NIH Grants & Validation Studies

Why prospective validation matters

The Sultan Lab's evidence-engine research establishes feasibility in outpatient practice. The next question is whether guideline-concordant decision support transports across clinicians, patient mixes, and resource environments. NIH-funded prospective studies test exactly that.

R21, NIH PAR-25-310

An exploratory/developmental grant for prospective, multi-site validation across two outpatient settings with divergent resource profiles: a well-resourced specialty practice in New York City and a community-based child psychiatry clinic with more constrained access to subspecialty consultation.

• Primary outcome: Guideline Concordance Score, the proportion of clinical decisions aligning with AACAP, AAP, and FDA guidance
• Secondary outcomes: documentation completeness, time to first prescribing decision, clinician-reported usability
• Implementation analysis follows the Consolidated Framework for Implementation Research (CFIR)

R01, NIH PAR-25-283

A larger implementation study building on the R21 foundation, including a stepped-wedge implementation pilot across community prescribers, with structured deprescribing support and family-engagement workflows as part of the research design.

Lead institutions

Studies are led from the Sultan Lab for Mental Health Informatics at the Columbia University Department of Psychiatry, with infrastructure support from Columbia University Irving Medical Center, New York State Psychiatric Institute, and clinical site support at NewYork-Presbyterian.