基于时序卷积网络的早期帕金森多模态检测系统

Early Parkinson s Multimodal Detection System Based on Temporal Convolutional Networks

帕金森病是最常见的神经退行性疾病之一,其临床特征与其他神经退行性疾病有重叠,且缺乏明确的病理机制,导致早期诊断检测困难、误诊率高等问题;为了研究有效的早期帕金森病检测方法,深入探索帕金森病发展的时间特征规律,并提高早期帕金森病预测、分析和诊断决策的准确性,设计了一种基于时序卷积网络的早期帕金森病多模态检测系统,为及时发现早期帕金森病提供辅助诊断依据;该系统利用语音、步态和受试者自测数据,采用多元线性池化方法进行多模态融合,结合时间卷积网络和参数共享方式,以提高系统的检测精度并降低过拟合风险;实验测试结果显示,基于时序卷积网络的早期帕金森病检测系统的准确率达到96.22%,在多项评估指标上优于传统的帕金森检测模型,展现出良好的早期帕金森联合检测效果。

Parkinson s disease is one of the most common neurodegenerative diseases,its clinical features overlap with other neurodegenerative diseases and lack a clear pathological mechanism,leading to difficulties in early diagnosis and high misdiagnosis rates;In order to study effective early detection methods for Parkinson s disease,deeply explore the temporal characteristics of Parkinson s disease development,and improve the accuracy of early Parkinson s disease prediction,analysis,and diagnostic decision-making,an early Parkinson s disease multimodal detection system based on temporal convolutional networks is designed,providing an auxiliary diagnostic basis on the timely detection of early Parkinson s disease;The system utilizes the speech,gait,and subject self-test data,adopts the multiple linear pooling method for multimodal fusion,and integrates the time convolutional networks and parameter sharing to improve the detection accuracy of the system and reduce overfitting risks;Experimental results show that the accuracy of the early Parkinson s disease detection system based on temporal convolutional networks reaches 96.22%,which is superior to traditional Parkinson s detection models in multiple evaluation indicators and demonstrates good early Parkinson s joint detection performance.