Assessing the androgenic and metabolic heterogeneity in polycystic ovary syndrome using cluster analysis
Authors' conclusion
We identified a subset of women in our PCOS cohort with significantly higher LH, FAI, and androstenedione levels. We show that higher levels of androstenedione and FAI are associated with a higher siMS, while higher DHEAS levels were associated with lower siMS.
Study context
- Population
- Women with polycystic ovary syndrome (PCOS) from a PCOS clinic (discovery cohort) and the Hull PCOS Biobank (replication cohort)discovery 199, replication 111
- Participants
- 310 women
- Comparison
- Smaller vs larger hormonal cluster of women with PCOS
- Smaller clustern = 62
- Larger clustern = 137reference
- Outcome
- Hormone levels in smaller vs larger cluster (discovery cohort)
Methodological detailsdiscovery and replication cohorts, K-means clustering (unsupervised machine learning), regression analysis
- Discovery and replication cohorts
- K-means clustering (unsupervised machine learning)
- Regression analysis
Main finding
As reported in the abstract
- Two clusters identified in both discovery and replication cohorts; smaller cluster = 31% of discovery participants
- Findings replicated in replication cohort (larger cluster n = 74, smaller cluster n = 37; 33%)
- Smaller cluster vs Larger cluster: P < 0.001
- Smaller cluster vs Larger cluster: P < 0.001
- Smaller cluster vs Larger cluster: P < 0.001
- Smaller cluster vs Larger cluster: P < 0.001
Further findings
Mean
| Outcome | Smaller cluster | Larger cluster | P value |
|---|---|---|---|
| siMS scoreNot statistically significant | 3.1 (SD 1.1) | 2.8 (SD 0.8) | P = 0.20 |
Hormonal predictors of siMS score (regression)
- Higher FAI associated with higher siMS, β (p = .003)
- .05
- Higher androstenedione associated with higher siMS, β (p = .02)
- .03
- Higher dehydroepiandrosterone sulphate (DHEAS) associated with lower siMS, β (p = .03)
- −.07
- Independently associated
Original publication
Assessing the androgenic and metabolic heterogeneity in polycystic ovary syndrome using cluster analysis. Clin Endocrinol (Oxf). Published 20 November 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →