The most effective of the solutions against Covid-19 is the various vaccines developed. Distrust of vaccines can hinder the rapid and effective use of this remedy. One of the means of expressing the thoughts of society is social media. Determining the time intervals during which anti-vaccination increases in social media can help institutions determine the strategy to be used in combating anti-vaccination. Recording and tracking every tweet entered with human labor would be inefficient, so various automation solutions are needed. In this study, The Bidirectional Encoder Representations from Transformers (BERT) model, which is a deep learning-based natural language processing (NLP) model, was used. In a dataset of 1506 tweets divided into four different categories as news, irrelevant, anti-vaccine, and vaccine supporters, the model was trained with a learning rate of 5e-6 for 25 epochs. To determine the intervals in which anti-vaccine tweets are concentrated, the categories to which 652840 tweets belong were determined by using the trained model. The change of the determined categories overtime was visualized and the events that could cause the change were determined. As a result of model training, in the test dataset, the f-score of 0.81 and AUC values for different classes were obtained as 0.99,0.91, 0.92, 0.92, respectively. In this model, unlike the studies in the literature, an auxiliary system is designed that provides data that institutions can use when determining their strategy by measuring and visualizing the frequency of anti-vaccine tweets in a time interval, different from detecting and censoring such tweets.
Wrist fractures are common cases in hospitals, particularly in emergency services. Physicians need images from various medical devices, and patients medical history and physical examination to diagnose these fractures correctly and apply proper treatment. This study aims to perform fracture detection using deep learning on wrist Xray images to assist physicians not specialized in the field, working in emergency services in particular, in diagnosis of fractures. For this purpose, 20 different detection procedures were performed using deep learning based object detection models on dataset of wrist Xray images obtained from Gazi University Hospital. DCN, Dynamic R_CNN, Faster R_CNN, FSAF, Libra R_CNN, PAA, RetinaNet, RegNet and SABL deep learning based object detection models with various backbones were used herein. To further improve detection procedures in the study, 5 different ensemble models were developed, which were later used to reform an ensemble model to develop a detection model unique to our study, titled wrist fracture detection combo (WFD_C). Based on detection of 26 different fractures in total, the highest result of detection was 0.8639 average precision (AP50) in WFD_C model developed. This study is supported by Huawei Turkey R&D Center within the scope of the ongoing cooperation project coded 071813 among Gazi University, Huawei and Medskor.
Fractures occur in the shoulder area, which has a wider range of motion than other joints in the body, due to various reasons. To diagnose these fractures the data gathered from X-radiation (X-ray), magnetic resonance imaging (MRI) or computed tomography (CT) are used. In this study, it is aimed to help physicians by classifying the shoulder images taken from X-Ray devices as fracture / non-fracture with artificial intelligence. For this purpose, the performances of 26 deep learning-based pretrained models in the detection of shoulder fractures were evaluated on the musculoskeletal radiographs (MURA) dataset, and 2 ensemble learning models (EL1, EL2) were developed. The pretrained models used are ResNet, ResNeXt, DenseNet, VGG, Inception, MobileNet and their versions with Spinal fully connected (Spinal FC). In EL1 and EL2 models developed using pretrained models with the highest test performance, test accuracy was 0.8455,0.8472; Cohens cappa 0.6907,0.6942; the area under the receiver operating characteristic (ROC) curve (AUC) 0.8862,0.8695 values were obtained for the fracture class. As a result of 28 different classifications in total, the highest test accuracy and Cohen cappa value were obtained in the EL2 model, and the highest AUC value was obtained in the EL1 model.