A deep learning method to spot signs of cognitive problems in EHRs
Official title: A deep learning algorithm to detect signs of cognitive impairment in electronic health records
Funded at Massachusetts General Hospital · NIH-11333297 · Data updated 2026-11-12
A patient-friendly tool using artificial intelligence to help doctors identify cognitive impairment in people at risk for Alzheimer’s disease by analyzing electronic health records.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Massachusetts General Hospital NIH-funded |
| Lab location | 1 site (Boston, United States) |
| Project start | June 15, 2024 |
| Project end | May 31, 2029 |
| Funding year | 2026 |
| Award (this year) | $803,872 |
| NIH project number | 5R01AG082698-03 |
| Project ID | NIH-11333297 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults whose health records include potential or suspected cognitive concerns and are receiving care at participating hospitals.
✕Less likely to help
Patients with no signs of cognitive impairment or those outside the participating institutions may not directly benefit.
What this research studies
This project develops Decipher-AI, a two-layer AI system that reads clinical notes and health history from three large hospitals to identify signs of cognitive decline. It focuses on improving how we detect cognitive impairment related to Alzheimer’s disease using real patient data while ensuring privacy and rigorous validation. The goal is to create a reliable signal from patterns in notes, tests, and interactions to help clinicians recognize ADRD earlier. If successful, the approach could complement existing methods and support timely care planning for patients and families.
Why it matters
Potential benefit: If successful, it could enable earlier identification of cognitive impairment, leading to timely interventions and better planning for patients and caregivers.
How similar studies have gone: Other AI-based methods have shown promise in analyzing EHR data, but this project aims to enhance accuracy by combining note-level and patient-level signals across multiple institutions.
Where this research is happening
-
Massachusetts General Hospital
Boston, United States Active
Researchers
- Principal investigator: Das, Sudeshna — Massachusetts General Hospital
- Study coordinator: Das, Sudeshna
Related research
Other NIH-funded projects on the same topics.
-
Using deep learning to find signs of cognitive impairment in health records
This study is working on a smart computer program called Decipher-AI that helps doctors spot signs of memory problems related to Alzheimer's and other dementias by looking at patients' health records, making it easier to catch these issues early and accurately.
-
Using deep learning to predict mild cognitive impairment and Alzheimer's dementia
This study is working on a smart computer program that looks at brain scans to help doctors spot early signs of mild cognitive impairment and Alzheimer's, so they can provide better care for patients like you.
-
Improving Neurological Health with Brain Training for Mild Cognitive Impairment (INHANCE-MCI)
A computer-based brain training program is being tested to help people with mild cognitive impairment maintain thinking skills and daily functioning.
-
Integrative histo-genomic analysis to guide cancer risk and targeted therapies with interpretable AI
Researchers are developing an advanced AI-powered approach to map genetic and cellular patterns across breast and cervical cancers to help tailor treatments.
-
Predicting how antimalarial drug resistance spreads with AI
A powerful AI model will be built to forecast how resistance to antimalarial drugs might spread in Africa and beyond, helping clinicians and public health teams stay ahead of outbreaks.
-
Global picture of dementia risk and memory loss across the world
A large international effort gathers data from many studies to understand how dementia and memory problems develop around the world, using shared information to reveal patterns and risk factors.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.