基于概率分类器加权的多模态AD分类模型研究

Research on Multimodal AD Classification Model Based on Weighted Probability Classifier

阿尔茨海默症(Alzheimer’s Disease, AD)是一种最常见的神经退行性疾病,其症状具体表现为记忆和思维能力的退化,同时AD是受遗传因素影响很大的疾病,目前对AD仍无有效的治疗手段,许多研究基于单一模态数据进行早期诊断的研究效果不理想。为此,研究基于磁共振影像(MRI)和单核苷酸多态性(Single Nucleotide Polymorphim, SNP)两种模态数据提出一种概率分类器加权的多模态集成学习新框架,为分类器提供更丰富、全面的信息,从而提高AD诊断分类的准确率和稳定性。研究方法在AD vs NC、MCIc vs NC和MCInc vs MCIc的5次5折交叉验证实验结果平均准确率分别高达80%、76%、70%,结果表明研究提出的多模态集成学习模型与利用单一模态数据的分类模型相比更具有优势。

Alzheimer’s Disease (AD) is one of the most common neurodegenerative diseases. Its symptoms are specifically manifested as the deterioration of memory and thinking ability. At the same time, AD is a disease that is greatly affected by genetic factors. Without effective treatment, many studies based on single modal data for early diagnosis have unsatisfactory results. Therefore, based on the two modal data of Magnetic Resonance Imaging (MRI) and Single Nucleotide Polymorphim (SNP), the study proposed a new framework for multimodal ensemble learning weighted by probabilistic classifiers. The device provides richer and more comprehensive information, thereby improving the accuracy and stability of AD diagnostic classification. This research method is used in the 5-fold crossover of AD vs NC, MCIc vs NC and MCInc vs MCIc. The average verification accuracy rates are as high as 80%, 76%, and 70%. The results show that the multi-modal integrated learning model proposed by the research, compared with the classification model of single modal data has more advantages.