Oral Presentation: Rewriting protein “grammar” to stop neurodegenerative disease before it starts
Presented virtually at ARPA-H BIOGAMI on February 20th, 2026 Source: https://arpa-h.gov/explore-funding/programs/biogami
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%…
Oral Presentation: Generative Optogenetics: Operant BioPharma
Presented at DARPA-GO in Washington, DC on January 7, 2026
Publication: Kinematic correlates of early speech motor changes in cognitively intact APOE-ε4 carriers: a preliminary study using a color-word interference task
Authors: Mehrdad Dadgostar, Lindsay C Hanford, Jordan R Green, Brian D Richburg, Averi Taylor Cannon, Nelson V Barnett, David H Salat, Steven E Arnold, Marziye Eshghi Abstract Introduction: Alzheimer's disease (AD) is the most prevalent form of dementia and a major public health challenge. In the absence of a cure, accurate and innovative early diagnostic methods are essential for proactive life and healthcare planning. Speech metrics have shown promising potential for identifying individuals with mild cognitive impairment (MCI) and AD, prompting investigation into whether speech motor features can detect elevated risk even prior to cognitive decline. This preliminary study examined whether speech kinematic features measured during a color-word interference task could distinguish cognitively normal APOE-ε4 carriers (ε4+) from non-carriers (ε4-). Methods: Sixteen cognitively normal older adults (n = 9 ε4+, n = 7 ε4-) completed…
Grant Funding: 1R41AG092186 – Restoring Self-Feeding with a Sensor Driven Robotic System
Project Narrative: The NIH STTR Phase I project aims to improve the Obi robotic feeding system with advanced technology, allowing it to autonomously deliver food to individuals with severe upper limb disabilities. This enhancement will provide a more independent eating experience, reduce caregiver burden, and has the potential to improve the quality of life for millions of people with mobility impairments. Source: 1R41AG092186-01A1 (NIH RePORTER)
Grant Funding: NIA Phase I SBIR Award
Abstract: This proposal responds to an acute challenge currently underserved by technology; the need to leverage novel approaches to develop cost-effective and responsive digital, mobile, website, and artificial intelligence (AI) tools to encourage participation in Alzheimer disease and related dementias (ADRD) clinical trials. With ADRD cases expected to double by 2060, efforts to ensure adequate participation in ADRD clinical trials is paramount to ensuring successful biomedical advances and drug development. Despite ongoing efforts to improve ADRD outcomes and clinical trial participation, no digital solution exists which has been purposefully designed and co-developed in partnership with patients at higher-risk of ADRD or with informal caregivers of ADRD patients critical in addressing challenges associated with trial participation. In response, this project utilizes approaches in digital tool development, AI, qualitative interviews and small group discussions, and use of…
Restoring Functional Eating in Late Stage Dementia
Jon Dekar, DESIN LLC, Zackory Erickson, CMU Robotics Institute. DESĪN LLC will enhance its existing Obi assistive feeding robot with AI-driven attention monitoring and redirection capabilities to support self-feeding in individuals with AD/ADRD who struggle with inattention. The project aims to demonstrate technical feasibility and clinical utility in long-term care settings, ultimately reducing caregiver burden and improving quality of life for affected individuals.