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.

Photodynamic tissue adhesion with chlorin(e6) protein conjugates

PURPOSE

To test the hypothesis that a photodynamic laser-activated tissue solder would perform better in sealing scleral incisions when the photosensitizer was covalently linked to the protein than when it was noncovalently mixed.

METHODS

Conjugates and mixtures were prepared between the photosensitizer chlorin(e6) and various proteins (albumin, fibrinogen, and gelatin) in different ratios and used to weld penetrating scleral incisions made in human cadaveric eyes. A blue-green (488-514 nm) argon laser activated the adhesive, and the strength of the closure was measured by increasing the intraocular pressure until the wound showed leakage.

RESULTS

Both covalent conjugates and noncovalent mixtures showed a light dose-dependent increase in leaking pressure. A preparation of albumin chlorin(e6) conjugate with additional albumin added (2.5 protein to chlorin(e6) molar ratio) showed significantly higher weld strength than other protein conjugates and mixtures.

CONCLUSIONS

This is the first report of dye-protein conjugates as tissue solders. These conjugates may have applications in ophthalmology.

Antiproliferative effect of intravitreal alpha-tocopherol and alpha-tocopheryl-acid-succinate in a rabbit model of PVR

PURPOSE

To evaluate the antiproliferative properties of alpha-tocopherol and alpha-tocopheryl-acid-succinate in a rabbit model of proliferative vitreoretinopathy.

METHODS

Fifty-seven rabbits underwent gas-compression vitrectomy and gas/fluid exchange. Group 1 (n = 8): 50 micrograms alpha-tocopherol in 1 ml of 0.5% ethanol in balanced salt solution; Group 2 (n = 8): 50 micrograms alpha-tocopheryl-acid-succinate in 1 ml of 0.5% ethanol in balanced salt solution; Groups 3 (n = 4) and 4 (n = 2): 1 ml 0.5% ethanol in balanced salt solution; Groups 5 (n = 12) and 8 (n = 9): alpha-tocopherol in 1 ml silicone oil (12 mg/ml); Group 6 (n = 9): 1 ml silicone oil; Group 7 (n = 5): 1 ml balanced salt solution. Groups 1-3, and 5-7 also received fibroblasts and platelet-rich plasma injection. Fundus evaluation was performed during a four-week period. The eyes were enucleated for gross examination on day 28. Histopathology was performed on Group 4.

RESULTS

Alpha-tocopherol and alpha-tocopheryl-acid-succinate in saline solution delayed development of proliferative vitreoretinopathy, compared to the control group (statistically significant during the first week, Mann Whitney, p < 0.05). The alpha-tocopherol in the silicone-oil group delayed development of proliferative vitreoretinopathy, compared to the silicone-oil group during the second to fourth weeks (no statistically significant difference, p > 0.05).

CONCLUSIONS

Alpha-tocopherol and alpha-tocopheryl-acid-succinate in saline solution showed retardation of proliferative vitreoretinopathy traction retinal detachments. In silicone oil, alpha-tocopherol is slowly released and decreases the severity of proliferative vitreoretinopathy, especially during the second week of follow-up.

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.

Ganciclovir-loaded polymer microspheres in rabbit eyes inoculated with human cytomegalovirus

PURPOSE

To test the antiviral effect of ganciclovir released from biodegradable polymer microspheres in rabbit eyes inoculated with human cytomegalovirus (HCMV).

METHODS

Human cytomegalovirus (5 x 10(3) plaque forming unit in 0.1 ml Hank's balanced salt solution) was inoculated 4 days after gas compression vitrectomy. Injected after 2 days was 10 mg of 300- to 500-micron ganciclovir-loaded microspheres (89.77 micrograms ganciclovir/mg) suspended in 0.1 ml of 2% hydroxypropylmethylcellulose. Blank microspheres were injected as control specimens. Vitritis, retinitis, and optic neuritis were graded from 0(+)-4+ for 14 days to separate the early HCMV-induced disease events from later nonspecific host inflammatory responses. Ganciclovir-loaded microspheres also were injected and observed for biodegradation and tissue reaction for 8 weeks.

RESULTS

In eyes injected with ganciclovir-loaded microspheres, vitritis decreased from days 3 to 14, and retinitis and optic neuritis decreased from days 3 to 9. In eyes injected with blank microspheres, vitritis increased from days 3 to 7, retinitis increased from days 3 to 9, and optic neuritis increased from days 3 to 14. Immunofluorescence of HCMV antigens in retinal tissues was shown only in eyes injected with blank microspheres. Histopathologic analysis showed minimal focal disruption of the retinal architecture in eyes injected with ganciclovir-loaded microspheres. Disorganization of the normal retinal architecture was observed in eyes injected with blank microspheres. No adverse tissue reaction was observed clinically and histopathologically in eyes injected with ganciclovir-loaded microspheres after 8 weeks.

CONCLUSIONS

Ten milligrams of 300 to 500 microns ganciclovir-loaded poly(D,L-lactide-co-glycolide) microspheres control the progression of fundus disease in HCMV-inoculated rabbit eyes.