Skip to content
cccskills
FreePublished on GitHub

ata-cortisol-cutoff-ai-diagnosis

Applies serum cortisol cutoffs (<3 μg/dL indicates central adrenal insufficiency; >15 μg/dL likely excludes it) when evaluating morning cortisol for suspected adrenal insufficiency. Triggers include morning cortisol measurement in suspected AI and use when interpreting morning cortisol levels for adrenal insufficiency workup.

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (1)

  • SKILL.md2.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Apply cortisol level cutoffs for central AI diagnosis

STEP 1 — Gather Information

Collect morning serum cortisol drawn between 8–9 AM after an overnight fast; document recent glucocorticoid exposure (must be off hydrocortisone ≥24 h or longer for synthetic GCs); note estrogen therapy, pregnancy, or medications affecting cortisol-binding globulin; record any acute illness or stress that could alter cortisol.

STEP 2 — Rule In / Rule Out

Is the morning cortisol level <3 μg/dL?

  • If yes, rule in central AI (indicative).
  • If no, proceed to next step.

STEP 3 — Classify or Stratify

Is the cortisol level between 3 and 15 μg/dL (inclusive)?

  • If yes, classify as indeterminate; ACTH stimulation test required.
  • If no (i.e., >15 μg/dL), classify as AI unlikely excluded.

STEP 4 — Decide

  • For cortisol <3 μg/dL: initiate glucocorticoid replacement (e.g., hydrocortisone 15–20 mg daily) and provide stress‑dose education.
  • For cortisol 3–15 μg/dL: order standard‑ or low‑dose ACTH stimulation test to confirm AI.
  • For cortisol >15 μg/dL: consider alternative diagnoses; avoid glucocorticoid replacement unless other evidence of AI exists.

Clinical Guardrails / Mimics / Pitfalls

Do not use random cortisol levels; estrogen therapy or pregnancy raises total cortisol via CBG, potentially masking AI; ensure patient is off glucocorticoids for adequate time; acute illness or stress can transiently elevate cortisol; assay variability and inter‑lab differences may affect cutoff interpretation; avoid glucocorticoid replacement based solely on a single borderline result without stimulation testing.

Concrete Clinical Example

A 48‑year‑old man with persistent fatigue and hypotension has a morning cortisol of 2.4 μg/dL drawn at 8:30 AM after being off hydrocortisone for 36 hours. The value is <3 μg/dL, indicating central AI; he is started on hydrocortisone 15 mg daily and instructed on stress‑dosing for illness.

Source: Hormonal Replacement in Hypopituitarism in Adults: An Endocrine Society Clinical Practice Guideline, Endocrine Society, 2016, DOI:10.1210/jc.2016-2118

TODO: consider adding scripts/calc.py for the ata-cortisol-cutoff-ai-diagnosis calculator

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Guide pump setting adjustments for the MiniMed 780G system based on CareLink data, using Medtronic's 3-step follow-up workflow. Use when a clinician has CareLink data for a 780G patient and wants to know what to change — which setting, by how much, and how to program it. Triggers include: "what do I adjust", "how to fix high TIR", "how to reduce hypos", "adjust ICR/ISF/basal", "SmartGuard settings", "780G pump settings review", or any question about optimising 780G therapy after reviewing a download.

The English summary is being prepared. Showing the original description.

dromlakhani/MD2SKILL14Updated Oct 20, 2026

Performs corticotropin stimulation test to diagnose adrenal insufficiency when morning cortisol is indeterminate (3-15 µg/dL). Triggers include morning cortisol 3-15 µg/dL requiring further AI testing.

The English summary is being prepared. Showing the original description.

dromlakhani/MD2SKILL14Updated Oct 20, 2026

Administers immediate parenteral injection of 50–100 mg hydrocortisone for suspected adrenal crisis secondary to adrenal insufficiency. Triggers include hypotension, hypoglycemia, or acute illness in a patient with known adrenal insufficiency.

The English summary is being prepared. Showing the original description.

dromlakhani/MD2SKILL14Updated Oct 20, 2026

Clinicians educate adrenal insufficiency patients taking nondexamethasone glucocorticoids who initiate enzyme-inducing antiepileptic drugs about early signs of adrenal insufficiency. Trigger when an AI patient on nondexamethasone GC starts an enzyme-inducing AED such as phenytoin, carbamazepine, or oxcarbazepine.

The English summary is being prepared. Showing the original description.

dromlakhani/MD2SKILL14Updated Oct 20, 2026

In central hypothyroidism patients receiving levothyroxine who initiate enzyme‑inducing antiepileptic drugs, the guideline recommends checking free T4 at least 6 weeks after AED start and increasing the levothyroxine dose if free T4 falls below the target range. Triggers include: central hypothyroidism patient on levothyroxine starting antiepileptic drug such as phenytoin, carbamazepine, or oxcarbazepine.

The English summary is being prepared. Showing the original description.

dromlakhani/MD2SKILL14Updated Oct 20, 2026

In patients with adrenal insufficiency receiving dexamethasone replacement, the guideline suggests increasing the dexamethasone dose when enzyme-inducing antiepileptic drugs are co-administered. Trigger phrases include "AI patient on dexamethasone starts enzyme-inducing antiepileptic drug" or "AI patient on dexamethasone requiring enzyme-inducing AED".

The English summary is being prepared. Showing the original description.

dromlakhani/MD2SKILL14Updated Oct 20, 2026

See all skills by dromlakhani

Report a problem with this skill