Diagnostic value of bilateral inferior petrosal sinus sampling in various modifications and methods of radiation and radionuclide imaging in the diagnosis and differential diagnosis of ACTH-dependent endogenous hypercortisolism

Belaya, Zh. E.; Golounina, O. O.; Sitkin, I. I.; Rozhinskaya, L. Ya.; Degtyarev, M. V.; Trukhina, D. A.; Bondarenko, E. V.; Lapshina, A. M.; Mamedova, E. O.; Przhiyalkovskaya, E. G.; Vaks, V. V.; Melnichenko, G. A.; Mokrysheva, N. G.; Dedov, I. I.

doi:10.14341/probl13299

Cited by 1 publication

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…С момента внедрения метод претерпел значительные изменения и усовершенствования с целью повышения диагностической точности [ 5 ]. Результаты исследования, проведенного в ФГБУ «НМИЦ эндокринологии» Минздрава России, свидетельствуют о высокой чувствительности (98,31% (95% ДИ 95,16–99,43)) и специфичности (94,64% (95% ДИ 85,39–98,16)) селективного забора крови с использованием стимуляции десмопрессином [ 6 ].…”

Section: обоснованиеunclassified

Machine learning methods in differential diagnosis of ACTH-dependent hypercortisolism

Golounina,

Belaya,

Voronov

et al. 2024

Probl Endokrinol (Mosk)

Self Cite

View full text Add to dashboard Cite

AIM: To develop a noninvasive method of differential diagnosis of ACTH-dependent hypercortisolism, as well as to evaluate the effectiveness of an optimal algorithm for predicting the probability of ectopic ACTH syndrome (EAS) obtained using machine learning methods based on the analysis of clinical data.MATERIALS AND METHODS: As part of a single-center, one-stage, cohort study, a retrospective prediction of the probability of EAS among patients with ACTH-dependent hypercortisolism was carried out. Patients were randomly stratified into 2 samples: training (80%) and test (20%). Eleven machine learning algorithms were used to develop predictive models: Linear Discriminant Analysis, Logistic Regression, elastic network (GLMNET), Support Vector machine (SVM Radial), k-nearest neighbors (kNN), Naive Bayes, binary decision tree (CART), C5.0 decision tree algorithms, Bagged CART, Random Forest, Gradient Boosting (Stochastic Gradient Boosting, GBM).RESULTS: The study included 223 patients (163 women, 60 men) with ACTH-dependent hypercortisolism, of which 175 patients with Cushing’s disease (CD), 48 — with EAS. As a result of preliminary data processing and selection of the most informative signs, the final variables for the classification and prediction of EAS were selected: ACTH level at 08:00 hours, potassium level (the minimum value of potassium in the active stage of the disease), 24-h urinary free cortisol, late-night serum cortisol, late-night salivary cortisol, the largest size of pituitary adenoma according to MRI of the brain. The best predictive ability in a training sample of all trained machine learning models for all three final metrics (ROC-AUC (0.867), sensitivity (90%), specificity (56.4%)) demonstrated a model of gradient boosting (Generalized Boosted Modeling, GBM). In the test sample, the AUC, sensitivity and specificity of the model in predicting EAS were 0.920; 77.8% and 97.1%, respectively.CONCLUSION: The prognostic model based on machine learning methods makes it possible to differentiate patients with EAS and CD based on basic clinical results and can be used as a primary screening of patients with ACTH-dependent hypercortisolism.

show abstract

Section: обоснованиеunclassified