三幅场景插画：老人对照屏幕跟读发声训练、面部与声谱图形的分析画面、以及手持设备的测试场景。它们与团队“声音作为研究对象”的方向主题相关；现有证据未将其对应到具体研究项目。
图背后的故事
帕金森病由多种风险因素引起，临床表现多样，不同因素与疾病特征之间的关系及其对患病的影响仍不明确。研究采用贝叶斯网络建立预测模型，使用 35 名患者与 26 名对照的数据训练；通过树增强网络完成结构学习，使用 Netica 软件进行参数学习。研究分别针对单音节、双音节、多音节及未分段音节建立四个模型，曲线下面积分别为 0.95、0.83、0.80 和 0.84。在单音节测试中，时长是最强预测特征，其后验概率为 92.70%；双音节测试中最低基频的预测表现最好，多音节与未分段音节中则分别为末端基频及最高基频。横断面比较显示，单音节测试中各变量的预测表现总体优于其他组别，单音节模型的预测表现最高。作者认为，这种网络方法可能成为帕金森病临床预测的有用工具。
论文摘要（中文译文 · 原文）
中文译文 帕金森病（PD）是一种由多种危险因素引起、临床表现多样的神经退行性疾病。然而，不同因素的作用、与PD相关的不同特征之间的关系，以及这些因素导致PD发病的程度仍不明确。我们采用贝叶斯网络构建预测模型，以35名患者与26名对照的数据训练预测系统；网络的结构学习与参数学习分别通过树增强朴素贝叶斯网络（TAN）与 Netica 软件完成。就音节层面构建了四个贝叶斯网络：单音节、双音节、多音节与未分音节。单音节、双音节、多音节与未分音节模型的曲线下面积（AUC）分别为0.95、0.83、0.80与0.84。单音节测试中PD的最佳预测因子是时长（duration），其后验概率为92.70%；双音节测试中最低基频（minimum f0，61.60%）预测效果最佳，多音节与未分音节测试中预测最佳的变量分别为末端基频（end f0，59.40%）与最大基频（maximum f0，58.40%）。横向比较显示，单音节测试中各变量的预测效果普遍高于其他测试组，单音节模型对PD的预测性能最高；在声学参数中，时长是单音节测试中预测PD患病最强的特征。我们认为这一网络方法将成为帕金森病临床预测的有用工具。
Parkinson's disease (PD) is a neurodegenerative disease with various clinical manifestations caused by multiple risk factors. However, the effect of different factors and relationships between different features related to PD and the extent of those factors leading to the incidence of PD remains unclear. we employed Bayesian network to construct a prediction model. The prediction system was trained on the data of 35 patients and 26 controls. The structure learning and parameter learning of Bayesian Network was completed through the tree-augmented network (TAN) and Netica software, respectively. We employed four Bayesian Networks in terms of the syllable, including monosyllables, disyllables, multisyllables and unsegmented syllables. The area under the curve (AUC) of monosyllabic, disyllabic, multisyllabic, and unsegmented-syllable models were 0.95, 0.83, 0.80 and 0.84, respectively. In the monosyllabic tests, the best predictor of PD was duration, the posterior probability of which was 92.70%. Meanwhile, minimum f0 (61.60%) predicted best in the disyllabic tests and the variables that predicted best in multisyllables and unsegmented syllables were end f0 (59.40%) and maximum f0 (58.40%). In the cross-sectional comparison, the prediction effect of each variable in the monosyllabic tests was generally higher than that of other test groups. The monosyllabic models had the highest predicted performance of PD. Among acoustic parameters, duration was the strongest feature in predicting the prevalence of PD in monosyllabic tests. We believe that this network methodology will be a useful tool for the clinical prediction of Parkinson's disease.