Header
- Model name
- Iron Deficiency
- 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
- iron_deficiency
- Biomarkers
- FERR, IRON, TIBC, IRONSAT
This document follows the CHAI Applied Model Card format (v0.1).
Summary
The Iron Deficiency pattern evaluates iron-status markers — ferritin, serum iron, total iron-binding capacity, and iron saturation — to flag laboratory profiles consistent with depleted iron stores or functional iron deficiency in adults. Deterministic rules apply pattern-specific thresholds and polarity (low ferritin, low iron saturation, elevated TIBC). Claude Haiku 4.5 synthesizes a physician-facing narrative describing which iron markers contributed. For licensed functional-medicine physicians, this is supportive clinical decision support: it does not diagnose anemia subtype, assess bleeding sources, or replace hematology consultation. The pattern prompts review of dietary intake, menstrual or GI blood loss, and correlation with hemoglobin indices from the separate Anemia pattern.
Uses & Directions
Intended use
Clinical decision support for licensed physicians evaluating iron-status marker patterns in adult panels.
Primary users
Licensed functional medicine physicians and similarly qualified clinicians.
How to use
Review iron markers alongside CBC indices, symptoms, and dietary or bleeding history. Physician authorization required.
Target population
Adults aged 18 and older in the United States.
Out of scope
- Direct patient use without physician oversight
- Pediatric populations
- Standalone diagnosis of anemia etiology
- Management of hemochromatosis or iron overload
Warnings
Clinical risk level
Low — supportive tool; the treating physician retains full clinical judgment and responsibility.
Known limitations
- Ferritin is an acute-phase reactant; inflammation can mask iron deficiency.
- Does not assess occult bleeding or malabsorption directly.
- Thresholds may vary by assay and population.
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 (iron_deficiency) plus Claude Haiku 4.5 for narrative synthesis
- Primary inputs: Ferritin, serum iron, TIBC, and iron saturation from structured extraction.
- Output: Pattern flag plus narrative on iron-status 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: FERR, IRON, TIBC, IRONSAT
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).