Machine Learning May Be an Alternative to BIPSS in the Differential Diagnosis of ACTH-dependent Cushing Syndrome.

CONTEXT: Artificial intelligence research in the field of neuroendocrinology has accelerated. It is possible to develop noninvasive, easy-to-use and cost-effective procedures that can replace invasive procedures for the differential diagnosis of adrenocorticotropin (ACTH)-dependent Cushing syndrome (CS) by artificial intelligence.

OBJECTIVE

This study aimed to develop machine-learning (ML) algorithms for the differential diagnosis of ACTH-dependent CS based on biochemical and radiological features.

METHODS

Logistic regression algorithms were used for ML, and the area under the receiver operating characteristics curve was used to measure performance. We used Shapley contributed comments (SHAP) values, which help explain the results of the ML models to identify the meaning of each feature and facilitate interpretation.

RESULTS

A total of 106 patients, 80 with Cushing disease (CD) and 26 with ectopic ACTH syndrome (EAS), were enrolled in the study. The ML task was created to classify patients with ACTH-dependent CS into CD and EAS. The average AUROC value obtained in the cross-validation of the logistic regression model created for the classification task was 0.850. The diagnostic accuracy of the algorithm was 86%. The SHAP values indicated that the most important determinants for the model were the 2-day 2-mg dexamethasone suppression test, greater than 50% suppression in the 8-mg high-dose dexamethasone test, late-night salivary cortisol, and the diameter of the pituitary adenoma. We have also made our algorithm available to all clinicians via a user-friendly interface.

CONCLUSION

ML algorithms have the potential to serve as an alternative decision-support tool to invasive procedures in the differential diagnosis of ACTH-dependent CS.