John Mafi
University of California-Los Angeles, CA·Medicine & Clinical Research
Older adults with memory problems and dementia often receive medical care that does not help them and can cause harm. At the same time, artificial intelligence (AI) tools that could improve their care are reaching clinics with little evidence about whether they help or hurt.
- Fields
Medicine & Clinical Research
Public Health & Epidemiology
Computer Science
- Topics
Alzheimer's disease
dementia
mild cognitive impairment
- Grants
- 2 known grants, through Jul 2031
What they work on
- 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.
- Establish best practices for ethical and fair AI in aging care, including design studios that build in co-design and ethics early and continuous fairness monitoring after tools are deployed.
- Generate national estimates of trends, costs and harms of low-value care, such as routine benzodiazepine use, in older adults with mild cognitive impairment and dementia, linking Medicare claims with the Health and Retirement Study.
- Identify which older adults with cognitive impairment are most at risk of low-value care, and test with interrupted time series analysis whether payment reform and an education campaign reduced it.
More about the research
Both projects ask how the healthcare system can deliver safer, evidence-based care to people with Alzheimer's disease and related dementias (ADRD), using large health datasets.
Why it matters
About 7 million Americans live with dementia. This work could help them by producing evidence for health policies that cut harmful, unnecessary care, such as sedatives that raise fall risk, and lower wasted spending. It could also give clinicians and patients more trustworthy guidance on which AI decision-support tools are safe and fair, including for rural and other underserved older adults.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Narges Razavian
New York University, NY·Computer Science
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.
Nina Joyce
Brown University, RI·Public Health & Epidemiology
Characterize how crash risk changes over many years in older drivers with mild cognitive impairment, Alzheimer's disease or related dementias, using 13 years of Medicare claims linked to New Jersey licensing and crash records.
Vinay Kini
Weill Medical College of Cornell University, NY·Medicine & Clinical Research
Test whether commonly used claims-based measures of low-value care for patients with coronary artery disease are accurate by comparing them against the gold standard of medical chart review.
The school
University of California-Los Angeles: 84 labs on PI Pages, $1.9B a year on research, 803 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.