Pilots

Oral Presentation: Old School Meets New School: Voice-Based, AI-Enabled Cognitive Rehabilitation for Dementia Care

This is part of the monthly MassAITC webinar series. Abstract: Cognitive rehabilitation therapy supports individuals living with mild cognitive impairment and early-stage dementia in maintaining and improving function in daily life. However, access remains limited due to constraints in the availability and scalability of trained therapists. Recent advances in artificial intelligence, combined with evolving reimbursement pathways for remote care in the United States, now make virtual delivery models increasingly viable, creating new opportunities to expand access to high-quality cognitive care. Moneta Health has developed a telephone-based cognitive rehabilitation platform that enables structured, personalized therapy sessions delivered remotely and overseen by licensed speech-language pathologists. The platform leverages AI-driven speech analysis and automated session orchestration to support consistent therapy delivery while preserving clinician oversight, enabling older adults to engage in care from their homes through a familiar…

Continue ReadingOral Presentation: Old School Meets New School: Voice-Based, AI-Enabled Cognitive Rehabilitation for Dementia Care

Preprint: Detecting Preclinical Alzheimer’s Disease Risk in Cognitively Normal Adults Using Speech Acoustics: Validation with Plasma p-Tau217 and APOE-ε4 Status

Authors: Mehrdad Dadgostar, Lindsay C. Hanford, Maryam Tavakoli, Steven E. Arnold, David H. Salat, Tatiana Sitnikova, Pia Kivisakk Webb, Jordan R. Green, Hengru Liu, Brian D. Richburg, Mariam Tkeshelashvili, Marziye Eshghi Abstract INTRODUCTION We tested whether spontaneous speech acoustics provide a scalable digital marker of biologically defined Alzheimer’s disease (AD) risk. METHODS Forty-nine cognitively unimpaired older adults were stratified within APOE genotype into Low-, Moderate-, and High-Risk groups based on log₁₀-transformed plasma p-tau217. Acoustic features were extracted from spontaneous speech and entered into multiclass SVM classifiers with leave-one-out cross-validation, with and without genetic-algorithm feature selection and age. Parallel models using neuropsychological measures were evaluated for comparison. Feature contributions were interpreted using SHAP. RESULTS Speech-based models substantially outperformed cognition-only models and exceeded chance performance for three-group classification (33.3%), achieving up to 77% accuracy compared with 47%…

Continue ReadingPreprint: Detecting Preclinical Alzheimer’s Disease Risk in Cognitively Normal Adults Using Speech Acoustics: Validation with Plasma p-Tau217 and APOE-ε4 Status

Publication: Validation of commercial sleep-tracking wearables and nearables in healthy young and older adults

Authors: M.E. Searles, A. Licata, M. Cucinotta, K. Kainec, and R.M.C. Spencer Abstract Study objectives: Changes in sleep with aging are associated with risk for Alzheimer’s and other neurological diseases, risk of accidents, and can be a predictor of health decline. For this reason, continuous sleep monitoring is of great interest for researchers, clinicians, and family members. The objective of this study was to assess the validity of consumer sleep-tracking devices in older relative to young adults. Methods: Analyses were based on one night of sleep assessed in young (19-24 years; n=13) and older adults (56-80 years; n=19). Participants wore sleep-tracking wearables (Fitbit Sense 2, Oura Ring) and nearables (Withings Sleep Mat, Sleep Score Max) were positioned nearby. Sleep measures were compared to polysomnography. Results: Results suggest that devices may be less accurate in older…

Continue ReadingPublication: Validation of commercial sleep-tracking wearables and nearables in healthy young and older adults

Publication: Replicable Bandits for Digital Health Interventions

Authors: Kelly W Zhang, Nowell Closser, Anna L Trella, Susan A Murphy Abstract Adaptive treatment assignment algorithms, such as bandit algorithms, are increasingly used in digital health intervention clinical trials. Frequently the data collected from these trials is used to conduct causal inference and related data analyses to decide how to refine the intervention, and whether to roll-out the intervention more broadly. This work studies inference for estimands that depend on the adaptive algorithm itself; a simple example is the mean reward under the adaptive algorithm. Specifically, we investigate the replicability of statistical analyses concerning such estimands when using data from trials deploying adaptive treatment assignment algorithms. We demonstrate that many standard statistical estimators can be inconsistent and fail to be replicable across repetitions of the clinical trial, even as the sample size grows large.…

Continue ReadingPublication: Replicable Bandits for Digital Health Interventions