Learning which antipsychotic treatments work best for older adults with schizophrenia

Robust Learning Approaches for Assessing Effects and Effect Heterogeneity of Real World Antipsychotic Treatment Regimes in Elderly Persons with Schizophrenia

NIH-funded research Harvard Medical School · NIH-11235193

Using real-world medical records and advanced computer methods to learn which antipsychotic drugs, combinations, and treatment patterns are safest and most helpful for older adults with schizophrenia.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionHarvard Medical School NIH-funded
Lab location1 site (Boston, United States)
Project IDNIH-11235193 on NIH RePORTER

What this research studies

Researchers will analyze large linked healthcare datasets from racially and socially diverse older adults with schizophrenia who receive antipsychotic medications. They will apply modern machine-learning and causal inference methods to compare different drugs, sequences, combinations, and dosing patterns over time. The team will also connect patients' records to neighborhood-level measures like income and crime to see how social context affects adherence, safety, and benefits. The goal is to identify which treatments work best for which groups and under what circumstances.

Who could benefit from this research

Good fit: Older adults (typically age 65 and up) with a clinical diagnosis of schizophrenia who receive antipsychotic medications and whose care is captured in large U.S. health or public insurance databases would be the people represented by this work.

Not a fit: Younger people, individuals without schizophrenia, or those whose care is not included in the linked health databases (for example only privately insured or uninsured patients whose records aren't available) are unlikely to be represented or directly benefit from this project.

Why it matters

Potential benefit: Could help clinicians choose safer, more effective antipsychotic approaches tailored to older patients' health profiles and social circumstances.

How similar studies have performed: Prior studies using claims and electronic health records have provided useful safety and effectiveness signals, but this project applies newer machine-learning and causal methods to compare multiple treatment patterns and social-context effects, making it more advanced and partly novel.

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.
Last reviewed 2026-06-13 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.