]}

Kudo, Shin-ei ^{[1
]}

Mori, Yuichi ^{[1
]}

Misawa, Masashi ^{[1
]}

Matsudaira, Shingo ^{[1
]}

Kouyama, Yuta ^{[1
]}

Baba, Toshiyuki ^{[1
]}

Hidaka, Eiji ^{[1
]}

Wakamura, Kunihiko ^{[1
]}

Hayashi, Takemasa ^{[1
]}

Kudo, Toyoki ^{[1
]}

Ishigaki, Tomoyuki ^{[1
]}

Yagawa, Yusuke ^{[1
]}

Nakamura, Hiroki ^{[1
]}

Takeda, Kenichi ^{[1
]}

Haji, Amyn ^{[2
]}

Hamatani, Shigeharu ^{[3
]}

Mori, Kensaku ^{[4
]}

Ishida, Fumio ^{[1
]}

Miyachi, Hideyuki ^{[1
,5
]}

机构：

[1] Showa Univ, Northern Yokohama Hosp, Digest Dis Ctr, Yokohama, Kanagawa, Japan

[2] Kings Coll Hosp London, Kings Inst Therapeut Endoscopy, London, England

[3] Jikei Univ, Dept Pathol, Sch Med, Tokyo, Japan

[4] Nagoya Univ, Informat & Commun, Nagoya, Aichi, Japan

[5] Miyachi Clin, Kakogawa, Hyogo, Japan

来源：

ENDOSCOPY | 2018年 / 50卷 / 03期

基金：

日本学术振兴会;

关键词：

LYMPH-NODE METASTASIS; CLINICAL-PRACTICE GUIDELINES; AIDED DIAGNOSTIC SYSTEM; SUPPORT VECTOR MACHINE; RECTAL-CANCER; RISK-FACTORS; CARCINOMA; METAANALYSIS; LESIONS; COLON;

D O I：

10.1055/s-0043-122385

中图分类号：

R57 [消化系及腹部疾病];

学科分类号：

摘要：

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.

引用

页码：230 / 240

页数：11

共 31 条

[1] Systematic review and meta-analysis of histopathological factors influencing the risk of lymph node metastasis in early colorectal cancer [J].