1st Department of Neurology, Eginition Hospital, National and Kapodistrian University of Athens, 11572 Athens, Greece.
Department of Mathematics, Marvdasht Branch, Islamic Azad University, Marvdasht 73711-13119, Iran.
Medicina (Kaunas). 2024 May 26;60(6):873. doi: 10.3390/medicina60060873.
: Currently, no tool exists to predict clinical outcomes in patients with advanced Parkinson's disease (PD) under levodopa-carbidopa intestinal gel (LCIG) treatment. The aim of this study was to develop a novel deep neural network model to predict the clinical outcomes of patients with advanced PD after two years of LCIG therapy. : This was a longitudinal, 24-month observational study of 59 patients with advanced PD in a multicenter registry under LCIG treatment from September 2019 to September 2021, including 43 movement disorder centers. The data set includes 649 measurements of patients, which make an irregular time series, and they are turned into regular time series during the preprocessing phase. Motor status was assessed with the Unified Parkinson's Disease Rating Scale (UPDRS) Parts III (off) and IV. The NMS was assessed by the NMS Questionnaire (NMSQ) and the Geriatric Depression Scale (GDS), the quality of life by PDQ-39, and severity by Hoehn and Yahr (HY). Multivariate linear regression, ARIMA, SARIMA, and Long Short-Term Memory-Recurrent NeuralNetwork (LSTM-RNN) models were used. : LCIG significantly improved dyskinesia duration and quality of life, with men experiencing a 19% and women a 10% greater improvement, respectively. Multivariate linear regression models showed that UPDRS-III decreased by 1.5 and 4.39 units per one-unit increase in the PDQ-39 and UPDRS-IV indexes, respectively. Although the ARIMA-(2,0,2) model is the best one with AIC criterion 101.8 and validation criteria MAE = 0.25, RMSE = 0.59, and RS = 0.49, it failed to predict PD patients' features over a long period of time. Among all the time series models, the LSTM-RNN model predicts these clinical characteristics with the highest accuracy (MAE = 0.057, RMSE = 0.079, RS = 0.0053, mean square error = 0.0069). : The LSTM-RNN model predicts, with the highest accuracy, gender-dependent clinical outcomes in patients with advanced PD after two years of LCIG therapy.
目前，尚无工具可预测接受左旋多巴-卡比多巴肠凝胶（LCIG）治疗的晚期帕金森病（PD）患者的临床结局。本研究旨在开发一种新的深度神经网络模型，以预测接受 LCIG 治疗两年后的晚期 PD 患者的临床结局。
这是一项纵向、为期 24 个月的多中心登记处观察研究，纳入了 59 名接受 LCIG 治疗的晚期 PD 患者，其中包括 43 家运动障碍中心。该数据集包含了 649 名患者的测量值，这些测量值构成了一个不规则的时间序列，在预处理阶段被转化为规则的时间序列。运动状态采用统一帕金森病评定量表（UPDRS）第三部分（关期）和第四部分进行评估。非运动症状（NMS）采用 NMS 问卷（NMSQ）和老年抑郁量表（GDS）进行评估，生活质量采用 PDQ-39 进行评估，严重程度采用 Hoehn 和 Yahr（HY）量表进行评估。采用多元线性回归、ARIMA、SARIMA 和长短期记忆-递归神经网络（LSTM-RNN）模型进行分析。
LCIG 显著改善了运动障碍的持续时间和生活质量，男性的改善幅度分别为 19%和 10%，女性的改善幅度分别为 19%和 10%。多元线性回归模型显示，PDQ-39 和 UPDRS-IV 指数每增加一个单位，UPDRS-III 分别减少 1.5 和 4.39 个单位。尽管 ARIMA-(2,0,2)模型是最好的模型，AIC 标准为 101.8，验证标准 MAE=0.25、RMSE=0.59 和 RS=0.49，但它未能预测 PD 患者在较长时间内的特征。在所有时间序列模型中，LSTM-RNN 模型对这些临床特征的预测准确率最高（MAE=0.057、RMSE=0.079、RS=0.0053、均方误差=0.0069）。
LSTM-RNN 模型以最高的准确率预测了接受 LCIG 治疗两年后的晚期 PD 患者的性别依赖性临床结局。
