scholarly journals Gender prediction via deep learning across different retinal fundus photograph fields: a multi-ethnic study (Preprint)

2020 ◽  
Author(s):  
Bjorn Kaijun Betzler ◽  
Henrik Seung Yang Hee ◽  
Sahil Thakur ◽  
Marco Yu ◽  
Ten Cheer Quek ◽  
...  
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Asian Population ◽  
Eye Diseases ◽  
Older Age ◽  
Cross Sectional ◽  
Individual Level ◽  
Performance Of Gender ◽  
Retinal Fundus ◽  
Retinal Photographs

BACKGROUND Deep Learning (DL) algorithms have been built for detection of systemic and eye diseases from retinal photographs. The retina possesses features which can be affected by gender differences, and the extent to which these features are captured upon photography differs depending on the retinal image field. OBJECTIVE To compare DL algorithms’ performance in predicting gender when using different fields of retinal photographs (disc-centered, macula-centered, peripheral). METHODS This retrospective cross-sectional study included 172,170 retinal photographs from 9956 adults aged ≥ 40 years from the Singapore Epidemiology of Eye Diseases (SEED) Study. Optic disc-centered, macula-centered and peripheral field retinal fundus images were included in this study as input to a DL model for gender prediction. Performance was estimated at individual level and image level. Receiver operating characteristic (ROC) curves for binary classification were calculated. RESULTS The DL algorithms predicted gender with area under the ROC (AUC) of 0.94 at individual-level and AUC of 0.87 at image-level. Across the three image fields, the best performance was seen in disc-centered (AUC: 0.91 in younger and 0.86 in older age subgroups), and peripheral field images showed the lowest performance (AUC: 0.85 in younger and 0.76 in older subgroups). Between the three ethnic subgroups, performance was lowest in the Indian subgroup (AUC: 0.88) compared to Malay (AUC: 0.91) and Chinese (AUC: 0.91) when tested on disc-centered images. The performance of gender prediction at the image level was better in younger age subgroups of < 65 years (AUC: 0.89) than in older age subgroups of ≥ 65 years (AUC: 0.82). CONCLUSIONS We confirmed that gender can be predicted from retinal photographs using DL in Asian population, and the performance of gender prediction differ according to field of retinal photographs, age-subgroups, and ethnic groups. Our work provides a further understanding of using DL models for prediction of gender-related diseases. Further validation of our findings is still needed.

scholarly journals Screening of Diabetes and Hypertension Based on Retinal Fundus Photographs Using Deep Learning

2019 ◽  
Author(s):  
Guangzheng Dai ◽  
Chenguang Zhang ◽  
Wei He
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Diabetic Control ◽  
Fine Tuning ◽  
Classification Model ◽  
Develop Model ◽  
Test Model ◽  
Fundus Photographs ◽  
Retinal Fundus ◽  
Retinal Photographs

ABSTRACTPurposeThe aim of this study was to use deep learning to screen for hypertension and diabetes based on retinal fundus images.MethodsWe collected 1160 retinal photographs which included 580 from patients with a diagnosis of hypertension or diabetes and 580 from normotensive and non-diabetic control. We divided this image dataset into (i) a development dataset to develop model and (ii) test dataset which were not present during the training process to assess model’s performance. A binary classification model was trained by fine-tuning the classifier and the last convolution layer of deep residual network. Precision, recall, the area under the ROC (AUC), and the area under the Precision-Recall curve (AUPR) were used to evaluate the performance of the learned model.ResultsWhen we used 3-channel color retinal photographs to train and test model, its prediction precision for diabetes or hypertension was 65.3%, the recall was 82.5%, the AUC was 0.745, and the AUPR was 0.742. When we used grayscale retinal photographs to train and test model, its prediction precision was 70.0%, the recall was 87.5%, the AUC was 0.803, and the AUPR was 0.779.ConclusionsOur study shows that trained deep learning model based on the retinal fundus photographs alone can be used to screen for diabetes and hypertension, although its current performance was not ideal.

scholarly journals Sociodemographic factors in relation to hypertension prevalence, awareness, treatment and control in a multi-ethnic Asian population: a cross-sectional study

BMJ Open ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. e025869 ◽  
Author(s):  
Seaw Jia Liew ◽  
John Tayu Lee ◽  
Chuen Seng Tan ◽  
Choon Huat Gerald Koh ◽  
Rob Van Dam ◽  
...  
Keyword(s):  
Ethnic Groups ◽  
Educational Level ◽  
Asian Population ◽  
Sociodemographic Factors ◽  
Older Age ◽  
Uncontrolled Hypertension ◽  
Cross Sectional ◽  
Hypertension Prevalence ◽  
Younger Age ◽  
And Control

ObjectivesLiterature suggested that multi-ethnic Western populations experienced differential hypertension outcomes, but evidence is limited in Asia. This study was aimed to determine sociodemographic correlates of hypertension and its awareness, treatment and control among a multi-ethnic Asian population living in Singapore.SettingWe used cross-sectional data of participants from the Multi-Ethnic Cohort (MEC) (n=14 530) recruited in Singapore between 2004 and 2010.ParticipantsParticipants who completed questionnaire and attended health examination, without cardiovascular diseases, cancer, stroke, renal failure, asthma and mental illnesses were included in the study. Multivariable logistic regression models were used to determine sociodemographics factors associated with hypertension, unawareness of having hypertension, untreated and uncontrolled hypertension.ResultsAmong 10 215 participants (47.2% Chinese, 26.0% Malay and 26.8% Indian), hypertension prevalence was estimated to be 31.1%. Older age, Malay ethnicity, male, lower educational level and being homemaker or retired/unemployed were factors significantly associated with hypertension. Stratified analysis suggested that age and education were consistently associated with hypertension across all ethnic groups. The proportions of being unaware, untreated and uncontrolled were 49.0%, 25.2% and 62.4%, respectively. Ethnicity and younger age were associated with unawareness; younger age, male and lower educational level were associated with untreated hypertension and older age was associated with uncontrolled hypertension.ConclusionsIn this study, ethnic differences in relation to hypertension were associated with sociodemographic variability in ethnic groups. Age and educational level were consistent correlates of hypertension in all ethnic groups. Unawareness and uncontrolled hypertension were common in this Asian population and associated with sociodemographic factors. More targeted strategies may be required to overcome the observed disparities.

Assessment of Knowledge and Practice of Various Eye Diseases in Sulaimani: A Descriptive Study

2018 ◽  
pp. 1-6
Author(s):  
Abdulrahman M. Ibrahem ◽  
Salah Q. Mahmood ◽  
Muhammed Babakir-Mina ◽  
Salar Ibrahim Ali ◽  
Bakhtyar Kamal Talabany
Keyword(s):  
Vision Loss ◽  
Good Practice ◽  
Study Data ◽  
Eye Diseases ◽  
Vision Impairment ◽  
P Value ◽  
Published Data ◽  
Knowledge Level ◽  
Cross Sectional ◽  
Knowledge And Practice

Knowledge and practice of public, especially patients about eye diseases are important to reduce magnitude of human blindness. Vision and sight are very essential because they allow us to connect to each other’s. In accordance to the recently published data; the estimation of 253 million people lives with vision impairment, 36 million are blind and 217 million suffer from moderate to severe vision impairment. A descriptive cross-sectional study was conducted at Shahid Dr. Aso Hospital in Sulaimani city-Iraq, from April to August 2017 by face-to-face interview through close ended questionnaire for data collecting. All data were analyzed by Statistical Package for Social Sciences version 22.0 software. P-value of < 0.05 was considered as a statistically significant. A total of 430 patients were randomly chosen to participate in the study. They were 254 (59.1%) males and 176 (40.9%) females. 76.7% of respondents was worrying about vision loss, 0.7% was worrying about hair loss. Of the participants, 32.8% was with a good knowledge level and 40.5% was with a poor knowledge level, as well as 3.1% was in a good practice and 58.8% was in a poor practice level. Female knowledge mean score was 9.53±4.96 and male knowledge mean score was 8.42±5.45, the practice mean score of males was 4.33±1.96 and mean practice score of females was 4.13±1.93. The study data indicate the worrying of participates about vision loss is in the highest proportion and the awareness and practice of patients about eye diseases is unsatisfactory. Health education campaigns are needed to improve personal awareness about vision related problems and for better eye health.

Creativity in Sociocultural Systems

2019 ◽  
pp. 269-284
Author(s):  
Dean Keith Simonton
Keyword(s):  
Macro Level ◽  
Historical Overview ◽  
Creative Activity ◽  
Cross Sectional ◽  
Individual Level ◽  
Short And Long Term ◽  
The Cross ◽  
Sociocultural Systems

Although psychologists typically see creativity as an individual-level event, sociologists and cultural anthropologists are more likely to view it as a sociocultural phenomenon. This phenomenon takes place at the level of relatively large and enduring collectives, such as cultures, nations, and even whole civilizations. This chapter reviews the extensive research on such macro-level creativity. The review begins with a historical overview before turning to the cross-sectional research on the creative Ortgeist, a subject that encompasses the factors that influence the relative creativity of both preliterate cultures and entire modern nations. From there the chapter turns to role of the Zeitgeist in affecting the creativity of civilizations across time—the rise and fall of creative activity. This research examines both quantitative and qualitative causes that operate both short- and long-term.

Tele-ophthalmology for screening for eye diseases in older patients with cognitive complaints

2020 ◽  
pp. 1357633X1989388
Author(s):  
Anne-Sophie Boureau ◽  
Helene Masse ◽  
Guillaume Chapelet ◽  
Laure de Decker ◽  
Pascal Chevalet ◽  
...  
Keyword(s):  
Cognitive Assessment ◽  
Older Patients ◽  
Screening Method ◽  
Poor Quality ◽  
Eye Diseases ◽  
Ophthalmological Examination ◽  
Cognitive Complaints ◽  
The Mean ◽  
To Come ◽  
Retinal Photographs

Introduction Population-based studies show a significant increase in the prevalence of visual impairment in older patients. However, older patients and patients with lower Mini-Mental State Examination (MMSE) scores have few ophthalmological assessments. The main objective of our study was to evaluate the feasibility of tele-ophthalmological screening for ophthalmological diseases in older patients referred for cognitive assessment. Methods This monocentric prospective study included patients referred to a memory clinic for cognitive assessment. All patients underwent a geriatric assessment comprising a cognitive assessment associated with tele-ophthalmological screening undertaken by an orthoptist, including undilated retinal photography. The retinal photographs were subsequently sent to an ophthalmologist. We identified patients who were not eligible for ophthalmological assessment, for patients that had to come back due to poor-quality retinal photographs and finally for detected eye diseases. The association between the geriatric variable and newly detected eye diseases was analysed in univariable and multivariable analyses. Results The mean age of the 298 patients included was 83.5 years  ± 5.65; 29.5% were male. The mean MMSE score was 20.8 ± 5.2; 66.3% of patients had a diagnosis of dementia. Eighteen patients (6.0%) were not eligible for ophthalmological examination and 13 patients (4.6%) were asked to come back owing to poor-quality retinal photographs. Forty-one patients (13.7%) had a newly detected eye disease. In multivariable analysis, patients with a lower MMSE had significantly more newly identified eye diseases. Discussion The tele-ophthalmological screening method identified unknown ophthalmological diseases requiring specialised management in this older population with cognitive complaints.

scholarly journals Cross-sectional observational study of epidemiology of COVID-19 and clinical outcomes of hospitalised patients in North West London during March and April 2020

BMJ Open ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. e044384
Author(s):  
Guduru Gopal Rao ◽  
Alexander Allen ◽  
Padmasayee Papineni ◽  
Liyang Wang ◽  
Charlotte Anderson ◽  
...  
Keyword(s):  
Mechanical Ventilation ◽  
Clinical Outcomes ◽  
Severe Infection ◽  
Older Age ◽  
Cross Sectional ◽  
North West ◽  
Icu Admission ◽  
Risk Of Death ◽  
Hospitalised Patients ◽  
Increased Risk

ObjectiveThe aim of this paper is to describe evolution, epidemiology and clinical outcomes of COVID-19 in subjects tested at or admitted to hospitals in North West London.DesignObservational cohort study.SettingLondon North West Healthcare NHS Trust (LNWH).ParticipantsPatients tested and/or admitted for COVID-19 at LNWH during March and April 2020Main outcome measuresDescriptive and analytical epidemiology of demographic and clinical outcomes (intensive care unit (ICU) admission, mechanical ventilation and mortality) of those who tested positive for COVID-19.ResultsThe outbreak began in the first week of March 2020 and reached a peak by the end of March and first week of April. In the study period, 6183 tests were performed in on 4981 people. Of the 2086 laboratory confirmed COVID-19 cases, 1901 were admitted to hospital. Older age group, men and those of black or Asian minority ethnic (BAME) group were predominantly affected (p<0.05). These groups also had more severe infection resulting in ICU admission and need for mechanical ventilation (p<0.05). However, in a multivariate analysis, only increasing age was independently associated with increased risk of death (p<0.05). Mortality rate was 26.9% in hospitalised patients.ConclusionThe findings confirm that men, BAME and older population were most commonly and severely affected groups. Only older age was independently associated with mortality.

scholarly journals Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ling-Ping Cen ◽  
Jie Ji ◽  
Jian-Wei Lin ◽  
Si-Tong Ju ◽  
Hong-Jie Lin ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Efficiency ◽  
Characteristic Curve ◽  
Weighted Average ◽  
Age Related Macular Degeneration ◽  
Learning Platform ◽  
Age Related ◽  
Public Data ◽  
Primary Test ◽  
Retinal Fundus

AbstractRetinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

Sign in / Sign up

Export Citation Format

Share Document