Brizzi Ana Carolina Brisola, Pinto Neto Osmar, Pedreiro Rodrigo Cunha de Mello, Moreira Lívia Helena
Biomedical Engineering Postgraduate Program, Anhembi Morumbi University, São José dos Campos 12247-016, Brazil.
Basic Institute of Biosciences, Taubaté University (Unitau), Taubaté 12020-040, Brazil.
Neurol Int. 2025 Aug 26;17(9):133. doi: 10.3390/neurolint17090133.
: Accurate differentiation of Parkinson's disease (PD) from healthy aging is crucial for timely intervention and effective management. Postural sway abnormalities are prominent motor features of PD. Quantitative stabilometry and machine learning (ML) offer a promising avenue for developing objective markers to support the diagnostic process. This study aimed to develop and validate high-performance ML models to classify individuals with PD and age-matched healthy older adults (HOAs) using a comprehensive set of stabilometric parameters. : Thirty-seven HOAs (mean age 70 ± 6.8 years) and 26 individuals with idiopathic PD (Hoehn and Yahr stages 2-3, on medication; mean age 66 years ± 2.9 years), all aged 60-80 years, participated. Stabilometric data were collected using a force platform during quiet stance under eyes-open (EO) and eyes-closed (EC) conditions, from which 34 parameters reflecting the time- and frequency-domain characteristics of center-of-pressure (COP) sway were extracted. After data preprocessing, including mean imputation for missing values and feature scaling, three ML classifiers (Random Forest, Gradient Boosting, and Support Vector Machine) were hyperparameter-tuned using GridSearchCV with three-fold cross-validation. An ensemble voting classifier (soft voting) was constructed from these tuned models. Model performance was rigorously evaluated using 15 iterations of stratified train-test splits (70% train and 30% test) and an additional bootstrap procedure of 1000 iterations to derive reliable 95% confidence intervals (CIs). : Our optimized ensemble voting classifier achieved excellent discriminative power, distinguishing PD from HOAs with a mean accuracy of 0.91 (95% CI: 0.81-1.00) and a mean Area Under the ROC Curve (AUC ROC) of 0.97 (95% CI: 0.92-1.00). Importantly, feature analysis revealed that anteroposterior sway velocity with eyes open (V-AP) and total sway path with eyes closed (TOD_EC, calculated using COP displacement vectors from its mean position) are the most robust and non-invasive biomarkers for differentiating the groups. : An ensemble ML approach leveraging stabilometric features provides a highly accurate, non-invasive method to distinguish PD from healthy aging and may augment clinical assessment and monitoring.
准确区分帕金森病（PD）与健康衰老对于及时干预和有效管理至关重要。姿势摇摆异常是PD突出的运动特征。定量稳定分析和机器学习（ML）为开发客观标志物以支持诊断过程提供了一条有前景的途径。本研究旨在开发和验证高性能的ML模型，使用一套全面的稳定分析参数对PD患者和年龄匹配的健康老年人（HOA）进行分类。37名HOA（平均年龄70±6.8岁）和26名特发性PD患者（Hoehn和Yahr分期2-3期，正在服药；平均年龄66岁±2.9岁），年龄均在60-80岁之间，参与了研究。在睁眼（EO）和闭眼（EC）条件下安静站立时，使用测力平台收集稳定分析数据，从中提取34个反映压力中心（COP）摇摆的时域和频域特征的参数。经过数据预处理，包括对缺失值进行均值插补和特征缩放，使用GridSearchCV和三倍交叉验证对三个ML分类器（随机森林、梯度提升和支持向量机）进行超参数调整。由这些调整后的模型构建了一个集成投票分类器（软投票）。使用15次分层训练-测试分割（70%训练和30%测试）以及额外的1000次迭代的自助程序来严格评估模型性能，以得出可靠的95%置信区间（CI）。我们优化后的集成投票分类器具有出色的判别能力，区分PD和HOA的平均准确率为0.91（95%CI：0.81-1.00），平均ROC曲线下面积（AUC ROC）为0.97（95%CI：0.92-1.00）。重要的是，特征分析表明，睁眼时的前后摇摆速度（V-AP）和闭眼时的总摇摆路径（TOD_EC，使用COP从其平均位置的位移向量计算）是区分两组最稳健且无创的生物标志物。一种利用稳定分析特征的集成ML方法提供了一种高度准确、无创的方法来区分PD与健康衰老，可能会增强临床评估和监测。
