Li Yunfei, Zhang Dongni, Wang Yiren, Hu Yiheng, Wen Zhongjian, Yang Cheng, Zhou Ping, Cheng Wen-Hui
Department of Oncology, The Affiliated Hospital of Southwest Medical University, Luzhou, China.
School of Nursing, Southwest Medical University, Luzhou, China.
Front Oncol. 2025 Jun 19;15:1589919. doi: 10.3389/fonc.2025.1589919. eCollection 2025.
This study aimed to develop a risk prediction model for post-treatment oligometastasis in nasopharyngeal carcinoma (NPC) by integrating pathomics features and an improved Support vector machine (SVM) algorithm, offering precise early decision support.
This study retrospectively included 462 NPC patients, without or with oligometastasis defined by ESTRO/EORTC criteria. Whole-slide images were scanned, and three representative H&E-stained regions were selected for pathomics feature extraction via CellProfiler software. Features screened by intraclass correlation coefficient, Mann-Whitney U test, Spearman correlation, minimum redundancy maximum relevance, and Least absolute shrinkage and selection operator regression. Based on these screened features, three models were built: Dynamic Multi-Swarm Particle Swarm Optimization SVM (DMS-PSO-SVM), Particle Swarm Optimization SVM (PSO-SVM), and a standard SVM. Model training and hyperparameter tuning were conducted on the training set (n=369), followed by evaluation on a validation set (n=93).
6 pathomics features were screened as important features. DMS-PSO-SVM yielded superior performance, with training-set AUC=0.880 and validation-set AUC=0.866, consistently outperforming both PSO-SVM (AUC=0.721) and standard SVM (AUC=0.718). Calibration curves showed good agreement for DMS-PSO-SVM (P>0.05) but indicated miscalibration in the standard SVM (P<0.05). Decision curve analysis further demonstrated that DMS-PSO-SVM offered higher net benefit across a wide range of risk thresholds.
Incorporating pathomics and DMS-PSO optimization significantly improved NPC oligometastasis prediction. This model showed high discriminative ability, calibration, and clinical utility, suggesting that pathomics and machine learning-based strategies could aid early recognition of high-risk patients and inform individualized treatment approaches. A demo of the DMS-PSO-SVM modeling algorithm code used in this study can be found on Github (https://github.com/Edward-E-S-Wang/DMS-PSO-SVM).
本研究旨在通过整合病理组学特征和改进的支持向量机（SVM）算法，开发一种鼻咽癌（NPC）治疗后寡转移的风险预测模型，提供精确的早期决策支持。
本研究回顾性纳入了462例NPC患者，根据ESTRO/EORTC标准定义有无寡转移。对全切片图像进行扫描，并通过CellProfiler软件选择三个代表性的苏木精和伊红（H&E）染色区域进行病理组学特征提取。通过组内相关系数、曼-惠特尼U检验、斯皮尔曼相关性、最小冗余最大相关性和最小绝对收缩和选择算子回归筛选特征。基于这些筛选出的特征，构建了三个模型：动态多群粒子群优化支持向量机（DMS-PSO-SVM）、粒子群优化支持向量机（PSO-SVM）和标准支持向量机。在训练集（n = 369）上进行模型训练和超参数调整，随后在验证集（n = 93）上进行评估。
筛选出6个病理组学特征作为重要特征。DMS-PSO-SVM表现出卓越的性能，训练集AUC = 0.880，验证集AUC = 0.866，始终优于PSO-SVM（AUC = 0.721）和标准支持向量机（AUC = 0.718）。校准曲线显示DMS-PSO-SVM具有良好的一致性（P>0.05），但标准支持向量机存在校准错误（P<0.05）。决策曲线分析进一步表明，DMS-PSO-SVM在广泛的风险阈值范围内提供了更高的净效益。
结合病理组学和DMS-PSO优化显著改善了NPC寡转移预测。该模型具有较高的判别能力、校准度和临床实用性，表明基于病理组学和机器学习的策略有助于早期识别高危患者并为个体化治疗方法提供依据。本研究中使用的DMS-PSO-SVM建模算法代码演示可在Github（https://github.com/Edward-E-S-Wang/DMS-PSO-SVM）上找到。
