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

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.

The effect of health education on Taiwanese hypertensive patients' knowledge and cognition of stroke.

BACKGROUND: Hypertension is a risk factor for stroke. Increasing patient knowledge and cognition about stroke among hypertensive patients is essential. AIMS: To explore the effect of a health education intervention on the knowledge and cognition of stroke in hypertensive patients. METHODS: A quasi-experimental design was used with 103 patients with hypertension. The sample was recruited from a cardiologist's outpatient office at a medical center in Kaohsiung city, southern Taiwan. Half the patients (experimental group, n = 52) received health education, whereas the others received only conventional general outpatient care (control group, n = 51). All patients underwent a pretest followed by posttests at 4 and 8 weeks after the intervention. A stroke knowledge scale and stroke cognition scale were used for data collection. RESULTS: The experimental group scored significantly higher than the control group in level of knowledge and cognition of stroke. DISCUSSION: This study supports that a health education CD-ROM and printed information provided in the outpatient clinical improves knowledge of and cognition of stroke among hypertensive patients. IMPLICATIONS FOR PRACTICE: In outpatient clinical practice, nurses can help improve patients' knowledge and cognition of the risks of stroke by playing the health education CD-ROM and providing printed information during the patients' wait time before appointments. CONCLUSIONS: Further studies with a longer follow-up (6 months or 1 year) are needed to evaluate the long-term effects of health education on stroke knowledge and cognition among patients with hypertension. LINKING EVIDENCE TO ACTION: An outpatient health education program using a CD-ROM and printed information for hypertensive patients can improve the patients' knowledge and cognition of stroke.

Bibliometric analysis of the top 100 most-cited articles on video laryngoscope from 2011 to 2022.

BACKGROUND: The popularity of video laryngoscope (VL) has increased rapidly since its introduction in the late 1990s. However, a comprehensive overview of VLs evolution and impact is lacking, which merits further investigation. METHODS: We conducted a bibliometric analysis of the top 100 most-cited articles on VL (Top100VL) published between 2011 and 2022 and retrieved from the PubMed and Web of Science databases. Using social network analysis, we identified the subject terms and subject categories of the Top100VL and compared their citation counts across individual subject terms and categories via one-way analysis of variance (ANOVA). Then, we employed the Medical Query Expert software to assess the practical applications of VL. RESULTS: The Top100VL included 65 subjects across nine subject categories, with "anesthesiology" being the most frequently represented category and "coronavirus infections" with the highest impact factor. The citation counts inferred by subject categories significantly correlated with the actual citation counts (Pearson's R = 0.4; p < 0.01). For enhanced visualization, we employed network visualization and Sankey diagrams to display the article characteristics. We highlighted the clinical advantages of VL, including its usefulness in difficult intubations, wider angle of view, and management of pediatric emergencies, as well as its teaching benefits, such as facilitating training programs and a lower learning curve. CONCLUSION: By using bibliometric analysis and natural language processing methods, we effectively summarized the applications of VL in both clinical and teaching settings, particularly in reducing the risk of cross-infection during the Coronavirus Disease 2019 pandemic.