Diagnosis of urinary tract infection based on artificial intelligence methods.

BACKGROUND AND OBJECTIVE: Urinary tract infection (UTI) is a common disease affecting the vast majority of people. UTI involves a simple infection caused by urinary tract inflammation as well as a complicated infection that may be caused by an inflammation of other urinary tract organs. Since all of these infections have similar symptoms, it is difficult to identify the cause of primary infection. Therefore, it is not easy to diagnose a UTI with routine examination procedures. Invasive methods that require surgery could be necessary. This study aims to develop an artificial intelligence model to support the diagnosis of UTI with complex symptoms. METHODS: Firstly, routine examination data and definitive diagnosis results for 59 UTI patients gathered and composed as a UTI dataset. Three classification models namely; decision tree (DT), support vector machine (SVM), random forest (RF) and artificial neural network (ANN), which are widely used in medical diagnosis systems, were created to model the definitive diagnosis results using the composed UTI dataset. Accuracy, specificity and sensitivity statistical measurements were used to determine the performance of created models. RESULTS: DT, SVM, RF and ANN models have 93.22%, 96.61%, 96.61%, 98.30% accuracy, 95.55%, 97.77%, 95.55%, 97.77% sensitivity and 85.71%, 92.85%, 100%, 100% specificy results, respectively. CONCLUSIONS: ANN has the highest accuracy result of 98.3% for UTI diagnosis within the proposed models. Although several symptoms, laboratory findings, and ultrasound results are needed for clinical UTI diagnosis, this ANN model only needs pollacuria, suprapubic pain symptoms and erythrocyte to get the same diagnosis with such accuracy. This proposed model is a successful medical decision support system for UTI with complex symptoms. Usage of this artificial intelligence method has its advantages of lower diagnosis cost, lower diagnosis time and there is no need for invasive methods.

The role of vitamin E in the prevention of zoledronic acid-induced nephrotoxicity in rats: a light and electron microscopy study.

INTRODUCTION: Bisphosphonates are widely used in metastatic cancer such as prostate and breast cancer, and their nephrotoxic effects have been established previously. In this study we aimed to evaluate both the nephrotoxic effects of zoledronic acid (ZA) and the protective effects of vitamin E (Vit-E) on this process under light and electron microscopy. MATERIAL AND METHODS: A total of 30 male Sprague-Dawley rats were divided into 3 groups. The first group constituted the control group. The second group was given i.v. ZA of 3 mg/kg once every 3 weeks for 12 weeks from the tail vein. The third group received the same dosage of ZA with an additional i.m. injection of 15 mg Vit-E every week for 12 weeks. Tissues were taken 4 days after the last dose of ZA for histopathological and ultrastructural evaluation. Paller score, tubular epithelial thickness and basal membrane thickness were calculated for each group. RESULTS: For group 2, the p-values are all < 0.001 for Paller score, epitelial thickness, and basal membrane thickness. For group 3 (ZA + Vit. E), the p-values are < 0.001 for Paller score, 0.996 for epitelial thickness, and < 0.001 basal membrane thickness. Significant differences were also observed in ultrastructural changes for group 2. However, adding Vit-E to ZA administration reversed all the histopathological changes to some degree, with statistical significance. CONCLUSIONS: Administration of ZA had nephrotoxic effects on rat kidney observed under both light and electron microscopy. Concomitant administration of Vit-E significantly reduces toxic histopathological effects of ZA.

Preliminary feasibility study of a new method of hypothermia in an experimental canine model.

OBJECTIVE: To build up a new microcontroller thermoelectric system to achieve renal hypothermia. MATERIAL AND METHODS: Renal hypothermia system was tested under in vivo conditions in the kidneys of ten Mongrel dogs. Ambient temperature was evaluated using two different microcontrollers. In order to ensure hypothermia in the renal parenchyma, selection can be made among 4 modules and sensors which detect the temperature of the area. The temperature range of the system was adjusted between -50°C and +50°C. RESULTS: When single and double poles of the kidney were cooled, initial mean intraperitoneal temperature values were found 37.7°C for rectum and 36.5°C for renal cortex and medulla. After the temperature of the cooling module was set to 12°C, the module was placed on the poles of the kidney. After fifteen minutes, temperature was 15.4°C in the lower pole of the kidney, 28.1°C in the cortex of the other side and 29.2°C in the intramedullary region. The temperature was found to be 15°C in the vicinity and 26.1°C in the cortex across the module. After the system was stabilized, a very slight change was observed in the temperature. CONCLUSION: Hypothermia system developed ensured desired cooling of the targeted part of the kidney; however, it did not cause a change in the temperature of other parts of the kidney or general body temperature. Thus, it was possible to create a long-term study area for renal parenchymal surgery.