Multiple studies presented satisfactory performances for the treatment of various ocular diseases. To date, there has been no study that describes a multiclass model, medically accurate, and trained on large diverse dataset. No study has addressed a class imbalance problem in one giant dataset originating from multiple large diverse eye fundus image collections. To ensure a real-life clinical environment and mitigate the problem of biased medical image data, 22 publicly available datasets were merged. To secure medical validity only Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD) and Glaucoma (GL) were included. The state-of-the-art models ConvNext, RegNet and ResNet were utilized. In the resulting dataset, there were 86,415 normal, 3787 GL, 632 AMD and 34,379 DR fundus images. ConvNextTiny achieved the best results in terms of recognizing most of the examined eye diseases with the most metrics. The overall accuracy was 80.46 ± 1.48. Specific accuracy values were: 80.01 ± 1.10 for normal eye fundus, 97.20 ± 0.66 for GL, 98.14 ± 0.31 for AMD, 80.66 ± 1.27 for DR. A suitable screening model for the most prevalent retinal diseases in ageing societies was designed. The model was developed on a diverse, combined large dataset which made the obtained results less biased and more generalizable.

Patients often search on the Internet information about different medical conditions and procedures. This study aimed to evaluate online health information on colonoscopy, focusing on quantity and comprehensibility of internet resources dedicated to the colonoscopy. This information could be used by European Union (EU) colorectal cancer (CRC) screening providers to address patient’s unfilled educational needs, fear of colonoscopy, and other barriers that deter from CRC screening. The term “colonoscopy” translated into 22 official EU languages was searched using the Google search engine. For each translation, generated list of websites was assessed with Google Translate. The first 50 websites in each language were assessed for suitability. Records in other languages were excluded. Included websites were free, focused on patient education, and did not have password. Readability assessments were performed with Lix score. A total of 588 websites in Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, and Swedish were evaluated. The overall mean Lix score was 56 ± 8 and was classified as very hard to comprehend. There were significant differences in mean Lix scores across the included languages (P<.001). There was not significant correlation (R² = 0.1, P = 0.142) between Lix score and number of search hits. Although there was a wealth of online patient information on colonoscopy, the comprehensibility of the available information is low. Physician guidance to reliable resources could increase patient’s willingness to undergo a screening colonoscopy.

Introduction: The process of scientific publishing changed greatly in the past decades. The authors aimed to get insight into the time required for articles to be accepted and released online in high-impacted ophthalmology journals. Methods: Comprehensive review of all original articles published by eight ophthalmology journals during a one-year period was performed for 2020 and 2005. Time taken from submission to acceptance and the first online release of the article was abstracted and analyzed. Results: A total of 3110 articles were reviewed. In 2020, the overall median time from submission to acceptance (AT) was 119 days (IQR 83-168) and 30 days (10-71) from acceptance to the first online release of the article (OP). AT increased by 7.3% from 2005 to 2020, whereas OP reduced by 73%. Publications, which the corresponding author was affiliated with US-located institution had shorter both AT and OP in 2005 and 2020. The author’s specialty in ophthalmology had an inconclusive impact on AT and OP. Papers with multiple affiliated institutions had shorter AT and OP in both 2005 and 2020; however, these differences were not statistically significant. Conclusion: This study demonstrated that increasing pressure on authors, editors, and reviewers to publish articles and journals with high impact factor (IF) significantly influenced publication times in ophthalmology journals. Inflation of research papers was associated with rising AT time. A significant decrease in OP time was potentially explained by the editor’s demand to achieve decent journal IF. This article brings to light relative publication times in the ophthalmology scientific journals.

Introduction Patients search on the Internet for information about various medical procedures and conditions. The main aim of this study was to evaluate the readability of online health information related to atopic dermatitis (AD). Online resources are becoming a standard in facilitating shared decision-making processes. With a pipeline of new therapeutic options like immunomodulators, understanding of the complexity of AD by the patients is crucial. Methods The term “atopic dermatitis” translated into 23 official European Union languages was searched using the Google search engine. The first 50 records in each language were evaluated for suitability. Included materials were barrier-free, focused on patient education, and were not categorized as advertisements. Article sources were classified into four categories: non-profit, online shops, pharmaceutical companies, and dermatology clinic. Readability was assessed with Lix score. Results A total of 615 articles in Swedish, Spanish, Slovenian, Slovak, Romanian, Portuguese, Polish, Lithuanian, Latvian, Irish, Italian, Hungarian, Greek, German, French, Finnish, Estonian, English, Dutch, Danish, Czech, Croatian, and Bulgarian were evaluated. The overall mean Lix score was 56 ± 8, which classified articles as very hard to comprehend. Significant differences in mean Lix scores were observed across all included languages (all P < 0.001). Articles released by non-profit organizations and pharmaceutical companies had the highest readability (P < 0.001). Low readability level was correlated with high article prevalence (R² = 0.189, P = 0.031). Conclusions Although there was an abundance of online articles related to AD, the readability of the available information was low. As online health information has become essential in making shared decisions between patients and physicians, an improvement in AD-related materials is needed.

Cataract surgery is the most common surgery performed in the European Union (EU) annually. Analysis of Google Trends (GT) data could give European eye care providers useful information regarding in...

The impact of social media on the eagerness to undergo aesthetic breast surgery is unknown. We aimed to evaluate the association between Instagram engagement and the willingness to undergo breast augmentation. Women aged between 19–34 years old participated in an online survey. Of the 1560 respondents, 1226 (78.59%) met the inclusion criteria. BMI, bra type, bra cup size, education, and level of activity on Instagram increased the willingness to undergo breast augmentation (OR = 1.520, p = 0.020). Moreover, concurrent Snapchat use (OR = 1.348, p = 0.024) and the number of published posts on a respondent’s Instagram accounts (reference, n > 26; 0 < n ≤ 26; OR = 0.708, p = 0.009; lack of posts (n = 0): OR = 0.702, p = 0.155) were significant drivers of the respondents’ willingness. Fashion (OR = 0.730, p = 0.021), design/architecture (OR = 0.730, p = 0.022), and models (OR = 0.623, p = 0.004) were the searched content categories that increased the desire for breast augmentation. Positive and negative feeling scores that were triggered by Instagram content were correlated with BREAST-Q scores. We concluded that Instagram is a commonly used social network service among young women, and it may drive a desire for breast augmentation. Further analyses of Instagram preferences may help assess the willingness to undergo breast surgery, and in turn assist in tailoring marketing campaigns.