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.

13-cis-retinoic acid in silicone-fluorosilicone copolymer oil in a rabbit model of proliferative vitreoretinopathy.

The purpose of this study was to evaluate the effect of 13-cis-Retinoic Acid (RA) in Silicone-Fluorosilicone Copolymer Oil (SiFO) in a rabbit model of proliferative vitreoretinopathy (PVR). Rabbits underwent gas-compression vitrectomy. During gas-SiFO exchange, group 1 was injected with 1 ml (10 microg ml-1) 13-cis-RA in SiFO, group 2 with 1.5 ml (9 microg 1.5 ml-1) all-trans-RA in SiFO, group 3 with 1 ml SiFO alone, and group 4 with balanced salt solution (BSS). Groups 1-4 were also injected with 0.1 ml suspension of fibroblasts (75,000 0.1 ml-1) and 0.05 ml platelet rich plasma (70,000 0.1 ml-1), and were observed for 4 weeks. Group 5 was injected with SiFO alone, group 6 with 1 ml (10 microg ml-1) 13-cis-RA in SiFO, group 7 with 1.5 ml (9 microg 1.5 ml-1) all-trans-RA in SiFO, and group 8 with BSS. After 4 weeks, groups 5-7 underwent SiFO-BSS exchange. ERG and histopathology were performed to test for retinal toxicity in groups 5-8. The incidence of traction retinal detachment at 4 weeks was: group 1, 42.9%; group 2, 36.4%; group 3, 87.5%; and group 4, 88.9%. A significant difference in the incidence of PVR was noted between treated eyes (groups 1 and 2) and control eyes (groups 3 and 4) at 2, 3, and 4 weeks (P<0.05). No significant difference in the incidence of PVR was found between groups 1 and 2 during the same observation periods. ERG and histopathological studies showed no differences between the treated and the control fellow eyes (group 5-7) after 4 weeks. 13-cis-RA in SiFO (10 microg ml-1) is as effective as all-trans-RA in SiFO (9 microg 1.5 ml-1) in controlling the incidence of PVR when used for short term retinal tamponade and does not appear to be associated with retinal toxicity.