As World Alzheimer’s Month this September highlights the urgent need for earlier detection and better support for patients with Alzheimer’s disease and related dementias and their caregivers, Maryam Zolnoori, PhD, brings rigorous, high-impact research to the forefront. Her work leverages artificial intelligence (AI) to detect subtle changes in speech that signal cognitive decline long before symptoms become apparent.
Zolnoori is an assistant professor at Columbia University School of Nursing with training in biomedical informatics. She has authored many peer-reviewed publications, 42 as first or senior author, in leading journals including the Journal of the American Medical Informatics Association, Artificial Intelligence in Medicine, and Nature Digital Medicine. Her research bridges clinical informatics, AI, and health equity, with a central focus on speech as a scalable, accessible biomarker for cognitive health.
Her recognition includes awards from the Food and Drug Administration’s Center of Excellence in Regulatory Science and Innovation and an Intramural Research Training award from the National Library of Medicine at the National Institutes of Health. She has also been recognized by Columbia’s Center of Artificial Intelligence Technology in collaboration with Amazon for innovative work using speech data to build risk-identification models.
Supported by the National Institute of Aging (NIA), the a2-Collective for AI Technology in Aging, and Columbia’s Center for Interdisciplinary Research on Alzheimer’s Disease Disparities, Zolnoori leads multidisciplinary collaborations aimed at improving early detection of mild cognitive impairment and reducing disparities among racially and ethnically diverse populations. Her group develops explainable, clinically grounded models and prototypes for integration into care settings, such as home health care, to support equitable screening and timely follow-up.
Her team earned three Recognition Awards in both Phase 2 and Phase 3 of the NIA PREPARE Challenge for the performance of their speech-based screening algorithm, the clarity and clinician-friendly design of their explainability interface for clinical, linguistic, and acoustic risk factors, and the successful development of a real-world implementation pathway, reflecting the innovation and practical promise of these approaches.
Selected Recent Publications
Maryam Zolnoori’s Innovative Approaches to Alzheimer’s Detection
Selected Recent Publications
- National Institute on Aging PREPARE Challenge: Early Detection of Cognitive Impairment Using Speech-The Speech CARE Solution
- ADscreen: A speech processing-based screening system for automatic identification of patients with Alzheimer’s disease and related dementia
- LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data
- Beyond electronic health record data: leveraging natural language processing and machine learning to uncover cognitive insights from patient-nurse verbal communications
- Decoding disparities: evaluating automatic speech recognition system performance in transcribing Black and White patient verbal communication with nurses in home healthcare
- HomeADScreen: developing Alzheimer’s disease and related dementia risk identification model in home healthcare
Suggested Story Angles and Media Topics for World Alzheimer’s Month
- How speech analysis and AI-driven tools are transforming early detection of Alzheimer’s disease
- Why early cognitive screening in home health care settings is essential and often overlooked
- What patient-clinician communication can reveal about cognitive decline
- The promise and limitations of AI in dementia detection and monitoring
- Equity considerations when using AI tools to identify Alzheimer’s risk in diverse populations
- How delayed start-of-care contributes to poorer outcomes in dementia care
- The future of cognitive impairment research
