Meral Mehmet, Ozbilgin Ferdi
Department of Neurosurgery, Private Erciyes Hospital, Kayseri 38020, Türkiye.
Department of Electrical and Electronic Engineering, Giresun University, Giresun 28200, Türkiye.
Diagnostics (Basel). 2025 Aug 14;15(16):2046. doi: 10.3390/diagnostics15162046.
: Early diagnosis of Parkinson's Disease (PD) is essential for initiating interventions that may slow its progression and enhance patient quality of life. Gait analysis provides a non-invasive means of capturing subtle motor disturbances, enabling the prediction of both disease presence and severity. This study evaluates and contrasts Bayesian-optimized convolutional neural network (CNN) and long short-term memory (LSTM) models applied directly to Vertical Ground Reaction Force (VGRF) signals for Parkinson's disease detection and staging. : VGRF recordings were segmented into fixed-length windows of 5, 10, 15, 20, and 25 s. Each segment was normalized and supplied as input to CNN and LSTM network. Hyperparameters for both architectures were optimized via Bayesian optimization using five-fold cross-validation. : The Bayesian-optimized LSTM achieved a peak binary classification accuracy of 99.42% with an AUC of 1.000 for PD versus control at the 10-s window, and 98.24% accuracy with an AUC of 0.999 for Hoehn-Yahr (HY) staging at the 5-s window. The CNN model reached up to 98.46% accuracy (AUC = 0.998) for binary classification and 96.62% accuracy (AUC = 0.998) for multi-class severity assessment. : Bayesian-optimized CNN and LSTM models trained on VGRF data both achieved high accuracy in Parkinson's disease detection and staging, with the LSTM exhibiting a slight edge in capturing temporal patterns while the CNN delivered comparable performance with reduced computational demands. These results underscore the promise of end-to-end deep learning for non-invasive, gait-based assessment in Parkinson's disease.
帕金森病（PD）的早期诊断对于启动可能减缓其进展并提高患者生活质量的干预措施至关重要。步态分析提供了一种捕捉细微运动障碍的非侵入性方法，能够预测疾病的存在和严重程度。本研究评估并对比了直接应用于垂直地面反作用力（VGRF）信号的贝叶斯优化卷积神经网络（CNN）和长短期记忆（LSTM）模型，用于帕金森病的检测和分期。：VGRF记录被分割为5、10、15、20和25秒的固定长度窗口。每个片段都进行了归一化处理，并作为输入提供给CNN和LSTM网络。两种架构的超参数通过使用五折交叉验证的贝叶斯优化进行了优化。：贝叶斯优化的LSTM在10秒窗口时，对PD与对照的二元分类准确率达到峰值99.42%，AUC为1.000；在5秒窗口时，对Hoehn-Yahr（HY）分期的准确率为98.24%，AUC为0.999。CNN模型在二元分类中准确率高达98.4%（AUC = 0.998），在多类严重程度评估中准确率为96.62%（AUC = 0.998）。：在VGRF数据上训练的贝叶斯优化CNN和LSTM模型在帕金森病检测和分期中均取得了高精度，LSTM在捕捉时间模式方面略有优势，而CNN在计算需求降低的情况下表现相当。这些结果强调了端到端深度学习在帕金森病非侵入性步态评估中的前景。
