Okura Keisuke, Fukuyama Keita, Seo Satoru, Nishino Hiroto, Yoh Tomoaki, Shimoike Norihiro, Nishio Takahiro, Koyama Yukinori, Ogiso Satoshi, Ishii Takamichi, Hida Koya, Matsumoto Shigemi, Muto Manabu, Morita Satoshi, Obama Kazutaka, Hatano Etsuro
Department of Surgery, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
Division of Medical Information Technology and Administration Planning, Kyoto University Hospital, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, 606-8507, Japan.
Int J Clin Oncol. 2025 May 1. doi: 10.1007/s10147-025-02766-6.
Predicting individual prognosis is required for patients with colorectal cancer in the era of precision medicine. However, this may be challenging for the conventional survival analysis such as the Cox proportional hazards model. This study aims to develop a personalized prognostic prediction that incorporates longitudinal data to improve predictions for colorectal cancer patients.
Patients with advanced or recurrent colorectal cancer, who received treatment at Kyoto University Hospital between April 2015 and December 2021, were retrospectively analyzed. The Joint model is one of the dynamic prediction models. Using longitudinal clinical data, a carcinoembryonic antigen (CEA) prediction equation was developed for each patient. Additionally, a personalized prognostic prediction model was created using the Joint model. The prediction accuracy of the Joint model was compared with one of the Cox proportional hazards model.
Among the 1010 patients, 614 patients were enrolled. The median frequency of tumor marker measurement (per patient) was 20 times (range: 3-117 times). CEA values could be predicted accurately and the Pearson's correlation coefficient between measured CEA and predicted CEA was 0.931. In the Joint model, the significant prognostic factors were baseline age (HR, 1.039; 95% CI, 1.025-1.054), poor-differentiated tumor (HR, 2.600; 95% CI 1.446-4.675) and log (predicted CEA) (HR, 1.551; 95% CI 1.488-1.617). The areas under the curve at 2, 3, 4, and 5 were significantly higher for the Joint model than for the Cox proportional hazards model, respectively.
The Joint model may accurately predict personalized prognosis that reflects changes in longitudinal tumor marker values.
在精准医学时代，预测结直肠癌患者的个体预后是必要的。然而，对于传统的生存分析方法，如Cox比例风险模型而言，这可能具有挑战性。本研究旨在开发一种个性化的预后预测方法，该方法纳入纵向数据以改善对结直肠癌患者的预测。
对2015年4月至2021年12月期间在京都大学医院接受治疗的晚期或复发性结直肠癌患者进行回顾性分析。联合模型是动态预测模型之一。利用纵向临床数据，为每位患者建立了癌胚抗原（CEA）预测方程。此外，使用联合模型创建了个性化的预后预测模型。将联合模型的预测准确性与Cox比例风险模型之一进行比较。
在1010例患者中，614例患者被纳入研究。肿瘤标志物测量的中位频率（每位患者）为20次（范围：3 - 117次）。CEA值能够被准确预测，实测CEA与预测CEA之间的Pearson相关系数为0.931。在联合模型中，显著的预后因素为基线年龄（HR，1.039；95%CI，1.025 - 1.054）、低分化肿瘤（HR，2.600；95%CI 1.446 - 4.675）和log（预测CEA）（HR，1.551；95%CI 1.488 - 1.617）。联合模型在2年、3年、4年和5年时的曲线下面积分别显著高于Cox比例风险模型。
联合模型可能准确预测反映纵向肿瘤标志物值变化的个性化预后。
