基于脂蛋白相关磷脂酶A2与血清生物标志物水平联合的结直肠癌肝转移预测模型

A colorectal liver metastasis prediction model based on the combination of lipoprotein-associated phospholipase A2 and serum biomarker levels.

作者信息

Feng Sisi, Zhou Manli, Huang Zixin, Xiao Xiaomin, Zhong Baiyun

机构信息

Department of Clinical Laboratory, Xiangya Hospital, Central South University, Changsha 410008, Hunan, China.

Department of Clinical Laboratory, Xiangya Hospital, Central South University, Changsha 410008, Hunan, China; National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha 410008, Hunan, China.

出版信息

Clin Chim Acta. 2025 Feb 15;568:120143. doi: 10.1016/j.cca.2025.120143. Epub 2025 Jan 16.

DOI:10.1016/j.cca.2025.120143

PMID:39826573

Abstract

OBJECTIVE

This study aims to assess the predictive value of serum lipoprotein-associated phospholipase A2 (Lp-PLA2) in colorectal liver metastasis (CRLM) patients.

METHODS

A total of 507 participants were recruited for this study, comprising 162 healthy controls (HCs), 186 non-CRLM patients, and 159 CRLM patients. Serum Lp-PLA2 levels were measured across these three groups, and a CRLM prediction model was developed using machine learning (ML) algorithms in conjunction with traditional serological markers. The performance of each model was assessed using the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, and other relevant metrics.

RESULTS

The serum Lp-PLA2 levels in CRLM patients were significantly elevated compared to those in HCs group and the non-CRLM group (P < 0.0001). The CRLM prediction model developed using the Random forest algorithm demonstrated superior performance, incorporating six features: Lp-PLA2, ALB, GLB, ALT, LDH, and TC. This model achieved an AUC of 0.918, with a sensitivity of 0.823, specificity of 0.889, positive predictive value (PPV) of 0.861, and negative predictive value (NPV) of 0.857.

CONCLUSION

The Random forest model, incorporating serum Lp-PLA2 level and conventional laboratory parameters, demonstrates robust predictive capability for CRLM and holds promise for enhancing early detection in CRLM patients.

摘要

目的

本研究旨在评估血清脂蛋白相关磷脂酶A2（Lp-PLA2）在结直肠癌肝转移（CRLM）患者中的预测价值。

方法

本研究共招募了507名参与者，包括162名健康对照者（HCs）、186名非CRLM患者和159名CRLM患者。测定了这三组人群的血清Lp-PLA2水平，并结合传统血清学标志物，使用机器学习（ML）算法建立了CRLM预测模型。使用受试者操作特征（ROC）曲线下面积（AUC）、敏感性、特异性和其他相关指标评估每个模型的性能。

结果

与HCs组和非CRLM组相比，CRLM患者的血清Lp-PLA2水平显著升高（P < 0.0001）。使用随机森林算法建立的CRLM预测模型表现优异，纳入了六个特征：Lp-PLA2、ALB、GLB、ALT、LDH和TC。该模型的AUC为0.918，敏感性为0.823，特异性为0.889，阳性预测值（PPV）为0.861，阴性预测值（NPV）为0.857。