From the Linguistic Data Consortium (S.C., M.Y.L.) and Department of Neurology (K.A.Q.C., S.S., S.A., D.J.I., M.G., N.N.), University of Pennsylvania, Philadelphia.
Neurology. 2022 Jul 25;99(4):e313-e322. doi: 10.1212/WNL.0000000000200581.
We compared digital speech and language features of patients with amnestic Alzheimer disease (aAD) or logopenic variant primary progressive aphasia (lvPPA) in a biologically confirmed cohort and related these features to neuropsychiatric test scores and CSF analytes.
We included patients with aAD or lvPPA with CSF (phosphorylated tau ([p-tau]/β-amyloid [Aβ] ≥0.09, and total tau/Aβ ≥0.34) or autopsy confirmation of AD pathology and age-matched healthy controls (HC) recruited at the Frontotemporal Degeneration Center of the University of Pennsylvania for a cross-sectional study. We extracted speech and language variables with automated lexical and acoustic pipelines from participants' oral picture descriptions. We compared the groups and correlated distinct features with clinical ratings and CSF p-tau levels.
We examined patients with aAD (n = 44; age 62 ± 8 years; 24 women; Mini-Mental State Examination [MMSE] score 21.1 ± 4.8) or lvPPA (n = 21; age 64.1 ± 8.2 years; 11 women; MMSE score 23.0 ± 4.2) and HC (n = 28; age 65.9 ± 5.9 years, 15 women; MMSE score 29 ± 1). Patients with lvPPA produced fewer verbs (10.5 ± 2.3; = 0.001) and adjectives (2.7 ± 1.3, = 0.019) and more fillers (7.4 ± 3.9; = 0.022) with lower lexical diversity (0.84 ± 0.1; = 0.05) and higher pause rate (54.2 ± 19.2; = 0.015) than individuals with aAD (verbs 12.5 ± 2; adjectives 3.8 ± 2; fillers 4.9 ± 4.5; lexical diversity 0.87 ± 0.1; pause rate 45.3 ± 12.8). Both groups showed some shared language impairments compared with HC. Word frequency (MMSE score: β = -1.6, = 0.009; Boston Naming Test [BNT] score: β = -4.36, < 0.001), adverbs (MMSE score: β = -1.9, = 0.003; BNT score: β = -2.41, = 0.041), pause rate (MMSE score: β = -1.21, = 0.041; BNT score: β = -2.09, = 0.041), and word length (MMSE score: β = 1.75, = 0.001; BNT score: β = 2.94, = 0.003) were significantly correlated with both MMSE and BNT scores, but other measures were not correlated with MMSE and/or BNT score. Prepositions ( = -0.36, = 0.019), nouns ( = -0.31, = 0.047), speech segment duration ( = -0.33, = 0.032), word frequency ( = 0.33, = 0.036), and pause rate ( = 0.34, = 0.026) were correlated with patients' CSF p-tau levels.
Our measures captured language and speech differences between the 2 phenotypes that traditional language-based clinical assessments failed to identify. This work demonstrates the potential of natural speech in reflecting underlying variants with AD pathology.
我们比较了遗忘型阿尔茨海默病（aAD）或语义性原发性进行性失语症（lvPPA）患者的数字语音和语言特征，并将这些特征与神经心理学测试评分和 CSF 分析物相关联。
我们纳入了宾夕法尼亚大学额颞叶变性中心招募的经 CSF（磷酸化 tau([p-tau]/β-淀粉样蛋白 [Aβ]≥0.09，总 tau/Aβ≥0.34）或尸检证实的 AD 病理的 aAD 或 lvPPA 患者，以及年龄匹配的健康对照者（HC），进行了一项横断面研究。我们从参与者的口头图片描述中提取语音和语言变量，使用自动词汇和声学管道。我们比较了各组，并将不同的特征与临床评分和 CSF p-tau 水平相关联。
我们检查了 44 例 aAD 患者（年龄 62±8 岁；24 名女性；简易精神状态检查 [MMSE]评分 21.1±4.8）、21 例 lvPPA 患者（年龄 64.1±8.2 岁；11 名女性；MMSE 评分 23.0±4.2）和 28 例 HC（年龄 65.9±5.9 岁，15 名女性；MMSE 评分 29±1）。与 aAD 患者相比，lvPPA 患者产生的动词（10.5±2.3； = 0.001）和形容词（2.7±1.3， = 0.019）更少，填充词（7.4±3.9； = 0.022）更多，词汇多样性（0.84±0.1； = 0.05）更低，停顿率（54.2±19.2； = 0.015）更高。与 HC 相比，两组患者的语言障碍均存在一些共同的表现。词频（MMSE 评分：β=-1.6， = 0.009；波士顿命名测试 [BNT]评分：β=-4.36， < 0.001）、副词（MMSE 评分：β=-1.9， = 0.003；BNT 评分：β=-2.41， = 0.041）、停顿率（MMSE 评分：β=-1.21， = 0.041；BNT 评分：β=-2.09， = 0.041）和词长（MMSE 评分：β=1.75， = 0.001；BNT 评分：β=2.94， = 0.003）与 MMSE 和 BNT 评分显著相关，但其他指标与 MMSE 和/或 BNT 评分不相关。介词（ = -0.36， = 0.019）、名词（ = -0.31， = 0.047）、语音段持续时间（ = -0.33， = 0.032）、词频（ = 0.33， = 0.036）和停顿率（ = 0.34， = 0.026）与患者的 CSF p-tau 水平相关。
我们的测量方法捕捉到了两种表型之间的语言和语音差异，而传统的基于语言的临床评估未能识别这些差异。这项工作表明，自然语音具有反映 AD 病理下潜在变异的潜力。
