Title: AI-Assisted Prediction of Healthy Aging and Alzheimer's Disease Progression Authors: Mike Krepps, Kushan Aryasomayajula, Juan Cuevas, Hannah Webster, Pia Kivisakk, Sudeshna Das, Chaitanya Gupta, Steven Arnold
Title: Leveraging Digital Cognitive Rhythms to Detect ADRD Risk in Family Caregivers Authors: Yeonsu Song, Alexander Demos, Alexandra Konig, Raeanne Moore
Title: TRIALCHAT: Development of an AI Agent Companion to Encourage Participation in ADRD Clinical Trail Authors: Tim Mackey, Joshua Yang, Tiana McMann, Mingxiang Cai, Zhuoran Li, Jiawei Li, Qing Xu
Presented at the Healthcare Information and Management Systems Society 2026 Annual Meeting Abstract: Older adults remain underrepresented in Alzheimer's disease and related dementias (ADRD) clinical trials despite bearing much of the disease burden. TrialChat is an AI-powered digital navigator addressing this gap through a conversational chatbot powered by an agentic AI framework and machine learning-based trial matching algorithm. Developed by S-3 Research LLC and CSU Fullerton, and supported by the U.S. National Institute on Aging under the NIH AITC program, TrialChat delivers personalized education and clinical trial recommendations via web and mobile platforms. What distinguishes TrialChat is its co-design approach: older adults and caregivers directly shape its language, flow, and features, elevating voices often overlooked in digital health while designed for commercialization and real-world application. This session shares TrialChat's architecture, early insights, and lessons for scaling inclusive, AI-enabled clinical trial engagement tools across health systems. Source: https://app.himssconference.com/event/himss-2026/planning/UGxhbm5pbmdfNDM2NTAzMQ==
Presented virtually at ARPA-H BIOGAMI on February 20th, 2026 Source: https://arpa-h.gov/explore-funding/programs/biogami
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%…
Presented at DARPA-GO in Washington, DC on January 7, 2026