人工智能可能有助于预测 T1 结直肠肿瘤内镜切除术后是否需要追加手术。

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

机构信息

Digestive Disease Center, Showa University, Northern Yokohama Hospital, Yokohama, Japan.

King's Institute of Therapeutic Endoscopy, King's College Hospital, London, United Kingdom.

出版信息

Endoscopy. 2018 Mar;50(3):230-240. doi: 10.1055/s-0043-122385. Epub 2017 Dec 22.

DOI:10.1055/s-0043-122385

PMID:29272905

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 %; < 0.001), 91 % (95 %CI 84 % to 96 %; < 0.001), and 91 % (95 %CI 84 % to 96 %; < 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.

摘要

背景与研究目的

内镜切除 T1 结直肠癌（CRC）后是否进行辅助手术存在一定难度，因为术前预测淋巴结转移（LNM）存在问题。我们研究了人工智能是否可以预测 LNM 的存在，从而减少不必要的辅助手术。

患者与方法

回顾性分析了 2001 年至 2016 年间接受手术切除的 690 例 T1 CRC 连续患者的数据。我们根据日期将患者分为两组：590 例患者的数据用于人工智能模型的机器学习，其余 100 例患者用于模型验证。人工智能模型分析了 45 项临床病理因素，然后预测 LNM 的阳性或阴性。手术标本作为 LNM 存在的金标准。通过计算预测 LNM 的灵敏度、特异性和准确性来验证人工智能模型，并将这些数据与美国、欧洲和日本指南进行比较。

结果

所有模型的灵敏度均为 100%（95%置信区间[CI]72%至 100%）。人工智能模型和美国、欧洲和日本指南的特异性分别为 66%（95%CI 56%至 76%）、44%（95%CI 34%至 55%）、0%（95%CI 0%至 3%）和 0%（95%CI 0%至 3%），准确性分别为 69%（95%CI 59%至 78%）、49%（95%CI 39%至 59%）、9%（95%CI 4%至 16%）和 9%（95%CI 4%至 16%）。由于误诊 LNM 阴性患者为 LNM 阳性而导致不必要的辅助手术的比率分别为：人工智能模型为 77%（95%CI 62%至 89%），美国、欧洲和日本指南分别为 85%（95%CI 73%至 93%；<0.001）、91%（95%CI 84%至 96%；<0.001）和 91%（95%CI 84%至 96%；<0.001）。