Polycystic ovary syndrome: clinical and laboratory variables related to new phenotypes using machine-learning models

PURPOSE

Polycystic Ovary Syndrome (PCOS) is the most frequent endocrinopathy in women of reproductive age. Machine learning (ML) is the area of artificial intelligence with a focus on predictive computing algorithms. We aimed to define the most relevant clinical and laboratory variables related to PCOS diagnosis, and to stratify patients into different phenotypic groups (clusters) using ML algorithms.

METHODS

Variables from a database comparing 72 patients with PCOS and 73 healthy women were included. The BorutaShap method, followed by the Random Forest algorithm, was applied to prediction and clustering of PCOS.

RESULTS

Among the 58 variables investigated, the algorithm selected in decreasing order of importance: lipid accumulation product (LAP); abdominal circumference; thrombin activatable fibrinolysis inhibitor (TAFI) levels; body mass index (BMI); C-reactive protein (CRP), high-density lipoprotein cholesterol (HDL-c), follicle-stimulating hormone (FSH) and insulin levels; HOMA-IR value; age; prolactin, 17-OH progesterone and triglycerides levels; and family history of diabetes mellitus in first-degree relative as the variables associated to PCOS diagnosis. The combined use of these variables by the algorithm showed an accuracy of 86% and area under the ROC curve of 97%. Next, PCOS patients were gathered into two clusters in the first, the patients had higher BMI, abdominal circumference, LAP and HOMA-IR index, as well as CRP and insulin levels compared to the other cluster.

CONCLUSION

The developed algorithm could be applied to select more important clinical and biochemical variables related to PCOS and to classify into phenotypically different clusters. These results could guide more personalized and effective approaches to the treatment of PCOS.

Microparticles: Inflammatory and haemostatic biomarkers in Polycystic Ovary Syndrome

Polycystic Ovary Syndrome (PCOS) is associated with a chronic low-grade inflammation and predisposition to hemostatic and atherosclerotic complications. This case-control study evaluated the microparticles (MPs) profile in patients with the PCOS and related these MPs to clinical and biochemical parameters. MPs derived from platelets (PMPs), leuckocytes (LMPs) and endothelial cells (EMPs) were evaluated, as well as MPs expressing tissue factor (TFMPs), by flow cytometry, comparing women with PCOS (n = 50) and a healthy control group (n = 50). PCOS women presented increased total MPs, PMPs, LMPs and EMPs levels when compared to control group (all p < 0.05). TFMPs was similar between the groups (p = 0.379). In conclusion, these MPs populations could be useful biomarkers for association with thrombosis and cardiovascular disease in PCOS women.

Estrogen receptor αlpha gene (ESR1) PvuII and XbaI polymorphisms are associated to metabolic and proinflammatory factors in polycystic ovary syndrome

BACKGROUND

Polycystic ovary syndrome (PCOS) is a complex endocrine disorder that involves multiple factors. Although the etiology of PCOS is unknown, there is an involvement of sex steroid hormones in the pathophysiology of this syndrome. Therefore, polymorphisms in genes involved in the action of estrogen may contribute to a woman's susceptibility to PCOS.

AIM

This study aimed to evaluate the association between the polymorphisms PvuII and XbaI in the estrogen receptor alpha (ESR1) gene and the occurrence of PCOS. The study also aimed to assess the influence of these polymorphisms on the metabolic and inflammatory profiles of women with PCOS.

MATERIAL AND METHODS

This case-control study included 99 women with PCOS, diagnosed according to the Rotterdam criteria, and 104 age-matched healthy women. The polymorphisms were evaluated using polymerase chain reaction-restriction fragment length polymorphism.

RESULTS

No association between the ESR1 gene polymorphisms and the presence of PCOS was observed. However, we found associations between the PvuII polymorphism and C-reactive protein levels, testosterone levels, family history of diabetes, and waist circumference. The XbaI polymorphism was associated with fasting glucose and a family history of hypertension.

CONCLUSION

These polymorphisms are not associated with PCOS development, but they are involved in the phenotype of complications of the syndrome. Therefore, prior knowledge of these genomic variants might contribute to taking preventive measures that could delay the metabolic and reproductive complications commonly seen in women with PCOS.

Correlation between plasminogen activator inhibitor-1 (PAI-1) promoter 4G/5G polymorphism and metabolic/proinflammatory factors in polycystic ovary syndrome

Polycystic Ovary Syndrome (PCOS) is the most common cause of subfertility associated to metabolic disorders. The aim of this study was to correlate metabolic and proinflammatory factors in women with PCOS. The frequency of Plasminogen Activator Inhibitor-1 (PAI-1) promoter 4 G/5 G polymorphism was also compared to healthy controls. We evaluated 79 PCOS and 79 healthy women. PAI-1 levels are positively correlated with proinflammatory factors in PCOS group. 4 G allele in PAI-1 gene was more frequent in PCOS and the 4G/4 G genotype was associated with increased PAI-1 levels. A correlation between insulin resistance and proinflammatory and overweight was also observed. C-reactive protein, serum levels of vascular cell adhesion molecule-1 (sVCAM-1), Lipid Accumulation Product (LAP) and vitamin D are good tools to evaluated factors associated to cardiovascular risk in women with PCOS.