Transparency · CHAI Applied Model Card
Autoimmune Risk
CHAI Applied Model Card (v0.1) for the Autoimmune Risk pattern in Zenlo Labs. This document is not CHAI-certified or CHAI-endorsed.
Header
Summary
The Autoimmune Risk pattern evaluates thyroid peroxidase antibodies, erythrocyte sedimentation rate, high-sensitivity CRP, and antinuclear antibody patterns in adult laboratory panels, flagging laboratory profiles suggestive of autoimmune or inflammatory activity for physician review. Deterministic rules apply pattern-specific positivity thresholds; qualifying markers fire the pattern. Claude Haiku 4.5 synthesizes narrative context on autoimmune-related laboratory signals. For licensed functional-medicine physicians, this is supportive clinical decision support — it does not diagnose specific autoimmune diseases, interpret ANA titers or patterns, or replace rheumatology referral. Outputs prompt correlation with symptoms, targeted autoantibody panels, and specialist evaluation.
Uses & Directions
Intended use
Clinical decision support for licensed physicians reviewing autoimmune-associated laboratory markers in adult panels.
Primary users
Licensed functional-medicine physicians and similarly qualified clinicians.
How to use
Review flagged markers with clinical symptoms, medication history, and targeted autoantibody or rheumatology referral as indicated.
Target population
Adults aged 18 and older in the United States.
Out of scope
- Direct patient use without physician oversight
- Pediatric autoimmune evaluation
- Standalone diagnosis of lupus, RA, or thyroid autoimmunity
- Immunosuppressive therapy management
Warnings
Clinical risk level
Low — supportive tool; the treating physician retains full clinical judgment and responsibility.
Known limitations
- ANA and TPO antibodies have specificity limitations; positive results require clinical correlation.
- Does not include comprehensive autoantibody panels (dsDNA, RF, CCP, etc.).
- ESR and hs-CRP are non-specific inflammatory markers.
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 (autoimmune_risk) plus Claude Haiku 4.5 for narrative synthesis
- Primary inputs: TPO antibodies, ESR, hs-CRP, and ANA from structured extraction.
- Output: Pattern flag plus narrative on autoimmune-associated marker 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: ATPO, ESR, HSCRP, ANA
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
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.