Obesity, Blood Pressure, and Intraocular Pressure: A Cross-Sectional Study in Italian Children

Integrating Deep Learning with Electronic Health Records for Early Glaucoma Detection: A Multi-Dimensional Machine Learning Approach

BACKGROUND

Recent advancements in deep learning have significantly impacted ophthalmology, especially in glaucoma, a leading cause of irreversible blindness worldwide. In this study, we developed a reliable predictive model for glaucoma detection using deep learning models based on clinical data, social and behavior risk factor, and demographic data from 1652 participants, split evenly between 826 control subjects and 826 glaucoma patients.

METHODS

We extracted structural data from control and glaucoma patients' electronic health records (EHR). Three distinct machine learning classifiers, the Random Forest and Gradient Boosting algorithms, as well as the Sequential model from the Keras library of TensorFlow, were employed to conduct predictive analyses across our dataset. Key performance metrics such as accuracy, F1 score, precision, recall, and the area under the receiver operating characteristics curve (AUC) were computed to both train and optimize these models.

RESULTS

The Random Forest model achieved an accuracy of 67.5%, with a ROC AUC of 0.67, outperforming the Gradient Boosting and Sequential models, which registered accuracies of 66.3% and 64.5%, respectively. Our results highlighted key predictive factors such as intraocular pressure, family history, and body mass index, substantiating their roles in glaucoma risk assessment.

CONCLUSIONS

This study demonstrates the potential of utilizing readily available clinical, lifestyle, and demographic data from EHRs for glaucoma detection through deep learning models. While our model, using EHR data alone, has a lower accuracy compared to those incorporating imaging data, it still offers a promising avenue for early glaucoma risk assessment in primary care settings. The observed disparities in model performance and feature significance show the importance of tailoring detection strategies to individual patient characteristics, potentially leading to more effective and personalized glaucoma screening and intervention.

The Effect of Childhood Obesity on Intraocular Pressure, Corneal Biomechanics, Retinal Nerve Fiber Layer, and Central Macular Thickness

PRCIS

Elevated corneal hysteresis (CH) and resistance factor (CRF) in obese and overweight children imply weight's effect on corneal biomechanics. Increased Goldmann-correlated intraocular pressure (IOPg) in obese children indicates glaucoma risk, emphasizing screening for IOP and retinal changes.

PURPOSE

To evaluate the effect of obesity on corneal biomechanics, retinal nerve fiber layer (RNFL), and central macular thickness (CMT) in children.

PATIENTS AND METHODS

In this prospective, cross-sectional, comparative study, 146 eyes of normal-weight, over-weight, and obese children aged between 6 to 17 years were evaluated. The IOPg, corneal compensated IOP (IOPcc), CH, CRF, and the average retinal nerve fiber layer (RNFL), average cup-to-disk ratio (c/d), and central macular thickness (CMT) were measured by Ocular Response Analyser and Spectral-Domain Optical Coherence Tomography (SD-OCT), respectively.

RESULTS

There was no statistically significant difference regarding age, gender, IOPcc, average RNFL thickness, c/d ratio, and CMT among the groups ( P ≥0.05). The IOPg was significantly higher in obese children compared with normal-weight children, while CH and CRF values were significantly higher in both obese and over-weight children compared with healthy ones ( P <0.05). There was a positive correlation between BMI percentile and IOPg, CH, and CRF values.

CONCLUSION

In our study, higher IOPg, corneal hysteresis, and corneal resistance factor values suggest that obese children could be potential candidates for glaucoma. Therefore, it would be appropriate to screen them for IOP and retinal alterations. Further investigations with larger sample size and longer follow-up are needed to understand the risk of glaucoma in obese children.

Microbiome Dysbiosis: A Pathological Mechanism at the Intersection of Obesity and Glaucoma

The rate at which obesity is becoming an epidemic in many countries is alarming. Obese individuals have a high risk of developing elevated intraocular pressure and glaucoma. Additionally, glaucoma is a disease of epidemic proportions. It is characterized by neurodegeneration and neuroinflammation with optic neuropathy and the death of retinal ganglion cells (RGC). On the other hand, there is growing interest in microbiome dysbiosis, particularly in the gut, which has been widely acknowledged to play a prominent role in the etiology of metabolic illnesses such as obesity. Recently, studies have begun to highlight the fact that microbiome dysbiosis could play a critical role in the onset and progression of several neurodegenerative diseases, as well as in the development and progression of several ocular disorders. In obese individuals, gut microbiome dysbiosis can induce endotoxemia and systemic inflammation by causing intestinal barrier malfunction. As a result, bacteria and their metabolites could be delivered via the bloodstream or mesenteric lymphatic vessels to ocular regions at the level of the retina and optic nerve, causing tissue degeneration and neuroinflammation. Nowadays, there is preliminary evidence for the existence of brain and intraocular microbiomes. The altered microbiome of the gut could perturb the resident brain-ocular microbiome ecosystem which, in turn, could exacerbate the local inflammation. All these processes, finally, could lead to the death of RGC and neurodegeneration. The purpose of this literature review is to explore the recent evidence on the role of gut microbiome dysbiosis and related inflammation as common mechanisms underlying obesity and glaucoma.

Obesity-induced ocular changes in children and adolescents: A review

Childhood obesity has reached epidemic levels worldwide. Overweight and obesity is associated with an increase in several inflammatory markers, leading to chronic low-grade inflammation responsible for macro- and microvascular dysfunction. While the impact of obesity on overall health is well-described, less is known about its ocular manifestations. Still, there are few studies in children and adolescents in this regard and they are inconsistent. However, some evidence suggests a significant role of overnutrition in the development of changes in retinal microvasculature parameters (wider venules, narrower arterioles, lower arteriovenous ratio). Higher values of intraocular pressure were found to be positively correlated with high body mass index (BMI) as well as obesity. In addition, the retinal nerve fiber layer (RNFL) values seem to be lower in obese children, and there is a significant negative correlation between RNFL values and anthropometric and/or metabolic parameters. Changes also could be present in macular retinal thickness and choroidal thickness as well as in the retinal vessel density in children with obesity. However, these associations were not consistently documented. The purpose of this review is to present the most current issues on child obesity and the related potential ocular effects through an overview of international publications from the years 1992-2022.

Weight self-stigma and engagement among obese students in a physical education class

BACKGROUND

This is a cross-sectional in design. It involves the mediating effects of basic psychological need satisfaction in relation to the moderating effects of teacher autonomy support regarding weight self-stigma's effect on engagement among obese students in physical education classes.

METHODS

This study includes 165 Chinese high school obese students [mean age, 16.84 (±0.147) years], comprising 93 males (56.63%) and 72 females (43.63%), with a mean body mass index (BMI) of 30.453 (SD = 2.426). Participants completed the weight self-stigma questionnaire, basic psychological need satisfaction questionnaire, teacher autonomy support questionnaire, and student engagement questionnaire.

RESULTS

Weight self-stigma and engagement among obese students were mediated by basic psychological need satisfaction. Moreover, the mediated effect of basic psychological need satisfaction was moderated by teacher autonomy support.

CONCLUSION

Weight self-stigma and basic psychological need satisfaction are the antecedents influencing the engagement of obese students. Notably, weight self-stigma not only directly blocks the engagement of obese students but also their engagement by hindering the acquisition of basic psychological need satisfaction. Teacher autonomy support can significantly reduce the negative impact of weight self-stigma on basic psychological need satisfaction and significantly promote engagement. Therefore, by promoting their physical education engagement, physical education teachers should strengthen the application of their supportive autonomous teaching strategies to help obese students meet their basic psychological needs.

Poor Uncorrected Visual Acuity and Association With Sleep Duration and Screen Time: A Dose-Response Relationship Study

Background

We aimed to investigate the prevalence of poor uncorrected visual acuity and the difference among students with different ages and residential areas in the Northeast of China. The relationships between screen time, nighttime sleep duration, and poor uncorrected visual acuity would be explored.

Methods

It was a cross-sectional study using multi-stage stratified random sampling method to recruit participants. 2149 students have completed questionnaires and underwent visual acuity examinations. The dose–response curve method was applied to examine the non-linear associations between sleep duration and poor uncorrected visual acuity under different screen time subgroups.

Results

The overall prevalence of poor uncorrected visual acuity and severe poor uncorrected visual acuity was 84.7% and 63.3%, respectively. The dose–response curve showed the odds ratios (ORs) of sleep duration for the poor uncorrected visual increased relatively slowly when screen time <1 hour, then increased dramatically in screen time ≥1 hours. The ORs of sleep time and poor uncorrected visual acuity showed a U-shaped change trend among students with 2 or more hours of screen time every day.

Conclusion

We found associations between nighttime sleep duration and poor uncorrected visual acuity in adolescents. However, these associations were not consistent across all screen time categories.

Greenness Surrounding Schools and Visual Impairment in Chinese Children and Adolescents

BACKGROUND

Evidence concerning the effects of greenness on childhood visual impairment is scarce.

OBJECTIVES

We aimed to assess whether greenness surrounding schools was associated with visual impairment prevalence and visual acuity levels in Chinese schoolchildren and whether the associations might be explained by reduced air pollution.

METHODS

In September 2013, we recruited 61,995 children and adolescents 6-18 years of age from 94 schools in seven provinces/municipalities in China. Greenness exposure was assessed using the normalized difference vegetation index (NDVI) and the soil-adjusted vegetation index (SAVI) from July to August 2013. Visual impairment was defined as at least one visual acuity level (dimensionless) lower than 4.9 (Snellen 5/6 equivalent). Three-year annual averages of particulate matter (PM) with an aerodynamic diameter of ≤1μm (PM1) and nitrogen dioxide (NO2) at each school were assessed using machine learning methods. We used generalized linear mixed models to estimate the associations between greenness and prevalent visual impairment and visual acuity levels and used mediation analyses to explore the potential mediating role of air pollution.

RESULTS

In the adjusted model, an interquartile range increase in NDVI500m was associated with lower odds of prevalent visual impairment [odds ratio (OR)=0.95; 95% confidence interval (CI): 0.93, 0.97]. The same increase in NDVI500m was also associated with 0.012 (95% CI: 0.008, 0.015) and 0.011 (95% CI: 0.007, 0.015) increases in visual acuity levels for left- and right-eye, respectively. Our results also suggested that PM1 and NO2 significantly mediated the association between NDVI500m and visual impairment. Similar effect estimates were observed for SAVI500m, and our estimates were generally robust in several sensitivity analyses.

DISCUSSION

These findings suggest higher greenness surrounding schools might reduce the risk of visual impairment, possibly owing in part to lower PM1 and NO2 in vegetated areas. Further longitudinal studies with more precise greenness assessment are warranted to confirm these findings. https://doi.org/10.1289/EHP8429.