News & Events

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

Past Webinar – Advancing Fair & Effective AI for Older Adults

https://www.youtube.com/watch?v=67St-zDEzjk Abstract: Artificial intelligence holds promise to transform care for older adults, yet today’s AI systems routinely underperform for this population due to poor data representation, limited validation, and weak alignment with lived experience. Drawing on a six-month collaboration between the SCAN Foundation, CHAI will be synthesizing evidence from literature review, expert interviews, and multi-stakeholder roundtables to surface why AI fails older adults—and what must change. They will outline practical pathways for building equitable AI, including multimodal data integration, standardized validation, local testing, and patient-centered deployment. The talk concludes with a roadmap for developing trustworthy AI that meaningfully improves outcomes for aging populations. Biography: Lucy Orr-Ewing, Head of Policy & Strategy, Coalition for Health AI (CHAI) Lucy Orr-Ewing leads Policy and Research for CHAI, where she leads policy engagement at both the state and federal…

Continue ReadingPast Webinar – Advancing Fair & Effective AI for Older Adults

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…

Continue ReadingPublication: Kinematic correlates of early speech motor changes in cognitively intact APOE-ε4 carriers: a preliminary study using a color-word interference task