Related Experiment Video

Updated: Aug 5, 2026

A Novel Method: Super-selective Adrenal Venous Sampling
06:08

A Novel Method: Super-selective Adrenal Venous Sampling

Published on: September 15, 2017

Baseline biochemical evaluation for etiologic differentiation in ACTH-dependent Cushing's syndrome: machine learning

Mario Detomas1, Juan P Prada Salcedo2, Barbara Altieri1

  • 1Department of Internal Medicine I, Division of Endocrinology and Diabetes, University Hospital, University of Würzburg, 97080 Würzburg, Germany.

European Journal of Endocrinology
|July 31, 2026
PubMed

Insights

Differentiating adrenocorticotropin (ACTH)-dependent Cushing

Area of Science:

  • Endocrinology
  • Diagnostic Medicine
  • Medical Imaging

Background:

  • Limited corticotropin-releasing hormone (CRH) availability hinders differentiation of ACTH-dependent Cushing's syndrome (CS).
  • Diagnostic value of screening tests for distinguishing Cushing's disease (CD) from ectopic CS (ECS) is unclear.

Purpose of the Study:

  • To assess the diagnostic performance of screening tests for differentiating CD from ECS.
  • To evaluate combined screening test models and machine learning algorithms for improved diagnostic accuracy.

Main Methods:

  • Retrospective multicenter study of 566 patients with ACTH-dependent CS.
  • Analysis of screening tests including morning ACTH, 24-hour urinary free cortisol (24h-UFC), and 1mg dexamethasone suppression test.
  • Development of composite scoring models and machine learning algorithms, incorporating pituitary MRI findings.

Main Results:

  • 24h-UFC demonstrated the highest diagnostic performance among individual tests (AUC=0.854).
  • A composite score combining screening tests achieved 78% sensitivity and 92% specificity (AUC=0.865).
  • Combining the composite score with MRI findings yielded 88% sensitivity and 85% specificity (AUC=0.931).
  • Machine learning models showed promising diagnostic performance, particularly when including MRI findings (AUC=0.902).

Conclusions:

  • Combined screening tests in composite scoring models and machine learning algorithms offer a potential diagnostic alternative to CRH stimulation tests.
  • These approaches enhance the differentiation of ACTH-dependent CS, improving diagnostic accuracy.
Abstract

Keywords:
Cushing's diseasedexamethasone suppressionectopiclate-night salivary cortisolmorning cortisolurinary free cortisol

More Related Videos

Fecal Glucocorticoid Analysis: Non-invasive Adrenal Monitoring in Equids08:02

Fecal Glucocorticoid Analysis: Non-invasive Adrenal Monitoring in Equids

Published on: April 25, 2016

Related Concept Videos

Cushing Syndrome I: Introduction01:26

Cushing Syndrome I: Introduction

Cushing syndrome refers to the collection of clinical manifestations that arise when tissues are exposed to excessive amounts of cortisol or cortisol-like medications over an extended period. Cortisol, a glucocorticoid produced by the adrenal cortex, regulates metabolism, immune responses, and the body’s adaptation to stress. When its concentration remains chronically elevated, these physiological pathways become dysregulated, resulting in the characteristic features of the syndrome.Exogenous...
Cushing Syndrome II: Pathophysiology01:19

Cushing Syndrome II: Pathophysiology

Cortisol production is normally governed by the hypothalamic–pituitary–adrenal (HPA) axis, which maintains hormonal balance through tightly regulated feedback mechanisms. Disruption of this regulatory system is central to the development of Cushing syndrome, whether the excess cortisol originates from external medications or internal pathology. Persistent cortisol elevation alters metabolism, immune function, and endocrine signaling, producing the characteristic clinical features of the...