多模态多分类器融合模型预测放射性口腔黏膜炎的性能  

Performance of multi-modality and multi-classifier fusion models for predicting radiation-induced oral mucositis in patients with nasopharyngeal carcinoma

作　　者：胡玥 曾玉 王琳婧 廖志伟 谭剑明 邝燕好 龚攀 齐斌 甄鑫[1] HU Yue;ZENG Yu;WANG Linjing;LIAO Zhiwei;TAN Jianming;KUANG Yanhao;GONG Pan;QI Bin;ZHEN Xin(School of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China;Department of Stomatology,Guangzhou Institute of Cancer Research,Affiliated Cancer Hospital of Guangzhou Medical University,Guangzhou 510095,China;Department of Radiation Oncology,Guangzhou Institute of Cancer Research,Affiliated Cancer Hospital of Guangzhou Medical University,Guangzhou 510095,China)

机构地区：[1]南方医科大学生物医学工程学院,广东广州510515 [2]广州医科大学附属肿瘤医院口腔科,广东广州510095 [3]广州医科大学附属肿瘤医院放射肿瘤科,广东广州510095

出　　处：《南方医科大学学报》2024年第12期2434-2442,共9页Journal of Southern Medical University

基　　金：国家自然科学基金(62106058);广东省自然科学基金(2024A1515012100,2022A1515011410,2022A1515012104);广州市科技计划项目(202201011662);广州市重点医学学科建设项目基金;广州市重点临床技术项目(20231A010060)

摘　　要：目的评估不同放射性口腔黏膜炎(RIOM)预测模型的性能,对比分析分层多模态多分类器融合(H-MCF)模型的有效性。方法回顾性收集2022年9月~2023年2月在广州医科大学附属肿瘤医院接受观察和治疗的198例放射性口腔黏膜炎局部晚期鼻咽癌患者的数据。基于口腔放射剂量-体积参数与鼻咽癌相关的临床特征,针对不同特征选择算法和分类器两两组合得到基础分类模型。我们使用基于多准则决策的多分类器融合模型(MCF)和它的变体——H-MCF模型对基础分类模型进行融合。通过对各个模态的基础分类模型与MCF模型的性能、多模态的基础模型和MCF模型以及H-MCF模型的性能、单模态与多模态模型的性能、H-MCF与MCF以及其他集成分类器的性能进行分析比较,并通过ROC曲线下面积(AUC)、准确率(ACC)、灵敏度(SEN)和特异度(SPE)4种评价指标来评估模型的泛化性能,分析RIOM预测模型有效性。结果结合多模态特征后,H-MCF模型在预测严重RIOM方面达到了最高的准确性(AUC=0.883,ACC=0.850,SEN=0.933,SPE=0.800)。结论相较于单个分类器的预测结果,结合临床和剂量两种模态的多分类器融合算法在预测严重RIOM发病率方面表现更优。Objective To evaluate the performance of different multi-modality fusion models for predicting radiation-induced oral mucositis(RIOM)following radiotherapy in patients with nasopharyngeal carcinoma(NPC).Methods We retrospectively collected the data from 198 patients with locally advanced NPC who experienced RIOM following radiotherapy at the Affiliated Tumor Hospital of Guangzhou Medical University from September,2022 to February,2023.Based on oral radiation dose-volume parameters and clinical features of NPC,basic classification models were developed using different combinations of feature selection algorithms and classifiers and integrated using a multi-criterion decision-making(MCDM)-based classifier fusion(MCF)strategy and its variant,the H-MCF model.The basic classification models,MCF model,the H-MCF model with a single modality or multiple modalities and other ensemble classifiers were compared for performances for predicting RIOM by assessing the area under the ROC curve(AUC),accuracy,sensitivity,and specificity.Results The H-MCF model,which integrated multi-modality features,achieved the highest accuracy for predicting severe RIOM with an AUC of 0.883,accuracy of 0.850,sensitivity of 0.933,and specificity of 0.800.Conclusion Compared with each of the individual classifiers,the multimodal multi-classifier fusion algorithm combining clinical and dosimetric modalities demonstrates superior performance in predicting the incidence of severe RIOM in NPC patients following radiotherapy.

关 键 词：鼻咽癌 放射性口腔黏膜炎 人工智能 多分类器 多准则决策 

分 类 号：R739.63[医药卫生—肿瘤] R781.5[医药卫生—临床医学]