Emerging Digital Technologies in Monitoring Endocrine Disorders: Continuous Glucose Monitoring Systems and Artificial Intelligence in the Diagnosis of Polycystic Ovary Syndrome

Introduction and objective: Endocrine disorders affect the regulation of metabolic processes and are often associated with disturbances in glucose and hormonal homeostasis. In recent years, digital tools have increasingly contributed to the diagnosis and monitoring of metabolic diseases. Technological advancements have introduced continuous glucose monitoring (CGM) for patients with diabetes, as well as artificial intelligence (AI) algorithms to support the assessment of hormonal and imaging parameters in the diagnosis of PCOS. Despite these advances, studies on patients with diabetes using CGM who are simultaneously diagnosed with PCOS remain limited. AI-based diagnostic tools show promising accuracy in detecting PCOS characteristics through hormonal profiles and ultrasound imaging. The aim of this review is to summarize current evidence on CGM systems and AI in the evaluation and diagnosis of endocrine disorders, focusing on diabetes and PCOS. Methods: This narrative review analyzed literature from 2019–2025 and one earlier publication using PubMed and Google Scholar, focusing on CGM, AI, and diagnostic approaches in endocrine disorders. Results: CGM provides valuable insight into glucose variability and metabolic patterns in diabetes, but evidence for its use in patients with concurrent PCOS is limited. AI-based tools demonstrate high accuracy in identifying PCOS features, especially through hormonal profiling and ultrasound analysis. Conclusion: Digital technologies such as CGM and AI offer promising opportunities to improve the evaluation and management of endocrine disorders, particularly in women with PCOS. Larger, standardized studies are needed to validate clinical utility and support integration into routine care.