Personalized depression treatment in primary care

Improving Outcomes in Depression in Primary Care

NIH-funded research Harvard Medical School · NIH-11087662

This project will use routine clinic information and computer learning to match people with moderate to severe depression to the antidepressant or brief behavioral therapy most likely to help them.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionHarvard Medical School NIH-funded
Lab location1 site (Boston, United States)
Project IDNIH-11087662 on NIH RePORTER

What this research studies

From your point of view, the team will collect information you can give in a regular clinic visit — symptoms, history, and simple measures — and use machine learning to build a rule that predicts whether an antidepressant or a short behavioral therapy (the Healthy Activity Program) is more likely to work. Patients will be assigned either according to this rule or by chance so researchers can compare who gets better and at what cost. The study aims to increase the number of people who reach remission and to spot those who should be referred quickly to specialist care. It will also compare the overall costs to see if choosing treatments this way saves resources.

Who could benefit from this research

Good fit: People with moderate to severe depression receiving care in participating primary care clinics who are willing to try an antidepressant or brief behavioral therapy are the ideal candidates.

Not a fit: Individuals already in specialty psychiatric care, those with only mild symptoms, or people requiring urgent inpatient or specialist treatment may not be included or benefit from this project.

Why it matters

Potential benefit: If successful, this could help more people with moderate to severe depression recover by guiding clinicians to the treatment most likely to work for each person.

How similar studies have performed: Prior trials have shown that generic antidepressants and the culturally adapted Healthy Activity Program can be effective in primary care, but using a machine‑learning precision treatment rule to pick the best option for each person is a newer approach with promising but not yet widespread proof.

Where this research is happening

Boston, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Conditions Disease remission
Last reviewed 2026-06-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.