Integrating Machine Learning and Traditional Survival Analysis to Identify Key Predictors of Foveal Involvement in Geographic Atrophy.

Purpose: The purpose of this study was to investigate the incidence of foveal involvement in geographic atrophy (GA) secondary to age-related macular degeneration (AMD), using machine learning to assess the importance of risk factors. Methods: Retrospective, longitudinal cohort study. Patients diagnosed with foveal-sparing GA, having GA size ≥ 0.049 mm² and follow-up ≥ 6 months, were included. Baseline GA area, distance from the fovea, and perilesional patterns were measured using fundus autofluorescence. Optical coherence tomography assessed foveal involvement, structural biomarkers, and outer retinal layers thickness. Onset of foveal involvement was recorded. Foveal survival rates were estimated using Kaplan-Meier curves. Hazard ratios (HRs) were assessed with mixed model Cox regression. Variable Importance (VIMP) was ranked with Random Survival Forests (RSF), with higher scores indicating greater predictive significance. Results: One hundred sixty-seven eyes (115 patients, average age = 75.8 ± 9.47 years) with mean follow-up of 50 ± 29 months, were included in this study. Median foveal survival time was 45 months (95% confidence interval [CI] = 38-55). Incidences of foveal involvement were 26% at 24 months and 67% at 60 months. Risk factors were GA proximity to the fovea (HR = 0.97 per 10-µm increase, 95% CI = 0.96-0.98), worse baseline visual acuity (HR = 1.37 per 0.1 LogMAR increase, 95% CI = 1.21-1.53), and thinner outer nuclear layer (HR = 0.59 per 10-µm increase, 95% CI = 0.46-0.74). RSF analysis confirmed these as main predictors (VIMP = 16.7, P = 0.002; VIMP = 6.2, P = 0.003; and VIMP = 3.4, P = 0.01). Lesser baseline GA area (HR = 1.09 per 1-mm2 increase, 95% CI = 1.01-1.16) and presence of a double layer sign (HR = 0.42, 95% CI = 0.20-0.88) were protective but less influential. Conclusions: This study identifies anatomic and functional factors impacting the risk of foveal involvement in GA. These findings may help identify at-risk patients, enabling tailored preventive strategies.

Peripheral and central capillary non-perfusion in diabetic retinopathy: An updated overview.

Capillary non-perfusion (CNP) is one of the key hallmarks of diabetic retinopathy (DR), which may develop both in the periphery and at the posterior pole. Our perspectives on CNP have extended with the introduction of optical coherence tomography angiography (OCTA) and ultra-widefield imaging, and the clinical consequences of peripheral and macular CNP have been well characterized. Fluorescein angiography (FA) continues to be the gold standard for detecting and measuring CNP, particularly when ultra-widefield imaging is available. OCTA, on the other hand, is a quicker, non-invasive approach that allows for a three-dimensional examination of CNP and may soon be regarded as an useful alternative to FA. In this review, we provide an updated scenario regarding the characteristics, clinical impact, and management of central and peripheral CNP in DR.

The impact of short-term hyperglycemia and obesity on biventricular and biatrial myocardial function assessed by speckle tracking echocardiography in a population of women with gestational diabetes mellitus.

BACKGROUND AND AIMS: To compare biventricular and biatrial myocardial strain indices assessed by two-dimensional speckle tracking echocardiography (2D-STE) in women with gestational diabetes mellitus (GDM) and those with uncomplicated pregnancy at the third trimester of pregnancy and in post-partum. METHODS AND RESULTS: 30 consecutive GDM women and 30 age-, ethnicity- and gestational week-matched controls without any comorbidity were examined in this prospective case-control study. All women underwent obstetric visit, blood tests and transthoracic echocardiography (TTE) implemented with 2D-STE analysis of all cardiac chambers at 36-38 weeks' gestation. TTE and 2D-STE were repeated at 6-10 weeks after delivery. At 36-38 weeks' gestation, GDM women, compared to controls, had significantly higher body mass index (BMI), blood pressure values and inflammatory markers. TTE showed increased left ventricular (LV) mass and impaired LV diastolic function in GDM women, whereas there was no significant difference between the groups in ejection fraction. 2D-STE revealed that biventricular global longitudinal strain (GLS) and biatrial reservoir strain indices were significantly lower in GDM women than controls. Third trimester BMI was inversely correlated with LV-GLS (r = -0.86) and was independently associated with reduced LV-GLS (less negative than -20%) in GDM women in post-partum (OR 1.81, 95%CI 1.14-2.89). A BMI value ≥ 30 kg/m2 had 100% sensitivity and 99.5% specificity for identifying GDM women with impaired LV-GLS in post-partum (AUC = 0.97). CONCLUSION: Women with GDM, compared to women with uncomplicated pregnancy, have significantly lower biventricular and biatrial myocardial deformation indices. These abnormalities may be persistent in post-partum in GDM women with obesity.