Attitudes and Behaviors with Diabetes Technology Use in the Hospital: Multicenter Survey Study in the United States.

Objective: To assess the attitudes, behaviors, and barriers with diabetes technology use in the general medicine hospital wards. Research Design and Methods: The authors developed a nonincentivized web-based anonymous survey that captured demographic and practice data regarding continuous subcutaneous insulin infusion (CSII) and continuous glucose monitor (CGM) use in the hospital. Setting: Four large hospital systems in the United States. Results: Among 128 survey respondents, 76%, 10%, and 6% were hospitalists, advanced practice providers, and primary care physicians, respectively. The majority of respondents rated the treatment of inpatient hyperglycemia (96%) and the continuation of CSII during the hospital stay (93%) "important." While most respondents (64%) acknowledged knowing the existence of their institution's policies for CSII use, only 84% of those respondents felt somewhat to very familiar with the policy. The most common barrier to CSII use in the inpatient setting was lack of practitioner (70%) and nursing (67%) knowledge of using the device. With regard to CGM use in the hospital, a minority (28%) of respondents were aware of their institution's CGM policies. Less than half of the providers, 43.8%, stated that, when admitting a patient, they reviewed CGM data to guide insulin dosing. Conclusions: In this US multicenter survey, we found that most inpatient practitioners valued glycemic control, but many were not familiar with institutional policies, had lack of knowledge with CSII, and were not reviewing CGM data.

Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging.

Anterior cruciate ligament (ACL) tear is caused by partially or completely torn ACL ligament in the knee, especially in sportsmen. There is a need to classify the ACL tear before it fully ruptures to avoid osteoarthritis. This research aims to identify ACL tears automatically and efficiently with a deep learning approach. A dataset was gathered, consisting of 917 knee magnetic resonance images (MRI) from Clinical Hospital Centre Rijeka, Croatia. The dataset we used consists of three classes: non-injured, partial tears, and fully ruptured knee MRI. The study compares and evaluates two variants of convolutional neural networks (CNN). We first tested the standard CNN model of five layers and then a customized CNN model of eleven layers. Eight different hyper-parameters were adjusted and tested on both variants. Our customized CNN model showed good results after a 25% random split using RMSprop and a learning rate of 0.001. The average evaluations are measured by accuracy, precision, sensitivity, specificity, and F1-score in the case of the standard CNN using the Adam optimizer with a learning rate of 0.001, i.e., 96.3%, 95%, 96%, 96.9%, and 95.6%, respectively. In the case of the customized CNN model, using the same evaluation measures, the model performed at 98.6%, 98%, 98%, 98.5%, and 98%, respectively, using an RMSprop optimizer with a learning rate of 0.001. Moreover, we also present our results on the receiver operating curve and area under the curve (ROC AUC). The customized CNN model with the Adam optimizer and a learning rate of 0.001 achieved 0.99 over three classes was highest among all. The model showed good results overall, and in the future, we can improve it to apply other CNN architectures to detect and segment other ligament parts like meniscus and cartilages.