Header
- Model name
- Thyroid Dysfunction
- Developer
- Zenlo LLC
- Release stage
- Research Tool (not FDA-cleared)
- Version
- 1.0
- Availability
- United States
- Regulatory status
- Not applicable — academic and transparency positioning
- Pattern slug
- thyroid_dysfunction
- Biomarkers
- TSH, FT3, FT4
This document follows the CHAI Applied Model Card format (v0.1).
Summary
The Thyroid Dysfunction pattern flags abnormal thyroid-stimulating hormone, free T3, and free T4 values in adult laboratory panels, signaling potential hypo- or hyperthyroid states for physician review. Deterministic comparison against registry reference ranges fires the pattern when TSH or free hormone levels are out of range. Claude Haiku 4.5 provides narrative context on which thyroid indices are abnormal. Intended for licensed functional-medicine physicians as supportive clinical decision support, the pattern does not interpret thyroid antibodies, nodules, or medication dosing. It highlights laboratory thyroid signals that warrant correlation with symptoms, physical exam, and repeat or expanded thyroid testing — not a standalone endocrine diagnosis.
Uses & Directions
Intended use
Clinical decision support for licensed physicians reviewing thyroid function tests in adult panels.
Primary users
Licensed functional medicine physicians and similarly qualified clinicians.
How to use
Correlate flagged thyroid labs with symptoms, medications, pregnancy status, and antibody testing as indicated.
Target population
Adults aged 18 and older in the United States.
Out of scope
- Direct patient use without physician oversight
- Pediatric populations and neonatal screening
- Standalone diagnosis or levothyroxine dosing
- Thyroid nodule or cancer evaluation
Warnings
Clinical risk level
Low — supportive tool; the treating physician retains full clinical judgment and responsibility.
Known limitations
- Does not incorporate thyroid antibodies (TPO, TgAb) or thyroglobulin.
- Single time-point labs may not reflect thyroid status during acute illness.
- Reference ranges vary by assay and trimester in pregnancy.
Validation note
Validation pending — a Tier A NHANES validation run has not yet been completed for this pattern. Distribution, agreement, and fairness results will be published here when available.
Trust Ingredients
AI system facts
- Deterministic pattern detector (thyroid_dysfunction) plus Claude Haiku 4.5 for narrative synthesis
- Primary inputs: TSH, free T3, and free T4 from structured laboratory extraction.
- Output: Pattern flag plus narrative on thyroid index abnormalities.
Security & compliance
- Anthropic Business Associate Agreement with zero-data-retention configuration
- HIPAA-aligned design; no patient data used for model training
Ongoing maintenance
Versioned, transparent, and reproducible via a public independent audit harness (see Resources).
Transparency
Self-funded development; no third-party sponsor for this pattern card.
Key Metrics
Usefulness / Efficacy
Zenlo's detection approach was benchmarked across five models in a separate study; see the medRxiv preprint in Resources. No per-pattern efficacy metric is published for this pattern.
Source: 5-model benchmark, medRxiv MEDRXIV/2026/346284
Fairness / Equity
Validation pending — a Tier A NHANES validation run has not yet been completed for this pattern. Distribution, agreement, and fairness results will be published here when available.
Safety / Reliability
- Supportive-only; not intended as a standalone diagnostic
- Physician authorization required before clinical use
- Deterministic detector is reproducible for inputs: TSH, FT3, FT4
Resources
- medRxiv preprint MEDRXIV/2026/346284 — 5-model benchmark (system-level detector evaluation)
- JAMIA Open submission JAMIO-2026-0120 (under review)
- Independent audit harness: github.com/dimashibakov/zenlo-audit — reproducibility manifest, NHANES 2015–2016 cycle, harness commit c10afe8
Footer
Note: The mention or sharing of any examples, products, organizations, or individuals does not indicate any endorsement of those examples, products, organizations, or individuals by the Coalition for Health AI (CHAI).