Abstract:
Diagnostic tests for Parkinsonism based on speech samples have shown promising results. Although abnormal auditory feedback integration during speech production and impaired rhythmic organization of speech are known in Parkinsonism, these aspects have not been incorporated into diagnostic tests. This study aimed to identify Parkinsonism using a novel speech behavioral test that involved rhythmically repeating syllables under different auditory feedback conditions. The study included 30 individuals with Parkinson\'s disease (PD) and 30 healthy subjects. Participants were asked to rhythmically repeat the PA-TA-KA syllable sequence, both whispering and speaking aloud under various listening conditions. The results showed that individuals with PD had difficulties in whispering and articulating under altered auditory feedback conditions, exhibited delayed speech onset, and demonstrated inconsistent rhythmic structure across trials compared to controls. These parameters were then fed into a supervised machine-learning algorithm to differentiate between the two groups. The algorithm achieved an accuracy of 85.4%, a sensitivity of 86.5%, and a specificity of 84.3%. This pilot study highlights the potential of the proposed behavioral paradigm as an objective and accessible (both in cost and time) test for identifying individuals with Parkinson\'s disease.
摘要:
基于语音样本的帕金森病诊断测试显示出可喜的结果。尽管在Parkinsonism中已知语音产生过程中异常的听觉反馈整合和语音节奏组织受损,这些方面尚未纳入诊断测试。这项研究旨在使用一种新颖的言语行为测试来识别帕金森病,该测试涉及在不同的听觉反馈条件下有节奏地重复音节。该研究包括30名帕金森病(PD)患者和30名健康受试者。参与者被要求有节奏地重复PA-TA-KA音节序列,在各种听力条件下低语和大声说话。结果表明,患有PD的个体在听觉反馈条件改变下难以耳语和发音,表现出延迟的言语发作,与对照组相比,试验中的节律结构不一致。然后将这些参数输入到有监督的机器学习算法中,以区分两组。该算法取得了85.4%的准确率,灵敏度为86.5%,特异性为84.3%。这项初步研究强调了所提出的行为范式作为一种客观和可获得的(成本和时间)测试的潜力,用于识别患有帕金森病的个体。