Identification of digital voice biomarkers for cognitive health.
Identification of digital voice biomarkers for cognitive health.
复制标题
DOI：
10.37349/emed.2020.00028
复制
发表时间：
2020
影响因子：
--
通讯作者：
Au R
中科院分区：
文献类型：
--
作者：
Lin H;Karjadi C;Ang TFA;Prajakta J;McManus C;Alhanai TW;Glass J;Au R
人的声音蕴含着丰富的信息。很少有纵向研究来调查语音监测认知健康的潜力。这项研究的目的是确定可预测未来痴呆症的声音生物标志物。参与者是从弗雷明汉心脏研究中招募的。记录对神经心理学测试的声音反应，然后将其分类以识别参与者的声音片段。使用 OpenSMILE 工具包 (v2.1) 提取声学特征。通过 Cox 比例风险模型评估每个声学特征与痴呆症的关联。我们的研究包括 4, 849 名参与者（平均年龄 63 ± 15 岁，54.6% 为女性）的 6, 528 段录音。大多数参与者（71.2%）有一份录音，23.9%有两份录音，其余参与者（4.9%）有三份或更多录音。尽管在检查时都没有症状，但患有痴呆症的参与者往往比没有患痴呆症的参与者的节段更短（P < 0.001）。此外，经过多次测试调整后，14 个声学特征与痴呆症显着相关（P < 0.05/48 = 1 × 10−3）。最重要的声学特征是 jitterDDP_sma_de (P = 7.9 × 10−7)，它表示差分帧到帧抖动。还构建了基于语音的线性分类器，能够预测痴呆症的发生，曲线下面积为 0.812。确定了与无症状参与者中痴呆症相关的多种声音和语言特征，这些特征可用于建立更好的被动认知健康监测预测模型。
Human voice contains rich information. Few longitudinal studies have been conducted to investigate the potential of voice to monitor cognitive health. The objective of this study is to identify voice biomarkers that are predictive of future dementia. Participants were recruited from the Framingham Heart Study. The vocal responses to neuropsychological tests were recorded, which were then diarized to identify participant voice segments. Acoustic features were extracted with the OpenSMILE toolkit (v2.1). The association of each acoustic feature with incident dementia was assessed by Cox proportional hazards models. Our study included 6, 528 voice recordings from 4, 849 participants (mean age 63 ± 15 years old, 54.6% women). The majority of participants (71.2%) had one voice recording, 23.9% had two voice recordings, and the remaining participants (4.9%) had three or more voice recordings. Although all asymptomatic at the time of examination, participants who developed dementia tended to have shorter segments than those who were dementia free (P < 0.001). Additionally, 14 acoustic features were significantly associated with dementia after adjusting for multiple testing (P < 0.05/48 = 1 × 10−3). The most significant acoustic feature was jitterDDP_sma_de (P = 7.9 × 10−7), which represents the differential frame-to-frame Jitter. A voice based linear classifier was also built that was capable of predicting incident dementia with area under curve of 0.812. Multiple acoustic and linguistic features are identified that are associated with incident dementia among asymptomatic participants, which could be used to build better prediction models for passive cognitive health monitoring.