Endocrine Abstracts

Objective: To develop a non-invasive method of differential diagnosis for ACTH-dependent hypercortisolism using machine learning methods based on clinical data analysis.

Materials and methods: This is a single-center study of a retrospective cohort to predict the probability of EAS among patients with ACTH-dependent hypercortisolism using artificial machine learning algorithms. 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 had Cushing’s disease (CD), 48 had 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: morning ACTH level, 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 mesurement of pituitary adenoma according to MRI. 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 GBM machine learning algorithm is useful to differentiate patients with EAS and CD based on basic clinical results and can be recommended as primary screening of patients with ACTH-dependent hypercortisolism.