Predictive model for the diagnosis of Ectopic Cushing Syndrome

The purpose of our study was to develop and externally validate a multivariable diagnostic model to distinguish ectopic ACTH secretion (EAS) from Cushing's disease (CD) using routine clinical parameters. The model was derived from a Spanish multicenter retrospective cohort and externally validated in a Colombian cohort. Predictors were selected through a multivariable logistic regression model with penalized logistic regression (LASSO) using the Spanish cohort. Discriminative performance was assessed using the area under the ROC curve [AUC] and calibration using the slope, the origin, and the Brier score. The derivation cohort included 253 patients from Spain (199 with CD and 54 with EAS). The external validation cohort comprised 72 Colombian patients (53 with CD and 19 with EAS). In the derivation cohort, multivariable modelling identified four independent predictors: ACTH concentration, 24-h urinary free cortisol (UFC), serum potassium, and maximum pituitary tumor diameter. The final model demonstrated good discrimination in the derivation cohort (mean AUC of 0.987), with excellent calibration (calibration slope ranged from 0.998 to 5.22, intercept -0.2 to 0.99, Brier score 0.035). In external validation, model performance remained robust (AUC ranging from 0.9885 to 0.9890; Brier score 0.0381). The model achieved a sensitivity of 95.3%, specificity of 93.6%, positive predictive value of 82.3%, and negative predictive value of 98.7% for detecting EAS. Thus, the diagnostic model developed, based on routinely available clinical variables, shows high accuracy and calibration in differentiating between EAS and CD, supporting its potential use in diverse clinical settings and integration into diagnostic workflows.

Authors

Institutions

Publication Details

Journal
Endocrine Related Cancer
Published
2026-04-16
DOI
https://doi.org/10.1530/erc-25-0348
Primary Topic
Pituitary Gland Disorders and Treatments
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Predictive model for the diagnosis of Ectopic Cushing Syndrome

Ana Castro Luna, Luis Candil Valero, Johnayro Gutiérrez Restrepo, María Johana Ramírez Castaño et al.
Endocrine Related Cancer
Pituitary Gland Disorders and Treatments
article

Predictive model for the diagnosis of Ectopic Cushing Syndrome

Ana Castro Luna, Luis Candil Valero, Johnayro Gutiérrez Restrepo, María Johana Ramírez Castaño, Pablo Alberto Castaño Ceballos, Pedro Iglesias, Marta Araujo‐Castro, Stefania Cruz Calderón, Wilfredo Antonio Rivera Martínez, Andrés Felipe García Ramos, Alejandro Román González, Victoria Alcázar, Néstor Andrés Díaz Posada, Rogelio García-Centeno, Betina Biagetti, Alejandro Pinzón Tovar, L Beltrán Fernández, Alfonso Soto Moreno, María Dolores Ollero García-Agulló, Natalia Aristizábal Henao, Felicia Hanzu, Alin Abreu Lomba, Edelmiro Menéndez Torre, Carlos Alfonso Builes Barrera, Carlos Esteban Builes-Montaño, Néstor López Pompey, Pol Candela, María Dolores Moure Rodríguez, Claudia Marcela Gómez Serna, David Vernaza, Miguel Paja, Fernando Guerrero-Pérez, Rosa Cámara, Andrés Cardona, Claudia Lozano Aida, Ana Irigaray Echarri
article en

Abstract

The purpose of our study was to develop and externally validate a multivariable diagnostic model to distinguish ectopic ACTH secretion (EAS) from Cushing's disease (CD) using routine clinical parameters. The model was derived from a Spanish multicenter retrospective cohort and externally validated in a Colombian cohort. Predictors were selected through a multivariable logistic regression model with penalized logistic regression (LASSO) using the Spanish cohort. Discriminative performance was assessed using the area under the ROC curve [AUC] and calibration using the slope, the origin, and the Brier score. The derivation cohort included 253 patients from Spain (199 with CD and 54 with EAS). The external validation cohort comprised 72 Colombian patients (53 with CD and 19 with EAS). In the derivation cohort, multivariable modelling identified four independent predictors: ACTH concentration, 24-h urinary free cortisol (UFC), serum potassium, and maximum pituitary tumor diameter. The final model demonstrated good discrimination in the derivation cohort (mean AUC of 0.987), with excellent calibration (calibration slope ranged from 0.998 to 5.22, intercept -0.2 to 0.99, Brier score 0.035). In external validation, model performance remained robust (AUC ranging from 0.9885 to 0.9890; Brier score 0.0381). The model achieved a sensitivity of 95.3%, specificity of 93.6%, positive predictive value of 82.3%, and negative predictive value of 98.7% for detecting EAS. Thus, the diagnostic model developed, based on routinely available clinical variables, shows high accuracy and calibration in differentiating between EAS and CD, supporting its potential use in diverse clinical settings and integration into diagnostic workflows.

Endocrine Related Cancer
Universidad Pontificia Bolivariana (CO), Instituto Cajal (ES), Bellvitge University Hospital (ES), ProMedica Toledo Hospital (US), Hospital General Universitario Gregorio Marañón (ES), Hospital Universitari i Politècnic La Fe (ES), Hospital Universitario de San Vicente Fundación (CO), Universidad de Antioquia (CO), Hospital de Basurto (ES), Instituto de Cancerología Las Américas (CO), Complejo Hospitalario de Navarra (ES), Hospital Universitario Puerta de Hierro Majadahonda (ES), Clínica Somer (CO), Hospital Pablo Tobon Uribe (CO), Hospital Clínic de Barcelona (ES), Leitat Technological Center (ES), Clínica Santa María (CO), Hospital San Juan de Dios (CL), Hospital Universitario de Neiva (CO), Instituto Ramón y Cajal de Investigación Sanitaria (ES), Vall d'Hebron Hospital Universitari (ES), Hospital Universitario Central de Asturias (ES), Hospital de Cruces (ES), Hospital Universitario Virgen del Rocío (ES), Hospital Universitario Severo Ochoa (ES), Complejo Hospitalario Universitario de Toledo (ES), Instituto de Investigación Sanitaria La Fe (ES), Universidad de Navarra (ES), Universidad del Valle (CO)
Reduced inequalities
Openalex Percentile: Top 19%
Pituitary Gland Disorders and Treatments
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.