Predictive modelling for high-risk stage II colon cancer using auto-artificial intelligence
Predictive modelling for high-risk stage II colon cancer using auto-artificial intelligence
复制标题
DOI：
10.1007/s10151-022-02685-y
复制
发表时间：
2022-08-28
影响因子：
3.3
通讯作者：
Nagakawa，Yuichi
中科院分区：
文献类型：
--
作者：
Ishizaki，Tetsuo;Mazaki，Junichi;Nagakawa，Yuichi
背景近年来，高危II期结肠癌（CC）的分层和辅助化疗的必要性已成为人们关注的焦点。这项回顾性研究的目的是使用 Prediction One 自动人工智能 (AI) 软件定义复发性 II 期 CC 的高风险因素，并开发一种新的高风险 II 期 CC 预测模型。方法该研究包括 2000 年 1 月至 2016 年 12 月期间在我们机构接受根治性切除术的连续 259 名病理性 II 期 CC 患者。使用具有五倍交叉验证的 Prediction One 软件创建预测模型和受试者工作特征 (ROC)曲线。使用 ROC 曲线下面积 (AUC) 评估 AI 的预测准确性。我们还使用基于排列特征重要性（IOV > 0.01定义的高危因素）的方法评估了变量的重要性（IOV）来评估无病生存（DFS）。结果中位观察期为6.1（范围 = 0.3–15.8）年。 37例患者复发（14.3%）； AI模型的AUC为0.775。术前癌胚抗原 > 5.0ng/mL（IOV = 0.047）、静脉侵犯（IOV = 0.014）和阻塞（IOV = 0.012）是导致癌症复发的高危因素。具有 2-3 个高危因素的患者的 5 年 DFS 低于具有 0-1 个因素的患者（87.4% vs 62.7%，p< 0.001）。结论我们开发了一种新的预测模型，可以使用自动 AI Prediction One 软件以高概率预测复发性高危 II 期 CC。具有≥2个上述因素的患者被认为具有复发II期CC的高风险，可能受益于辅助化疗。
BackgroundRecently, stratification of high-risk stage II colon cancer (CC) and the need for adjuvant chemotherapy have been the focus of attention. The aim of this retrospective study was to define high-risk factors for recurrent stage II CC using Prediction One auto-artificial intelligence (AI) software and develop a new predictive model for high-risk stage II CC.MethodsThe study included 259 consecutive pathological stage II CC patients undergoing curative resection at our institution between January 2000 and December 2016. Prediction One software with five-fold cross-validation was used to create a predictive model and receiver operating characteristic (ROC) curve. Predictive accuracy of AI was evaluated using the area under the ROC curve (AUC). We also evaluated the importance of variables (IOV) using a method based on permutation feature importance (IOV > 0.01 defined high-risk factors) to evaluate disease-free survival (DFS).ResultsThe median observation period was 6.1 (range = 0.3–15.8) years. Thirty-seven patients had recurrence (14.3%); the AUC of the AI model was 0.775. Preoperative carcinoembryonic antigen > 5.0 ng/mL (IOV = 0.047), venous invasion (IOV = 0.014), and obstruction (IOV = 0.012) were high-risk factors contributing to cancer recurrence. Patients with 2–3 high-risk factors had lower 5-year DFS than those with 0–1 factor (87.4% vs 62.7%,p< 0.001).ConclusionsWe developed a new predictive model that could predict recurrent high-risk stage II CC with high probability using auto-AI Prediction One software. Patients with ≥ 2 of the aforementioned factors are considered to have high risks for recurrent stage II CC and may benefit from adjuvant chemotherapy.