An Optimized Pathway for the Differential Diagnosis of ACTH-Dependent Cushing's Syndrome Based on Low-Dose Dexamethasone Suppression Test

An updated clinico-investigative approach to diagnosis of cutaneous hyperandrogenism in relation to adult female acne, female pattern alopecia & hirsutism a primer for dermatologists

INTRODUCTION

Hyperandrogenism is a clinical state consequent to excess androgen production by the ovary, adrenals, or increased peripheral conversion of androgens. The varied manifestations of hyperandrogenism include seborrhea, acne, infertility, hirsutism, or overt virilization of which adult female acne, hirsutism, and female pattern hair loss are of clinical relevance to dermatologists.

AREAS COVERED

We limited our narrative review to literature published during period from 1 January 1985 to Dec 2022 and searched PubMed/MEDLINE, Web of Science (WOS), Scopus, and Embase databases with main search keywords were 'Hyperandrogenism,' 'Female,' 'Biochemical,' 'Dermatological', and 'Dermatology.' We detail the common etiological causes, nuances in interpretation of biochemical tests and imaging tools, followed by an algorithmic approach which can help avoid extensive tests and diagnose the common causes of hyperandrogenism.

EXPERT OPINION

Based on current data, total testosterone, sex hormone binding globulin, DHEAS, prolactin, free androgen index, and peripheral androgenic metabolites like 3-alpha diol and androsterone glucuronide are ideal tests though not all are required in all patients. Abnormalities in these biochemical investigations may require radiological examination for further clarification. Total testosterone levels can help delineate broadly the varied causes of hyperandrogenism. Serum AMH could be used for defining PCOM in adults.

Machine learning models for differential diagnosis of Cushing's disease and ectopic ACTH secretion syndrome

BACKGROUND

Using machine learning (ML) to explore the noninvasive differential diagnosis of Cushing's disease (CD) and ectopic corticotropin (ACTH) secretion (EAS) model is the next hot research topic. This study was to develop and evaluate ML models for differentially diagnosing CD and EAS in ACTH-dependent Cushing's syndrome (CS).

METHODS

Two hundred sixty-four CD and forty-seven EAS were randomly divided into training and validation and test datasets. We applied 8 ML algorithms to select the most suitable model. The diagnostic performance of the optimal model and bilateral petrosal sinus sampling (BIPSS) were compared in the same cohort.

RESULTS

Eleven adopted variables included age, gender, BMI, duration of disease, morning cortisol, serum ACTH, 24-h UFC, serum potassium, HDDST, LDDST, and MRI. After model selection, the Random Forest (RF) model had the most extraordinary diagnostic performance, with a ROC AUC of 0.976 ± 0.03, a sensitivity of 98.9% ± 4.4%, and a specificity of 87.9% ± 3.0%. The serum potassium, MRI, and serum ACTH were the top three most important features in the RF model. In the validation dataset, the RF model had an AUC of 0.932, a sensitivity of 95.0%, and a specificity of 71.4%. In the complete dataset, the ROC AUC of the RF model was 0.984 (95% CI 0.950-0.993), which was significantly higher than HDDST and LDDST (both p < 0.001). There was no significant statistical difference in the comparison of ROC AUC between the RF model and BIPSS (baseline ROC AUC 0.988 95% CI 0.983-1.000, after stimulation ROC AUC 0.992 95% CI 0.983-1.000). This diagnostic model was shared as an open-access website.

CONCLUSIONS

A machine learning-based model could be a practical noninvasive approach to distinguishing CD and EAS. The diagnostic performance might be close to BIPSS.

A noninvasive scoring model for the differential diagnosis of ACTH-dependent Cushing's syndrome: a retrospective analysis of 311 patients based on easy-to-use parameters

OBJECTIVES

The differential diagnosis of ACTH-dependent Cushing's disease (CS) is challenging. The gold standard approach bilateral inferior petrosal sinus sampling (BIPSS) is expensive and invasive, while other noninvasive tests, like the high-dose dexamethasone suppression test (HDDST), provide unsatisfactory diagnostic accuracy. This study aimed to find a new noninvasive practical approach with higher diagnostic accuracy to differently diagnose ACTH-dependent CS, which can be used in centers where BIPSS cannot be applied.

METHODS

264 Cushing's disease (CD) patients and 47 ectopic ACTH secretion syndrome (EAS) patients were analyzed in this single-center retrospective study (2011-2021). The multivariate logistic model was used to construct the scoring model.

RESULTS

Female (adjusted OR 3.030, 95%CI 1.229-7.471), hypokalemia (0.209, 0.076-0.576), ACTH (0.988, 0.982-0.994), MRI pituitary lesion positive (8.671, 3.521-21.352), and HDDST positive (2.768, 1.139-6.726) have a strong association with the differential diagnosis of ACTH-dependent CS and were included in the final multivariable logistic regression model. A -14-to-14-point noninvasive scoring model was built on the model. The AUC of the noninvasive scoring model was 0.915 (95% CI 0.869-0.960), significantly higher than the AUC of HDDST (0.756, 95% CI 0.685-0.825, P = 0.004). The optimal cutoff of the model was ≥0 to diagnose CD. The sensitivity of the noninvasive scoring model was 91.3% (95% CI 87.3%-94.1%), and the specificity was 80.9% (95% CI 67.5%-89.6%). When the model's sensitivity was 100.0%, the cutoff was ≥ -10 with a specificity of 19.2%; when the model's specificity was 100.0%, the cutoff was ≥ 13 with a sensitivity of 22.7%.

CONCLUSIONS

We developed a noninvasive scoring model to distinguish CD and EAS in ACTH-dependent CS patients with higher diagnostic utility than HDDST in the same cohort. The noninvasive scoring model might be applied in areas where BIPSS is unavailable, the CRH is hard to obtain, or the desmopressin stimulation is not widely applied. It also provided a triage tool for selecting patients that might benefit the most from a further BIPSS test.