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

Transparency · CHAI Applied Model Card

Kidney Stress

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

Header

Model nameKidney Stress
DeveloperZenlo LLC
Release stageResearch Tool (not FDA-cleared)
Versionv0.1
AvailabilityUnited States
Regulatory statusNot applicable — academic and transparency positioning
Pattern slugkidney_stress
BiomarkersCreatinine, Blood Urea Nitrogen, eGFR

Summary

The Kidney Stress pattern flags creatinine elevation, blood urea nitrogen abnormalities, and reduced estimated glomerular filtration rate in adult laboratory panels, signaling potential renal impairment for physician review. Deterministic rules compare creatinine, BUN, and eGFR against registry reference thresholds. Claude Haiku 4.5 synthesizes narrative context on which renal indices are abnormal. Intended for licensed functional-medicine physicians as supportive clinical decision support, the pattern does not stage chronic kidney disease, assess proteinuria, or guide medication dosing. It highlights laboratory renal signals requiring correlation with hydration status, medications, blood pressure, and urinalysis — not a standalone nephrology diagnosis.

Uses & Directions

Intended use

Clinical decision support for licensed physicians reviewing renal function markers in adult panels.

Primary users

Licensed functional-medicine physicians and similarly qualified clinicians.

How to use

Review flagged renal labs with blood pressure, urinalysis, medications, and repeat testing as indicated.

Target population

Adults aged 18 and older in the United States.

Out of scope

  • Direct patient use without physician oversight
  • Pediatric renal evaluation
  • Standalone CKD staging or dialysis planning
  • Acute kidney injury management in critical care

Warnings

Clinical risk level

Low — supportive tool; the treating physician retains full clinical judgment and responsibility.

Known limitations

  • eGFR estimating equations have known limitations in extremes of muscle mass and age.
  • Does not incorporate urine albumin-to-creatinine ratio or urinalysis.
  • Single creatinine elevation may reflect hydration rather than chronic disease.

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 (kidney_stress) plus Claude Haiku 4.5 for narrative synthesis
  • Primary inputs: Creatinine, BUN, and eGFR from structured laboratory extraction.
  • Output: Pattern flag plus narrative on renal function 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 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: CREAT, BUN, EGFR

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