Bilateral Inferior Petrosal Sinus Sampling Without Lateralization Is Less Accurate for the Diagnosis of Cushing Disease.

Context: During bilateral inferior petrosal sinus sampling (BIPSS), the side-to-side adrenocorticotropic hormone (ACTH) ratio, referred to as sampling lateralization, was used to predict pituitary adenoma localization. Objective: To investigate the potential different diagnostic accuracy of BIPSS for differentiating Cushing disease (CD) and ectopic ACTH secretory syndrome (EAS) patients with low lateralization (inferior petrosal sinus [IPS]:IPS ≤ 1.4) and high lateralization (IPS:IPS > 1.4). Methods: This single-center retrospective study (2011-2021) included (all patients had BIPSS results and confirmed pathologic diagnoses) 220 consecutive CD patients (validation set), 30 EAS patients, and 40 of the CD patients who had digital subtraction angiography (DSA) videos (discovery set). Results: In the discovery set, the low-lateralization CD group (n = 11) had a higher median plasma ACTH concentration (62.2, IQR 44.7-181.0 ng/L) than the high-lateralization CD group (n = 29) (33.0, IQR 18.5-59.5, P = .013). Lower IPS to peripheral ratios were observed in the low-lateralization group during BIPSS, both before and after stimulation (P = .013 and P = .028). The sensitivity of BIPSS before stimulation in differentiating CD from EAS was lower in the low-lateralization group than the high-lateralization group (54.6% vs 93.1%, P = .003), as validated in the validation set. DSA videos revealed higher vascular area difference visible in the 2 sides of the pituitary in low lateralization (median 1.2 × 105 pixels, IQR 0.5-1.8) than the high-lateralization group (0.4 × 105 pixels, IQR 0.1-0.7, P = .008). The vascular area ratio of the 2 sides was also significantly higher in low (1.55, IQR 1.31-2.20) than high lateralization (1.19, IQR 1.07-1.35, P = .010). Conclusion: Our study suggested that low lateralization in CD patients may reduce the diagnostic sensitivity of BIPSS, which might be potentially associated with peripituitary vascular anatomy.

Artificial intelligence facial recognition system for diagnosis of endocrine and metabolic syndromes based on a facial image database.

AIM: To build a facial image database and to explore the diagnostic efficacy and influencing factors of the artificial intelligence-based facial recognition (AI-FR) system for multiple endocrine and metabolic syndromes. METHODS: Individuals with multiple endocrine and metabolic syndromes and healthy controls were included from public literature and databases. In this facial image database, facial images and clinical data were collected for each participant and dFRI (disease facial recognition intensity) was calculated to quantify facial complexity of each syndrome. AI-FR diagnosis models were trained for each disease using three algorithms: support vector machine (SVM), principal component analysis k-nearest neighbor (PCA-KNN), and adaptive boosting (AdaBoost). Diagnostic performance was evaluated. Optimal efficacy was achieved as the best index among the three models. Effect factors of AI-FR diagnosis were explored with regression analysis. RESULTS: 462 cases of 10 endocrine and metabolic syndromes and 2310 controls were included into the facial image database. The AI-FR diagnostic models showed diagnostic accuracies of 0.827-0.920 with SVM, 0.766-0.890 with PCA-KNN, and 0.818-0.935 with AdaBoost. Higher dFRI was associated with higher optimal area under the curve (AUC) (P = 0.035). No significant correlation was observed between the sample size of the training set and diagnostic performance. CONCLUSIONS: A multi-ethnic, multi-regional, and multi-disease facial database for 10 endocrine and metabolic syndromes was built. AI-FR models displayed ideal diagnostic performance. dFRI proved associated with the diagnostic performance, suggesting inherent facial features might contribute to the performance of AI-FR models.