Predicting Pain Recovery with a Multimodal AI using Harmonized Health Records
Official title: Predicting Pain Recovery: A Multimodality Machine-learning Approach using Harmonized Electronic Health Record Data
Funded at Mayo Clinic Arizona · NIH-11600236 · Data updated 2026-11-12
Aging patients with headaches will be helped by a new AI tool that uses medical records and brain images from Mayo Clinic and VA to predict who might have persistent pain.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Mayo Clinic Arizona NIH-funded |
| Lab location | 1 site (Scottsdale, United States) |
| Project start | September 15, 2025 |
| Project end | September 14, 2027 |
| Funding year | 2026 |
| Award (this year) | $1,124,798 |
| NIH project number | 3OT2OD037955-01S1 |
| Project ID | NIH-11600236 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults with headache diagnoses (migraine, post-traumatic headache, post-stroke headache) whose electronic health records and brain imaging are available.
✕Less likely to help
Patients without available brain imaging or incomplete records may not benefit from the model.
What this research studies
This project will combine harmonized electronic health records and brain imaging from two large clinics to build a predictive model for pain recovery in people with migraine and related headaches. It will develop separate models for each dataset first, then create a unified multimodal model that fuses different data types even when some information is missing. The team will use supervised learning and a vision-language approach to extract meaningful features and connect data across modalities, with plans to share code and involve stakeholders in evaluating multimodal AI for chronic pain. Validation will compare the harmonized model to models built from each dataset alone, aiming for clinically useful predictions that can generalize in real-world settings.
Why it matters
Potential benefit: If successful, patients and clinicians could receive better forecasts of pain recovery to tailor treatments and follow-up.
How similar studies have gone: Previous multimodal AI efforts show promise in clinical prediction, but this study emphasizes harmonization across two major healthcare systems.
Where this research is happening
-
Mayo Clinic Arizona
Scottsdale, United States Active
Researchers
- Principal investigator: Chong, Catherine Daniela — Mayo Clinic Arizona
- Study coordinator: Chong, Catherine Daniela
Related research
Other NIH-funded projects on the same topics.
-
Understanding immune signals in ALS to guide future therapies
A Mayo Clinic team will study how the immune system sees proteins in the brain of people with ALS and related conditions, to find clues for better treatments.
-
Determinants of Pathogenic Anti-PF4 Antibody–Mediated Platelet Activation
This project looks at why certain anti-PF4 antibodies in people cause harmful blood clots and how to better diagnose and treat those cases.
-
Understanding how a type of immune cell called ILC2s affect asthma in adults
This grant studies how group 2 innate lymphoid cells influence asthma in adults to help identify new ways to manage airway inflammation.
-
EHMT1 Variants and Kleefstra Syndrome: How Structure Shapes Neurodevelopmental Risks
A small NIH grant will explore how genetic changes in EHMT1 affect brain development in Kleefstra Syndrome using computer models and analysis of protein structure.
-
Targeting epigenomic regulators to assault pancreatic cancer replication stress
This research tests a new way to treat pancreatic cancer by blocking key epigenetic regulators during DNA replication to make cancer cells less able to cope with replication stress.
-
New ideas to understand, diagnose, and treat heparin-induced thrombocytopenia
A Mayo Clinic led study will look at the different kinds of HIT antibodies to improve diagnosis and treatment for people with HIT.
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.