SFEBES2022 Poster Presentations Reproductive Endocrinology (36 abstracts)
Cluster analysis with routine hormonal parameters identifies two distinct subsets of polycystic ovary syndrome (PCOS)
Harshal Deshmukh 1 , Shahzad Akbar 1 , Amira Bhaiji 1 , Yamna Saeed 1 , Najeeb Shah 1 , Lucy Batten 1 , Kazeem A Adeleke 1 , Stephen Atkin 2 & Thozhukat Sathyapalan 1
1University of Hull, Hull, United Kingdom; 2RCSI, Bahrain, Bahrain
Introduction: Women with PCOS have a higher risk of metabolic syndrome and cardiovascular complications. We aimed to understand if routinely measured hormonal parameters can identify women with PCOS with a higher risk of metabolic syndrome (MetS).
Methods: The data for the study consisted of a discovery cohort (PCOS clinic database) and a replication cohort (Hull PCOS Biobank.) We used eight routinely measured hormonal parameters in our clinics (free androgen index (FAI), sex hormone-binding globulin SHBG), dehydroepiandrosterone sulphate (DHEAS), androstenedione, luteinizing hormone (LH), follicular stimulating hormone (FSH), antimullerian hormone and 17 hydroxy-progesterone) to perform a K-means clustering and an unsupervised machine learning algorithm. We used NbClust Package in R to determine the best number of clusters. The MetS score (siMS) was calculated by using the formula: 2*waist-circumference/Height + (Baseline glucose/5.6) + (Triglycerides/1.7) + (systolic blood pressure/130) - (HDL/1.28)
Results: The study consisted of 199 women with PCOS in the discovery cohort and 111 in the replication cohort. The cluster analysis showed a smaller cluster with statistically significantly higher LH, FAI, and androstenedione levels in both the discovery (31% of women with PCOS and replication cohort (33% of women with PCOS). The mean MetS score was higher in the smaller cluster (2.85 vs 3.01); however, this was not statistically significant. In the regression analysis, androstenedione (Beta=0.03, P=0.03) and FAI (Beta=0.04, P=0.01) were independently and statistically significantly associated with MetS.
Conclusions: We identified a subset of women with PCOS with significantly higher levels of LH, FAI and androstenedione; In addition, androstenedione was independently associated with a higher MetS score and can be a useful marker for metabolic syndrome in women with PCOS.
Article tools
My recent searches
My recently viewed abstracts
Authors
Endocrine Abstracts
ISSN 1470-3947 (print) | ISSN 1479-6848 (online)
© Bioscientifica 2024 |
Privacy policy |
Cookie settings
BiosciAbstracts
Bioscientifica Abstracts is the gateway to a series of products that provide a permanent, citable record of abstracts for biomedical and life science conferences.
Find out more