From Narratives to Metrics — Applied AI in IDD Practice
Turning qualitative observations into structured behavioral data.
This page is take-home material from a poster presentation at the AAIDD 2026 Annual Meeting in Chicago. AAIDD — the American Association on Intellectual and Developmental Disabilities — is the field’s primary professional society for clinicians, researchers, and educators. The resources below extend that conference work to anyone applying AI in IDD practice.
Three take-home resources for IDD professionals exploring AI-assisted analysis of qualitative data:
- Three ready-to-use prompt templates for extracting structured metrics from caregiver and clinician narratives
- A two-path de-identification guide
- An output evaluation framework
Three Prompt Templates
Custom behavior goal scoring · Multi-dimensional entry scoring · Pattern analysis across scored entries
Read online→Two-Path De-identification Guide
The two HIPAA-defensible paths for using AI with patient material — a BAA-covered tool, or a local redaction tool plus an IDD-specific manual review. Includes tool recommendations (CamoText, Lacuna, BAA-covered options) and the IDD second-pass checklist for what consumer-grade redaction can’t catch.
Read online→Output Evaluation Framework
A short rubric for clinicians and educators to validate AI-generated content — covering model selection, grounding, bias, and actionability.
Read online→Want to talk?
If your organization is exploring AI integration in IDD services — clinical documentation, behavioral data analysis, family-facing tools — I’d be glad to compare notes. I do consulting on AI architecture and LLM workflows for HIPAA-regulated environments.
Doug Kerwin · Founder, VillageMetrics
doug@villagemetrics.com · villagemetrics.com
This material is educational and not clinical guidance. AI tools should supplement, not replace, professional clinical judgment. © 2026 VillageMetrics.