To assess risk factors for mortality in invasive pneumococcal disease (IPD). We conducted a systemic literature search to January 2019. The main outcome measure included death within 30 days after ...

Introduction: The most common causes of microcytic anemia are iron deficiency anemia (IDA) and thalassemia trait (TT). This study investigated the reliability of erythrocyte indices and formulas as screening tests in the differential diagnosis of IDA and TT before performing detailed tests for definitive diagnosis. Materials and Methods: In total, 50 children with β-TT, 31 with α-TT, 50 with IDA were included. For the 8 erythrocyte indices and formulas (red blood cells [RBC], red blood cell distribution width [RDW], red blood cell distribution width index [RDWI], Mentzer index [MI], Shine and Lal index [S&L], England and Fraser [E&F], Green and King index [G&K], Srivastava index) the sensitivity, specificity, positive and negative predictive values (PPVs and NPVs, respectively) were calculated according to the cutoff values in the literature and recalculated revised cutoff values. Results: According to the cutoff values in the literature for the differential diagnosis of IDA and TT, the ranking of sensitivity, specificity, PPVs, and NPVs from the highest to the lowest was RDWI, RBC, E&F, G&K, MI, Srivastava, RDW, S&L. The sensitivity, specificity, PPVs, and NPVs of all the indices according to the revised cutoff values were higher than those according to the cutoff values in the literature. Conclusions: According to both the cutoff values in the literature and revised cutoff values, the most reliable indices were RBC and RDWI.

Purpose: This study aimed to evaluate the classification performance of pretrained convolutional neural network models or architectures using fundus image dataset containing eight disease labels. Methods: A publicly available ocular disease intelligent recognition database has been used for the diagnosis of eight diseases. This ocular disease intelligent recognition database has a total of 10,000 fundus images from both eyes of 5,000 patients for the following eight diseases: healthy, diabetic retinopathy, glaucoma, cataract, age-related macular degeneration, hypertension, myopia, and others. Ocular disease classification performances were investigated by constructing three pretrained convolutional neural network architectures including VGG16, Inceptionv3, and ResNet50 models with adaptive moment optimizer. These models were implemented in Google Colab, which made the task straight-forward without spending hours installing the environment and supporting libraries. To evaluate the effectiveness of the models, the dataset was divided into 70%, 10%, and 20% for training, validation, and testing, respectively. For each classification, the training images were augmented to 10,000 fundus images. Results: ResNet50 achieved an accuracy of 97.1%; sensitivity, 78.5%; specificity, 98.5%; and precision, 79.7%, and had the best area under the curve and final score to classify cataract (area under the curve = 0.964, final score = 0.903). By contrast, VGG16 achieved an accuracy of 96.2%; sensitivity, 56.9%; specificity, 99.2%; precision, 84.1%; area under the curve, 0.949; and final score, 0.857. Conclusions: These results demonstrate the ability of the pretrained convolutional neural network architectures to identify ophthalmological diseases from fundus images. ResNet50 can be a good architecture to solve problems in disease detection and classification of glaucoma, cataract, hypertension, and myopia; Inceptionv3 for age-related macular degeneration, and other disease; and VGG16 for normal and diabetic retinopathy.

Objective: This research aims to examine the knowledge level and awareness of Faculty of Medicine students about medical artificial intelligence technologies. Methods: In this study involving students studying at Medical Faculties in Turkey, descriptive questionnaire, and the Medical Artificial Intelligence Readiness Scale for Medical Students (MAIRS-MS) were used. The suitability of continuous variables for normal distribution was tested with the Shapiro-Wilk test. Descriptive statistics for continuous variables are presented as mean and standard deviation or median (Q1-Q3). Descriptive statistics for categorical variables are reported as frequencies and percentages. Homogeneity of variances was evaluated with the Levene test. Mann Whitney U test was used to compare the scale subdimension and total scores according to two independent groups; One-way Analysis of Variance or Kruskal Wallis test was used to compare the scale subdimensions and total scores according to more than two independent groups. Dunn-Bonferroni test was used for multiple comparisons if there was a significant difference between the groups. The relationship between MAIRS-MS subdimensions and MAIRS-MS score was evaluated with the Spearman correlation coefficient. MAIRS-MS reliability was determined by Cronbach alpha value. The value of p