Narges Razavian
New York University, NY·Computer Science
Alzheimer's disease and related dementias affect more than 6 million people in the United States, yet many cases are diagnosed late or not at all. Most diagnoses happen in primary care, where few older adults are regularly screened for memory and thinking problems.
- Fields
Computer Science
Medicine & Clinical Research
Public Health & Epidemiology
- Topics
Alzheimer's disease
dementia
mild cognitive impairment
- Grants
- 2 known grants, through Jul 2028
What they work on
- Run a pilot embedded pragmatic clinical trial in primary care to test the acceptability, usability and adoption of an existing AI/machine learning tool and decision support for detecting cognitive impairment.
- Measure whether the electronic health record tool raises cognitive screening rates and improves diagnosis of mild cognitive impairment and dementia, plus cardiovascular prevention, at NYU Langone clinics serving 10,000+ older adults.
- Analyze whether uptake of screening, diagnosis and cardiovascular prevention differs across patient subgroups, including disadvantaged and racial and ethnic minority populations.
- Develop self-supervised learning methods that learn from large unlabeled real-world datasets pairing T1 and FLAIR MRI, PET imaging and electronic health records to detect dementia early.
- Build dementia detection models that generalize across scanner types and medically complex patients with heart and metabolic conditions, using new multimodal training objectives.
More about the research
Earlier detection gives patients and families time to plan, join clinical trials and get any available treatment. Two projects use artificial intelligence (AI) and routine clinical data to find dementia earlier. One builds better AI models from real-world records and brain scans. The other tests an AI tool inside everyday primary care.
Why it matters
Older adults in primary care, including disadvantaged and minority patients who are often diagnosed late, could gain earlier detection of dementia and timely care. Better screening could also improve heart disease prevention linked to dementia risk. The AI methods may extend to other diseases that have imaging and clinical markers.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
John Mafi
University of California-Los Angeles, CA·Medicine & Clinical Research
Build governance and infrastructure for rapid, reproducible evaluation of AI clinical decision-support tools for dementia, using UC Health Data Warehouse EHR and imaging data and the ATLAS genotyped biobank.
Sunny Lou
Washington University in St Louis, MO·Medicine & Clinical Research·Early-career
Embed S-PATH, a personalized AI model that predicts a patient's risk of needing a surgical blood transfusion, into the electronic health record as a clinical decision support tool for presurgical blood orders.
Evan Jordan
Indiana University, IN·Public Health & Epidemiology
Determine where, when, and what environmental stressors are experienced by 300 urban and 300 rural Indiana residents with mild cognitive impairment, using the STRIVE smartphone app, GPS tracking, and smartwatch data.
The school
New York University: 72 labs on PI Pages, $1.5B a year on research, 540 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.