Data modelling in corpus linguistics: How low may we go?

Voice biomarkers as indicators of cognitive changes in middle and later adulthood

Voice prosody measures have been linked with Alzheimer's disease (AD), but it is unclear whether they are associated with normal cognitive aging. We assessed relationships between voice measures and 10-year cognitive changes in the MIDUS national sample of middle-aged and older adults ages 42-92, with a mean age of 64.09 (standard deviation = 11.23) at the second wave. Seven cognitive tests were assessed in 2003-2004 (Wave 2) and 2013-2014 (Wave 3). Voice measures were collected at Wave 3 (N = 2585) from audio recordings of the cognitive interviews. Analyses controlled for age, education, depressive symptoms, and health. As predicted, higher jitter was associated with greater declines in episodic memory, verbal fluency, and attention switching. Lower pulse was related to greater decline in episodic memory, and fewer voice breaks were related to greater declines in episodic memory and verbal fluency, although the direction of these effects was contrary to hypotheses. Findings suggest that voice biomarkers may offer a promising approach for early detection of risk factors for cognitive impairment or AD.

How to do things with (thousands of) words: Computational approaches to discourse analysis in Alzheimer's disease

Natural Language Processing (NLP) is an ever-growing field of computational science that aims to model natural human language. Combined with advances in machine learning, which learns patterns in data, it offers practical capabilities including automated language analysis. These approaches have garnered interest from clinical researchers seeking to understand the breakdown of language due to pathological changes in the brain, offering fast, replicable and objective methods. The study of Alzheimer's disease (AD), and preclinical Mild Cognitive Impairment (MCI), suggests that changes in discourse (connected speech or writing) may be key to early detection of disease. There is currently no disease-modifying treatment for AD, the leading cause of dementia in people over the age of 65, but detection of those at risk of developing the disease could help with the identification and testing of medications which can take effect before the underlying pathology has irreversibly spread. We outline important components of natural language, as well as NLP tools and approaches with which they can be extracted, analysed and used for disease identification and risk prediction. We review literature using these tools to model discourse across the spectrum of AD, including the contribution of machine learning approaches and Automatic Speech Recognition (ASR). We conclude that NLP and machine learning techniques are starting to greatly enhance research in the field, with measurable and quantifiable language components showing promise for early detection of disease, but there remain research and practical challenges for clinical implementation of these approaches. Challenges discussed include the availability of large and diverse datasets, ethics of data collection and sharing, diagnostic specificity and clinical acceptability.

High amyloid burden is associated with fewer specific words during spontaneous speech in individuals with subjective cognitive decline

Self-perceived word-finding difficulties are common in aging individuals as well as in Alzheimer's Disease (AD). Language and speech deficits are difficult to objectify with neuropsychological assessments. We therefore aimed to investigate whether amyloid, an early AD pathological hallmark, is associated with speech-derived semantic complexity. We included 63 individuals with subjective cognitive decline (age 64 ± 8, MMSE 29 ± 1), with amyloid status (positron emission tomography [PET] scans n = 59, or Aβ_1-42 cerebrospinal fluid [CSF] n = 4). Spontaneous speech was recorded using three open-ended tasks (description of cookie theft picture, abstract painting and a regular Sunday), transcribed verbatim and subsequently, linguistic parameters were extracted using T-scan computational software, including specific words (content words, frequent, concrete and abstract nouns, and fillers), lexical complexity (lemma frequency, Type-Token-Ratio) and syntactic complexity (Developmental Level scale). Nineteen individuals (30%) had high levels of amyloid burden, and there were no differences between groups on conventional neuropsychological tests. Using multinomial regression with linguistic parameters (in tertiles), we found that high amyloid burden is associated with fewer concrete nouns (OR_middle (95%CI): 7.6 (1.4-41.2), OR_lowest: 6.7 (1.2-37.1)) and content words (OR_lowest: 6.3 (1.0-38.1). In addition, we found an interaction for education between high amyloid burden and more abstract nouns. In conclusion, high amyloid burden was modestly associated with fewer specific words, but not with syntactic complexity, lexical complexity or conventional neuropsychological tests, suggesting that subtle spontaneous speech deficits might occur in preclinical AD.