MyMedR

Displaying all 8 publications

Abstract:

Sort:

Retinal vascular fractal and blood pressure in a multiethnic population

Sng CC, Wong WL, Cheung CY, Lee J, Tai ES, Wong TY

J Hypertens, 2013 Oct;31(10):2036-42.
PMID: 23787404 DOI: 10.1097/HJH.0b013e328362c201

OBJECTIVE(S): To examine the effect of blood pressure (BP) on retinal vascular fractal dimension (Df), a measure of microvascular network complexity and density in a multiethnic cohort.
METHODS: A population-based study of 3876 Chinese, Malay and Indian participants in Singapore. Retinal Df was measured using a computer-based program from digital retinal photographs. Associations between retinal Df and mean arterial BP (MABP) in the whole cohort and in each racial group were analysed using linear regression analysis. Logistic regression was used to examine the association between retinal Df and hypertension status.
RESULTS: The mean retinal Df of the study population was 1.45 (standard deviation 0.03). After adjustment for age, sex, race, diabetes, BMI, cholesterol and creatinine levels, persons with smaller Df had higher MABP (mean difference MABP was 6.18 mmHg comparing lowest to highest Df quartiles, P<0.001). This was similar in Chinese, Malay and Indian persons [mean difference 6.40 (P<0.001), 4.72 (P=0.011) and 6.62 (P<0.001)mmHg, respectively]. Persons with smaller retinal Df were more likely to have uncontrolled treated or untreated hypertension [odds ratio 1.79 (P=0.003) and 2.60 (P=0.003), respectively, comparing lowest to highest Df quartiles] than those with no hypertension; this relationship was not seen comparing persons with controlled treated hypertension with no hypertension (odds ratio 1.01, P=0.972).
CONCLUSION: Hypertension was associated with a sparser retinal vascular network, which was similar across different racial/ethnic groups and most apparent in those with uncontrolled or untreated hypertension. These data suggest that microvascular remodelling can be quantified by measuring retinal vasculature.
Prevalence and risk factors of epiretinal membrane in Asian Indians

Koh V, Cheung CY, Wong WL, Cheung CM, Wang JJ, Mitchell P, et al.

Invest Ophthalmol Vis Sci, 2012 Feb;53(2):1018-22.
PMID: 22247478 DOI: 10.1167/iovs.11-8557

To describe the prevalence of epiretinal membrane (ERM) and its risk factors in an Indian population and compare the findings with other populations.
Fulltext Retinal vascular geometry in Asian persons with diabetes and retinopathy

Cheung CY, Lamoureux E, Ikram MK, Sasongko MB, Ding J, Zheng Y, et al.

J Diabetes Sci Technol, 2012 May 01;6(3):595-605.
PMID: 22768891 DOI: 10.1177/193229681200600315

Purpose: Our purpose was to examine the relationship of retinal vascular parameters with diabetes and retinopathy in an older Asian population.

Methods: Retinal photographs from participants of a population-based survey of Asian Malay persons aged 40-80 years were analyzed. Specific retinal vascular parameters (tortuosity, branching angle, fractal dimension, and caliber) were measured using a semiautomated computer-based program. Diabetes was defined as random plasma glucose ≥ 11.1 mmol/liter, the use of diabetes medication, or physician-diagnosed diabetes. Retinopathy signs were graded from photographs using the modified Airlie House classification system.

Results: A total of 2735 persons were included in the study. Persons with diabetes (n = 594) were more likely to have straighter (less tortuous) arterioles and wider arteriolar and venular caliber than those without diabetes (n = 2141). Among subjects with diabetes, those with retinopathy had wider venular caliber than those without retinopathy (211.3 versus 204.9 mm, p = .001). Among nondiabetic subjects, however, those with retinopathy had more tortuous venules than those without retinopathy [5.19(×10(4)) versus 4.27(×10(4)), p < .001].

Conclusions: Retinal vascular parameters varied by diabetes and retinopathy status in this older Asian cohort. Our findings suggest that subtle alterations in retinal vascular architecture are influenced by diabetes.
Fulltext Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection

Lemaître G, Rastgoo M, Massich J, Cheung CY, Wong TY, Lamoureux E, et al.

J Ophthalmol, 2016;2016:3298606.
PMID: 27555965 DOI: 10.1155/2016/3298606

This paper addresses the problem of automatic classification of Spectral Domain OCT (SD-OCT) data for automatic identification of patients with DME versus normal subjects. Optical Coherence Tomography (OCT) has been a valuable diagnostic tool for DME, which is among the most common causes of irreversible vision loss in individuals with diabetes. Here, a classification framework with five distinctive steps is proposed and we present an extensive study of each step. Our method considers combination of various preprocessing steps in conjunction with Local Binary Patterns (LBP) features and different mapping strategies. Using linear and nonlinear classifiers, we tested the developed framework on a balanced cohort of 32 patients. Experimental results show that the proposed method outperforms the previous studies by achieving a Sensitivity (SE) and a Specificity (SP) of 81.2% and 93.7%, respectively. Our study concludes that the 3D features and high-level representation of 2D features using patches achieve the best results. However, the effects of preprocessing are inconsistent with different classifiers and feature configurations.
Chronic kidney disease, cardiovascular disease and mortality: A prospective cohort study in a multi-ethnic Asian population

Lim CC, Teo BW, Ong PG, Cheung CY, Lim SC, Chow KY, et al.

Eur J Prev Cardiol, 2015 Aug;22(8):1018-26.
PMID: 24857889 DOI: 10.1177/2047487314536873

BACKGROUND: Few studies have examined the impact of chronic kidney disease (CKD) on adverse cardiovascular outcomes and deaths in Asian populations. We evaluated the associations of CKD with cardiovascular disease (CVD) and all-cause mortality in a multi-ethnic Asian population.
DESIGN: Prospective cohort study of 7098 individuals who participated in two independent population-based studies involving Malay adults (n = 3148) and a multi-ethnic cohort of Chinese, Malay and Indian adults (n = 3950).
METHODS: CKD was assessed from CKD-EPI estimated glomerular filtration rate (eGFR) and urine albumin-to-creatinine ratio (UACR). Incident CVD (myocardial infarction, stroke and CVD mortality) and all-cause mortality were identified by linkage with national disease/death registries.
RESULTS: Over a median follow-up of 4.3 years, 4.6% developed CVD and 6.1% died. Risks of both CVD and all-cause mortality increased with decreasing eGFR and increasing albuminuria (all p-trend <0.05). Adjusted hazard ratios (HR (95% confidence interval)) of CVD and all-cause mortality were: 1.54 (1.05-2.27) and 2.21 (1.67-2.92) comparing eGFR <45 vs ≥60; 2.81 (1.49-5.29) and 2.34 (1.28-4.28) comparing UACR ≥300 vs <30. The association between eGFR <60 and all-cause mortality was stronger among those with diabetes (p-interaction = 0.02). PAR of incident CVD was greater among those with UACR ≥300 (12.9%) and that of all-cause mortality greater among those with eGFR <45 (16.5%).
CONCLUSIONS: In multi-ethnic Asian adults, lower eGFR and higher albuminuria were independently associated with incident CVD and all-cause mortality. These findings extend previously reported similar associations in Western populations to Asians and emphasize the need for early detection of CKD and intervention to prevent adverse outcomes.
Quantitative and qualitative retinal microvascular characteristics and blood pressure

Cheung CY, Tay WT, Mitchell P, Wang JJ, Hsu W, Lee ML, et al.

J Hypertens, 2011 Jul;29(7):1380-91.
PMID: 21558958 DOI: 10.1097/HJH.0b013e328347266c

The present study examined the effects of blood pressure on a spectrum of quantitative and qualitative retinal microvascular signs.
An anomaly detection approach for the identification of DME patients using spectral domain optical coherence tomography images

Sidibé D, Sankar S, Lemaître G, Rastgoo M, Massich J, Cheung CY, et al.

Comput Methods Programs Biomed, 2017 Feb;139:109-117.
PMID: 28187882 DOI: 10.1016/j.cmpb.2016.11.001

This paper proposes a method for automatic classification of spectral domain OCT data for the identification of patients with retinal diseases such as Diabetic Macular Edema (DME). We address this issue as an anomaly detection problem and propose a method that not only allows the classification of the OCT volume, but also allows the identification of the individual diseased B-scans inside the volume. Our approach is based on modeling the appearance of normal OCT images with a Gaussian Mixture Model (GMM) and detecting abnormal OCT images as outliers. The classification of an OCT volume is based on the number of detected outliers. Experimental results with two different datasets show that the proposed method achieves a sensitivity and a specificity of 80% and 93% on the first dataset, and 100% and 80% on the second one. Moreover, the experiments show that the proposed method achieves better classification performance than other recently published works.
Fulltext Acceptance and Perception of Artificial Intelligence Usability in Eye Care (APPRAISE) for Ophthalmologists: A Multinational Perspective

Gunasekeran DV, Zheng F, Lim GYS, Chong CCY, Zhang S, Ng WY, et al.

Front Med (Lausanne), 2022;9:875242.
PMID: 36314006 DOI: 10.3389/fmed.2022.875242

BACKGROUND: Many artificial intelligence (AI) studies have focused on development of AI models, novel techniques, and reporting guidelines. However, little is understood about clinicians' perspectives of AI applications in medical fields including ophthalmology, particularly in light of recent regulatory guidelines. The aim for this study was to evaluate the perspectives of ophthalmologists regarding AI in 4 major eye conditions: diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and cataract.
METHODS: This was a multi-national survey of ophthalmologists between March 1st, 2020 to February 29th, 2021 disseminated via the major global ophthalmology societies. The survey was designed based on microsystem, mesosystem and macrosystem questions, and the software as a medical device (SaMD) regulatory framework chaired by the Food and Drug Administration (FDA). Factors associated with AI adoption for ophthalmology analyzed with multivariable logistic regression random forest machine learning.
RESULTS: One thousand one hundred seventy-six ophthalmologists from 70 countries participated with a response rate ranging from 78.8 to 85.8% per question. Ophthalmologists were more willing to use AI as clinical assistive tools (88.1%, n = 890/1,010) especially those with over 20 years' experience (OR 3.70, 95% CI: 1.10-12.5, p = 0.035), as compared to clinical decision support tools (78.8%, n = 796/1,010) or diagnostic tools (64.5%, n = 651). A majority of Ophthalmologists felt that AI is most relevant to DR (78.2%), followed by glaucoma (70.7%), AMD (66.8%), and cataract (51.4%) detection. Many participants were confident their roles will not be replaced (68.2%, n = 632/927), and felt COVID-19 catalyzed willingness to adopt AI (80.9%, n = 750/927). Common barriers to implementation include medical liability from errors (72.5%, n = 672/927) whereas enablers include improving access (94.5%, n = 876/927). Machine learning modeling predicted acceptance from participant demographics with moderate to high accuracy, and area under the receiver operating curves of 0.63-0.83.
CONCLUSION: Ophthalmologists are receptive to adopting AI as assistive tools for DR, glaucoma, and AMD. Furthermore, ML is a useful method that can be applied to evaluate predictive factors on clinical qualitative questionnaires. This study outlines actionable insights for future research and facilitation interventions to drive adoption and operationalization of AI tools for Ophthalmology.