Hanevelt Julia, Brohet Richard M, Moons Leon M G, Laclé Miangela M, Vleggaar Frank P, van Westreenen Henderik L, de Vos Tot Nederveen Cappel Wouter H
Department of Gastroenterology and Hepatology, Isala, Zwolle, The Netherlands.
Department of Epidemiology and Statistics, Isala, Zwolle, The Netherlands.
Ann Surg Oncol. 2025 May;32(5):3078-3088. doi: 10.1245/s10434-025-16921-w. Epub 2025 Jan 23.
Similar to T1 colon cancer (CC), risk stratification may guide T2 CC treatment and reduce unnecessary major surgery. In this study, prediction models were developed that could identify T2 CC patients with a lower risk of lymph node metastasis (LNM) for whom (intensive) follow-up after local treatment could be considered.
A nationwide cohort study was performed involving pT2 CC patients who underwent surgery between 2012 and 2020, using data from the Dutch ColoRectal Audit, which were linked to the Nationwide Pathology Databank. Four machine learning models were evaluated to predict LNM.
LNMs were found in 1877/9803 patients (19.1%). Independent risk factors included (younger) age (odds ratio [OR] 0.98, 95% confidence interval [CI] 0.979-0.990), left-sided CC (OR 1.5, 95% CI 1.4-1.7), poor differentiation (OR 1.7, 95% CI 1.4-2.2), and lymphovascular invasion (LVI; OR 4.1, 95% CI 3.6-4.7). A deficient mismatch repair (MMR) status significantly lowered the risk of LNM (OR 0.3, 95% CI 0.2-0.5). The general linear model demonstrated the highest prediction accuracy, achieving area under the receiver operating characteristic curves of 0.67 and 0.68, with good calibration. In the absence of risk factors, elderly patients (≥74 years of age) had a predicted risk of LNM of 10.7%, yet up to 30% experienced postoperative complications, with mortality rates reaching up to 3.5%. Patients with a deficient MMR status had a predicted risk of LNM of 6.1% if LVI was absent and the tumor was well-differentiated.
The risk of LNM should be weighed against surgical risks. The findings of this study will enable clinicians to make more deliberate considerations about these competing risks before making a shared decision.
与T1期结肠癌（CC）类似，风险分层可指导T2期CC的治疗并减少不必要的大型手术。在本研究中，开发了预测模型，可识别淋巴结转移（LNM）风险较低的T2期CC患者，对于这些患者，可考虑在局部治疗后进行（强化）随访。
利用荷兰结直肠癌审计的数据，并将其与全国病理数据库相链接，进行了一项全国性队列研究，纳入2012年至2020年间接受手术的pT2期CC患者。评估了四种机器学习模型以预测LNM。
在1877/9803例患者（19.1%）中发现有LNM。独立危险因素包括（较年轻的）年龄（优势比[OR]0.98，95%置信区间[CI]0.979 - 0.990）、左侧CC（OR 1.5，95% CI 1.4 - 1.7）、低分化（OR 1.7，95% CI 1.4 - 2.2）和淋巴管浸润（LVI；OR 4.1，95% CI 3.6 - 4.7）。错配修复（MMR）缺陷状态显著降低了LNM风险（OR 0.3，95% CI 0.2 - 0.5）。一般线性模型显示出最高的预测准确性，受试者工作特征曲线下面积分别为0.67和0.68，校准良好。在无危险因素的情况下，老年患者（≥74岁）的LNM预测风险为10.7%，但高达30%的患者出现术后并发症，死亡率高达3.5%。如果不存在LVI且肿瘤分化良好，MMR缺陷状态的患者LNM预测风险为6.1%。
应权衡LNM风险与手术风险。本研究结果将使临床医生在做出共同决策之前，能够更慎重地考虑这些相互竞争的风险。
