Correlating natural language processing and automated speech analysis with clinician assessment to quantify speech-language changes in mild cognitive impairment and Alzheimer's dementia.

BACKGROUND: Language impairment is an important marker of neurodegenerative disorders. Despite this, there is no universal system of terminology used to describe these impairments and large inter-rater variability can exist between clinicians assessing language. The use of natural language processing (NLP) and automated speech analysis (ASA) is emerging as a novel and potentially more objective method to assess language in individuals with mild cognitive impairment (MCI) and Alzheimer's dementia (AD). No studies have analyzed how variables extracted through NLP and ASA might also be correlated to language impairments identified by a clinician. METHODS: Audio recordings (n=30) from participants with AD, MCI, and controls were rated by clinicians for word-finding difficulty, incoherence, perseveration, and errors in speech. Speech recordings were also transcribed, and linguistic and acoustic variables were extracted through NLP and ASA. Correlations between clinician-rated speech characteristics and the variables were compared using Spearman's correlation. Exploratory factor analysis was applied to find common factors between variables for each speech characteristic. RESULTS: Clinician agreement was high in three of the four speech characteristics: word-finding difficulty (ICC = 0.92, p<0.001), incoherence (ICC = 0.91, p<0.001), and perseveration (ICC = 0.88, p<0.001). Word-finding difficulty and incoherence were useful constructs at distinguishing MCI and AD from controls, while perseveration and speech errors were less relevant. Word-finding difficulty as a construct was explained by three factors, including number and duration of pauses, word duration, and syntactic complexity. Incoherence was explained by two factors, including increased average word duration, use of past tense, and changes in age of acquisition, and more negative valence. CONCLUSIONS: Variables extracted through automated acoustic and linguistic analysis of MCI and AD speech were significantly correlated with clinician ratings of speech and language characteristics. Our results suggest that correlating NLP and ASA with clinician observations is an objective and novel approach to measuring speech and language changes in neurodegenerative disorders.

Patient Outcomes With Use of Computed Tomography Angiography in Acute Ischemic Stroke and Transient Ischemic Attack: A Systematic Review and Meta-Analysis.

Objectives It remains uncertain whether computed tomography angiography (CTA) in ischemic strokes and transient ischemic attacks (TIAs) benefits patient outcomes beyond those eligible for endovascular therapy. We conducted a systematic review and meta-analysis of observational studies and randomized controlled trials (RCTs) investigating the use of CTA against other imaging modalities for recurrent stroke, mortality, disability, emergency department (ED) revisits, or changes in management in ischemic stroke and TIA. (PROSPERO: 349590) Methods MEDLINE, Embase, and CENTRAL were searched. We included studies evaluating CTA against non-CTA imaging modalities for outcomes of interest in ischemic stroke or TIA. Two reviewers extracted data and assessed study quality. Data were pooled by the generic inverse variance method. Heterogeneity was assessed using Cochran's Q statistic and quantified by I2. Quality of the evidence was assessed by GRADE. Results We found 12 eligible cohort studies involving 17,481 patients, and no eligible RCTs. No changes were detected in recurrent stroke, mortality, or disability when CTA was compared against pooled imaging modalities, nor compared to non-contrast computed tomography (NCCT) alone. The evidence for each outcome was graded as low quality to very low quality. Conclusions CTA use was not associated with significant reductions in recurrent stroke, mortality, or disability in ischemic stroke and TIA patient compared with other imaging modalities. More high-quality studies are needed.

Subcortical hyperintensities in the cholinergic system are associated with improvements in executive function in older adults with coronary artery disease undergoing cardiac rehabilitation.

OBJECTIVE: Coronary artery disease (CAD) is frequently accompanied by white matter hyperintensities and executive dysfunction. Because acetylcholine is important in executive function, these symptoms may be exacerbated by subcortical hyperintensities (SH) located in cholinergic (CH) tracts. This study investigated the effects of SH on cognitive changes in CAD patients undergoing a 48-week cardiac rehabilitation program. METHODS: Fifty patients (age 66.5 ± 7.1 years, 84% male) underwent the National Institute of Neurological Disorders and Stroke - Canadian Stroke Network neurocognitive battery at baseline and 48 weeks. Patients underwent a 48-week cardiac program and completed neuroimaging at baseline. Subcortical hyperintensities in CH tracts were measured using Lesion Explorer. Repeated measures general linear models were used to examine interactions between SH and longitudinal cognitive outcomes, controlling for age, education, and max VO2 change as a measure of fitness. RESULTS: In patients with SH in CH tracts, there was a significant interaction with the Trail Making Test (TMT) part A and part B over time. Patients without SH improved on average 16.6 and 15.0% on the TMT-A and TMT-B, respectively. Patients with SH on average showed no improvements in either TMT-A or TMT-B over time. There were no significant differences in other cognitive measures. CONCLUSION: These results suggest that CAD patients with SH in CH tracts improve less than those without SH in CH tracts, over 48 weeks of cardiac rehabilitation. Thus, SH in CH tracts may contribute to longitudinal cognitive decline following a cardiac event and may represent a vascular risk factor of cognitive decline. © 2017 The Authors. International Journal of Geriatric Psychiatry Published by John Wiley & Sons Ltd.

White Matter Microstructural Integrity Is Associated with Executive Function and Processing Speed in Older Adults with Coronary Artery Disease.

OBJECTIVE: Coronary artery disease (CAD) is associated with an increased risk of cognitive decline. Although cerebral white matter (WM) damage predicts cognitive function in CAD, conventional neuroimaging measures only partially explain the effect of CAD on cognition. The purpose of this study was to determine if WM microstructural integrity and CAD using diffusion tensor imaging (DTI) correlates with cognitive function in older adults with CAD. METHODS: Forty-nine CAD patients (66 ± 7 years old, 86% male) underwent neurocognitive assessments using the cognitive battery recommended by the National Institute of Neurological Disorders and Stroke-Canadian Stroke Network for the study of vascular cognitive impairment. Composite scores for each cognitive domain were calculated. Microstructural integrity in normal-appearing WM was quantified as fractional anisotropy (FA) using DTI in nine bilateral and two interhemispheric WM tracts from the Johns Hopkins University WM Tractography Atlas. Linear regression models examined associations between FA and cognitive performance, controlling for age, sex, and education, with correction for multiple comparisons using a false discovery rate of 5%. RESULTS: Executive function was most significantly associated with FA in the left parahippocampal cingulum (ß = 0.471, t = 3.381, df = 44, p = 0.002) and left inferior fronto-occipital fasciculus (ß = 0.430, t = 2.984, df = 44, p = 0.005). FA was not associated with memory in any of the WM tracts examined. CONCLUSION: These results suggest that WM microstructural integrity may be an important neural correlate of executive function even in cognitively intact CAD patients. This study suggests WM damage may be relevant to subtle cognitive decline in a population that may have early neural risk for dementia.