Zenlo
About Engine Database Cases
ds@zenlo.app Request a signatureRequest
Patterns
Structural · validation pending

Transparency · CHAI Applied Model Card

Iron Deficiency

CHAI Applied Model Card (v0.1) for the Iron Deficiency pattern in Zenlo Labs. This document is not CHAI-certified or CHAI-endorsed.

Header

Model nameIron Deficiency
DeveloperZenlo LLC
Release stageResearch Tool (not FDA-cleared)
Versionv0.1
AvailabilityUnited States
Regulatory statusNot applicable — academic and transparency positioning
Pattern slugiron_deficiency
BiomarkersFerritin, Serum Iron, Total Iron Binding Capacity, Iron Saturation

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 10.64898/2026.02.13.26346284.

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 10.64898/2026.02.13.26346284 — 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

Note: The mention or sharing of any examples, products, organizations, or individuals does not indicate any endorsement by the Coalition for Health AI (CHAI). Zenlo Labs is a clinical decision support tool intended exclusively for use by licensed healthcare providers — not a substitute for professional medical judgment, and not intended for direct patient use.

Version v0.1 · Zenlo Research

Zenlo
Terms· Privacy· Security· Contact· Cookie Notice
Biomarker Evidence Engine · © 2026 Zenlo LLCds@zenlo.app