Using computer learning to match people with the best antidepressant
Official title: Machine learning to personalize antidepressant treatment
Funded at Kaiser Foundation Research Institute · NIH-11403758 · Data updated 2026-11-12
This project uses computer learning to help match people starting antidepressants with the medication most likely to help them.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Kaiser Foundation Research Institute NIH-funded |
| Lab location | 1 site (Oakland, UNITED STATES) |
| Project start | July 1, 2024 |
| Project end | April 30, 2027 |
| Funding year | 2026 |
| Award (this year) | $765,573 |
| NIH project number | 5R01MH134831-03 |
| Project ID | NIH-11403758 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are people beginning a new antidepressant whose electronic health records are included in participating health systems.
✕Less likely to help
People without records in the participating systems, those seeking only non-medication treatments, or people with very unusual or complex medical histories may not benefit directly.
What this research studies
Researchers will analyze large sets of medical records from many patients who have taken antidepressants and use machine-learning tools to find patterns linked to success with particular drugs. They will combine information like symptoms, diagnoses, past treatments, doses, side effects, demographics, and available biological markers to train prediction models. The team will work to separate overall chances of getting better from benefits tied to specific medications so predictions are more useful. The work draws on harmonized data from the Mental Health Research Network and Kaiser to increase sample size and reliability.
Why it matters
Potential benefit: If successful, this could help people get the right antidepressant sooner, reducing months of trial-and-error, discouragement, and dropout.
How similar studies have gone: Previous studies have been small and mixed, so this larger, data-driven machine-learning approach is promising but not yet proven in routine care.
Where this research is happening
-
Kaiser Foundation Research Institute
Oakland, United States Active
Researchers
- Principal investigator: Simon, Gregory E. — Kaiser Foundation Research Institute
- Study coordinator: Simon, Gregory E.
Related research
Other NIH-funded projects on the same topics.
-
Understanding how where you live and personal factors during pregnancy affect a child’s risk for obesity and metabolic problems
This project looks at how neighborhood conditions and individual factors during pregnancy may influence a child’s risk of obesity and metabolic health as they grow.
-
Evidence-based practices for managing neonatal hypothermia in newborn nurseries
A doctor-led project will study how common newborn hypothermia affects babies in US nurseries and develop trusted guidelines to improve care.
-
Michigan Diabetes Project: A Peer-Led Self-Management Program for Adults with Type 2 Diabetes
A peer-led self-management program for adults with type 2 diabetes is being tested to see if it improves blood sugar control and daily diabetes care.
-
Kaiser Permanente NCORP: Community cancer care research network and trials
A community-based cancer research program partners with Kaiser Permanente to bring modern cancer trials and cancer-control studies to a diverse patient population.
-
Can cancer cachexia be reversed by targeting body-wide metabolic signals?
Researchers at Kaiser are exploring how cancer-related weight and muscle loss (cachexia) happens and whether new approaches can improve appetite, metabolism, and tissue health for people with cancer.
-
National Dental Practice-Based Research Network Coordinating Center
A nationwide network of dental professionals is testing ways to improve how dental care is delivered in real clinics through a central coordinating center.
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.