Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort

Ishii, Kaori; Asaoka, Ryo; Fujishiro, Takashi; Mitaki, Shingo; Fujino, Yuri; Murata, Hiroshi; Onoda, Keiichi; Nagai, Atsushi; Yamaguchi, Shûhei; Obana, Akira; Tanito, Masaki

doi:10.1038/s41598-020-80839-4

Cited by 9 publications

(8 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous studies in general populations, an age-dependent decline of IOP was observed. (40,41) The balance between aqueous humor inflow and outflow determines the IOP. Aging causes decreased aqueous humor production (42) and increased trabecular meshwork resistance; (43) thus, SH might affect the IOP via the effects of age.…”

Section: Discussionmentioning

confidence: 99%

Linear association between aging and decreased blood thiol antioxidant activity in patients with cataract

Tanito

Takayanagi

Ishida

et al. 2023

J. Clin. Biochem. Nutr.

Self Cite

View full text Add to dashboard Cite

We comprehensively assessed the roles of systemic redox markers by including both prooxidant and antioxidant markers in 121 Japanese subjects (mean ± SD age, 70 ± 11 years; 38 men) with no ocular pathology except age-related cataract. Serum levels of lipid peroxides, ferric-reducing activity, and thiol antioxidant activity were measured using the diacron reactive oxygen metabolite (dROM), biologic antioxidant potential (BAP), and sulfhydryl (SH) tests, respectively, using a free-radical analyzer. Univariate analyses suggested that older age, higher pulse rate, worse bestcorrected visual acuity (BCVA), higher intraocular pressure, and higher cataract grade were associated with a lower SH level. Scatterplots revealed virtually linear associations between age and the SH level (estimate, −4.4 μM/year). Multivariate analyses suggested that older age, higher systolic blood pressure, and worse BCVA were associated with a lower SH level. Neither the univariate nor multivariate analyses, except between female sex and higher dROM level, were associated with the dROM or BAP level. A lower serum SH level was the driver of aging itself and age-related decline in VA due to cataract. The serum SH level may be an excellent predictor of aging status in each subject.

show abstract

Section: Discussionmentioning

confidence: 99%

Linear association between aging and decreased blood thiol antioxidant activity in patients with cataract

Tanito

Takayanagi

Ishida

et al. 2023

J. Clin. Biochem. Nutr.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Their results showed AUC from 0.89 to 0.97, according to different conditions [ 28 ]. Interestingly, performance of IOP prediction between a multivariate linear regression model (MLM) with 35 systemic variables and a DLS with colour fundus images showed that the former had a better predictive value [ 29 ]. The results may support that it may be better to use demographics to predict physiological parameters than to do glaucoma screening with images.…”

Section: Discussionmentioning

confidence: 99%

Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study

et al. 2022

View full text Add to dashboard Cite

Background To verify efficacy of automatic screening and classification of glaucoma with deep learning system. Methods A cross-sectional, retrospective study in a tertiary referral hospital. Patients with healthy optic disc, high-tension, or normal-tension glaucoma were enrolled. Complicated non-glaucomatous optic neuropathy was excluded. Colour and red-free fundus images were collected for development of DLS and comparison of their efficacy. The convolutional neural network with the pre-trained EfficientNet-b0 model was selected for machine learning. Glaucoma screening (Binary) and ternary classification with or without additional demographics (age, gender, high myopia) were evaluated, followed by creating confusion matrix and heatmaps. Area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score were viewed as main outcome measures. Results Two hundred and twenty-two cases (421 eyes) were enrolled, with 1851 images in total (1207 normal and 644 glaucomatous disc). Train set and test set were comprised of 1539 and 312 images, respectively. If demographics were not provided, AUC, accuracy, precision, sensitivity, F1 score, and specificity of our deep learning system in eye-based glaucoma screening were 0.98, 0.91, 0.86, 0.86, 0.86, and 0.94 in test set. Same outcome measures in eye-based ternary classification without demographic data were 0.94, 0.87, 0.87, 0.87, 0.87, and 0.94 in our test set, respectively. Adding demographics has no significant impact on efficacy, but establishing a linkage between eyes and images is helpful for a better performance. Confusion matrix and heatmaps suggested that retinal lesions and quality of photographs could affect classification. Colour fundus images play a major role in glaucoma classification, compared to red-free fundus images. Conclusions Promising results with high AUC and specificity were shown in distinguishing normal optic nerve from glaucomatous fundus images and doing further classification.

show abstract

“…Intraocular pressure (IOP) is the amount of fluid pressure within the eye and is one of the most important examination metrics in ophthalmic clinics ( 11 ). It is an important marker for many ophthalmic diseases such as glaucoma and intraocular pressure that is too high or too low will damage eye tissues and visual functions to different degrees ( 12 ).…”

Section: Introductionmentioning

confidence: 99%

“…It is worth noting that according to a previous study, there was a significant increase in IOP in patients with severe and critical COVID-19 disease ( 15 ). Therefore, it is reasonable to think that in the autoimmune stage of COVID-19, a considerable number of patients may exhibit subclinical ocular inflammation and possibly high intraocular pressure ( 11 ). If high IOP is not dealt with in time, it may lead to irreversible vision loss.…”

Section: Introductionmentioning

confidence: 99%

The causal relationship between COVID-19 and increased intraocular pressure: A bidirectional two-sample Mendelian randomization study

Lin

Jiang²,

Cai³

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

BackgroundCoronavirus disease 2019 (COVID-19) has brought great challenges to the global public health system and huge economic burdens to society, the causal effect of COVID-19 and intraocular pressure was blank.ObjectiveThis study aimed to explore the causal association between coronavirus disease (COVID-19) susceptibility, severity and criticality and intraocular pressure (IOP) by bidirectional Mendelian randomization (MR) analysis.Materials and methodsGenetic associations with COVID-19 susceptibility, severity and criticality were obtained from the COVID-19 Host Genetics Initiative. Genetic associations with IOP were obtained from GWAS summary data. The standard inverse variance weighted (IVW) method was used in the primary assessment of this causality. Other methods were also implemented in supplementary analyses. Finally, sensitivity analysis was performed to evaluate the reliability and stability of the results.ResultsThe results showed that COVID-19 susceptibility had null effect on IOP (β = 0.131; Se = 0.211; P = 0.533) as assessed by the IVW method. Moreover, the results revealed that COVID-19 severity, specifically, hospitalization due to COVID-19, had a positive effect on IOP with nominal significance (β = 0.228; Se = 0.116; P = 0.049). However, there were null effect of COVID-19 criticality on IOP (β = 0.078; Se = 0.065; P = 0.227). Sensitivity analysis showed that all the results were reliable and stable. The reverse MR analysis revealed that there was null effect of IOP on COVID-19.ConclusionsWe demonstrated that hospitalization due to COVID-19 might increase IOP; therefore, greater attention should be given to monitoring IOP in inpatients with COVID-19.

show abstract

Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort

Cited by 9 publications

References 69 publications

Linear association between aging and decreased blood thiol antioxidant activity in patients with cataract

Linear association between aging and decreased blood thiol antioxidant activity in patients with cataract

Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study

The causal relationship between COVID-19 and increased intraocular pressure: A bidirectional two-sample Mendelian randomization study

Contact Info

Product

Resources

About