Reproductive Markers in Alzheimer's Disease Progression: The Framingham Heart Study.

BACKGROUND: Reproductive status, such as the age of menarche or menopause, may be linked to cognitive abilities and risk for incident Alzheimer's disease (AD) but the evidence is conflicting. It is also not fully known if these factors interact with cortical beta-amyloid deposition. OBJECTIVES: To study the relationship between reproductive risks, sex hormone markers and risk for decline in specific cognitive domains in women. DESIGN, SETTING AND PARTICIPANTS: We analyzed the association of reproductive markers (age at menarche, number of births, age at menopause, sex hormone-binding globulin, estradiol, estrone, total testosterone, free testosterone) with incident AD and annualized cognitive decline in the community-based longitudinal Framingham Heart Study (FHS) Offspring women 60 years and older (n=772, mean age 68 years, mean follow-up 10.7 ± 3 years). We used the Cox proportional hazards regression model and linear regression model, adjusting for covariates. OUTCOME MEASURES: Incident AD dementia as well as the annualized change in memory, language, attention and executive functions. RESULTS: Older age at menopause was associated with a lower risk of incident AD dementia (p = 0.047, 6% lower risk per older year) after adjusting for baseline age, education, hormone therapy status, and MMSE score. Older age at menopause was significantly associated with a slower annualized decline in memory (beta = 0.085, p = 0.00059). The lower level of plasma Aß42 was also associated with a higher risk of incident AD (HR = 0.97, 95% CI = 0.95, 0.99; p = 0.0039) but there was no significant interaction effect with age at menarche, age at menopause or plasma sex hormone levels. CONCLUSION: Younger age at menopause is a risk factor for late-life memory decline and incident AD. This risk appears to be independent of Aß42 pathology. Further studies to understand the biological and social mechanisms underlying the differential effects of reproductive risks are warranted.

Cognitive Digital Biomarkers from Automated Transcription of Spoken Language.

BACKGROUND: Although patients with Alzheimer's disease and other cognitive-related neurodegenerative disorders may benefit from early detection, development of a reliable diagnostic test has remained elusive. The penetration of digital voice-recording technologies and multiple cognitive processes deployed when constructing spoken responses might offer an opportunity to predict cognitive status. OBJECTIVE: To determine whether cognitive status might be predicted from voice recordings of neuropsychological testing. DESIGN: Comparison of acoustic and (para)linguistic variables from low-quality automated transcriptions of neuropsychological testing (n = 200) versus variables from high-quality manual transcriptions (n = 127). We trained a logistic regression classifier to predict cognitive status, which was tested against actual diagnoses. SETTING: Observational cohort study. PARTICIPANTS: 146 participants in the Framingham Heart Study. MEASUREMENTS: Acoustic and either paralinguistic variables (e.g., speaking time) from automated transcriptions or linguistic variables (e.g., phrase complexity) from manual transcriptions. RESULTS: Models based on demographic features alone were not robust (area under the receiver-operator characteristic curve [AUROC] 0.60). Addition of clinical and standard acoustic features boosted the AUROC to 0.81. Additional inclusion of transcription-related features yielded an AUROC of 0.90. CONCLUSIONS: The use of voice-based digital biomarkers derived from automated processing methods, combined with standard patient screening, might constitute a scalable way to enable early detection of dementia.