Fan Rencai, Mao Chenkai, Zhang Jiaqi, Dai Min, Zhang Rong, Wang Xinran, Dai Jiaxin, Li Shicheng, Zhuang Zhixiang
Center for Cancer Diagnosis and Treatment, The Second Affiliated Hospital of Soochow University, No.1055, Sanxiang Road, Gusu District, Soochow, 215004, Jiangsu Province, P.R. China.
Department of Respiratory Medicine, Wu Zhong People's Hospital, No. 61 Dongwu North Road, Wu Zhong District, Soochow, 215100, Jiangsu Province, P.R. China.
Int J Colorectal Dis. 2025 Feb 26;40(1):53. doi: 10.1007/s00384-025-04841-w.
Oligometastatic colorectal cancer (OMCRC) patients can achieve long-term disease control with multidisciplinary treatment. However, the development of extensive metastasis worsens prognosis and restricts treatment options. This study aims to develop a predictive model for extensive metastasis in OMCRC to assist in clinical decision-making.
Clinical and pathological data for OMCRC patients were collected from the Second Affiliated Hospital of Soochow University. Patients were randomly divided into training and testing cohorts. Risk factors for extensive metastasis were identified through LASSO regression analysis and COX regression analysis. Three predictive models were developed in the training cohort and validated in the testing cohort: COX regression analysis, Extreme Gradient Boosting (XGBoost), and Survival Support Vector Machine (SurvSVM). Finally, the optimal model was visualized with the nomogram.
A total of 214 patients with OMCRC were enrolled in the study. Four independent risk factors were identified: whether surgery has been undertaken following oligometastasis (WST), histological type (HT), carcinoembryonic antigen at the last follow-up (CAE at last-FU), and preoperative albumin to globulin ratio (Preop-AGR). In the testing cohort, the COX model (1-year AUC = 0.82, 3-year AUC = 0.72, 5-year AUC = 0.85, mean AUC = 0.80) performed best. Decision curve analysis (DCA) confirmed the net benefit of the Cox model, and the nomogram provided accurate predictions of metastasis risk.
CAE at last-FU, Preop-AGR, HT, and WST are independent risk factors for extensive metastasis in OMCRC. The nomogram model incorporating risk factors can assist clinicians in developing optimal treatment for OMCRC patients.
寡转移性结直肠癌（OMCRC）患者通过多学科治疗可实现长期疾病控制。然而，广泛转移的发生会使预后恶化并限制治疗选择。本研究旨在建立一个预测OMCRC广泛转移的模型，以协助临床决策。
收集苏州大学附属第二医院OMCRC患者的临床和病理数据。患者被随机分为训练队列和测试队列。通过LASSO回归分析和COX回归分析确定广泛转移的危险因素。在训练队列中开发了三个预测模型，并在测试队列中进行验证：COX回归分析、极端梯度提升（XGBoost）和生存支持向量机（SurvSVM）。最后，用列线图对最佳模型进行可视化。
本研究共纳入214例OMCRC患者。确定了四个独立危险因素：寡转移后是否进行手术（WST）、组织学类型（HT）、最后一次随访时的癌胚抗原（最后一次随访时的CAE）和术前白蛋白球蛋白比（术前AGR）。在测试队列中，COX模型（1年AUC = 0.82，3年AUC = 0.72，5年AUC = 0.85，平均AUC = 0.80）表现最佳。决策曲线分析（DCA）证实了Cox模型的净效益，列线图提供了准确的转移风险预测。
最后一次随访时的CAE、术前AGR、HT和WST是OMCRC广泛转移的独立危险因素。纳入危险因素的列线图模型可协助临床医生为OMCRC患者制定最佳治疗方案。
