Endocrine Abstracts

JOINT1427

Objectives: The primary objective of this study was to evaluate the feasibility, accuracy, and clinical relevance of the Smart Menstrual Health Monitoring Patch(SMHMP), a non-invasive newly designed wearable device designed to continuously monitor menstrual cycle biomarkers. The study aimed to assess its effectiveness in predicting ovulation, detecting cycle irregularities, and identifying potential menstrual disorders such as PCOS, endometriosis, and infertility.

Design: A prospective, multi-centered study was conducted to validate the SMHMP’s biosensor technology and AI-driven analytics. The study followed a longitudinal observational design, comparing SMHMP data with conventional menstrual tracking methods (eg: basal body temperature chart and hormone assays) and clinical diagnosis.

Methods: 500 participants, aged 18-40 with varying menstrual health profiles, were recruited from gynecological clinics. Participants wore SMHMP continuously for six menstrual cycles. The patch collected basal body temperature, hormone fluctuation data (estrogen and progesterone levels via interstitial fluid analysis), and other biomarkers data were analyzed using machine learning algorithms to detect cycle trends, ovulation windows, and potential menstrual disorders. Clinical validation was performed through physical assessments, blood hormone assays, and ultrasound confirmation where necessary.

Results: The SMHMP demonstrated a 92.3% accuracy in ovulation prediction compared to standard luteinizing hormone tests. It successfully detected menstrual irregularities in 87.5% of participants previously diagnosed with PCOS and identified 78.9% of cases with suspected endometriosis. User compliance and satisfaction rates exceeded 85% with participants reporting improved menstrual health awareness and ease of use compared to traditional tracking methods.

Conclusion: The findings suggest that SMHMP is a viable, non-invasive solution for menstrual health monitoring, offering real-time insights that can aid in the early detection of menstrual disorders. This technology has to potential to transform gynecological practice by providing an accessible, AI-driven approach to reproductive health management. Future research should focus on expanding clinical trials, refining AI algorithms for increased diagnostic accuracy, and exploring integration with border women’s health initiatives.