Diagnosis of Chronic Kidney Disease Based on Support Vector Machine by Feature Selection Methods.

As Chronic Kidney Disease progresses slowly, early detection and effective treatment are the only cure to reduce the mortality rate. Machine learning techniques are gaining significance in medical diagnosis because of their classification ability with high accuracy rates. The accuracy of classification algorithms depend on the use of correct feature selection algorithms to reduce the dimension of datasets. In this study, Support Vector Machine classification algorithm was used to diagnose Chronic Kidney Disease. To diagnose the Chronic Kidney Disease, two essential types of feature selection methods namely, wrapper and filter approaches were chosen to reduce the dimension of Chronic Kidney Disease dataset. In wrapper approach, classifier subset evaluator with greedy stepwise search engine and wrapper subset evaluator with the Best First search engine were used. In filter approach, correlation feature selection subset evaluator with greedy stepwise search engine and filtered subset evaluator with the Best First search engine were used. The results showed that the Support Vector Machine classifier by using filtered subset evaluator with the Best First search engine feature selection method has higher accuracy rate (98.5%) in the diagnosis of Chronic Kidney Disease compared to other selected methods.

[Sensitivity of cough with capsaicin in smokers]. / Sigara içenlerde kapsaisin ile öksürük duyarliligi.

In this study, effect of long term smoking on sensitivity of cough reflex was investigated. Healthy, current smoker male and female was evaluated by capsaicin cough challenge test and they were compared with healthy, non-smoker persons with similar age and gender, prospectively. In current smokers, there were 50 male and 39 female, in non-smoker control group, there were 20 male and 21 female. Mean and log C5 dosage in current smoker and non-smoker groups and mean and log C5 dosage in current smoker according to gender were calculated by using Mann-Whitney U-test. Results of capsaicin cough challenge test in current and non-smoker groups were evaluated by using Pearson Chi-Square test and Fisher's Exact test. In current smokers comparison of results of capsaicin cough challenge test with smoking history (age with first smoking, duration, pocket year and smoking per day) was evaluated by using Mann-Whitney U-test. Mean C5 and mean log C5 dosage were found decreased in current smokers when they were compared to control group (p< 0.00). In current smoker group mean C5 and mean log C5 dosage were found decreased in male (p< 0.002). When the results of capsaicin cough challenge test were compared between current smoker and control groups, sensitivity of cough reflex in concentration with 0.49, 0.98, 1.95, 3.9, 7.8, 15.6 microM was significantly decreased in current smoker group. Also there was a significant correlation between concentration with 0.98, 1.95, 3.9, 7.8, 15.6, 31.2 microM, and duration of smoking and pocket year of smoking. Also there was a correlation between concentration with 15.6, 31.2, 62.5, 125 microM and smoking per day. This results were correlated with hypothesis about inhibition of C-fibers with nicotin or decrease of C-fibers' sensitivity due to induction of neuropeptide wasting.

[Evaluation of silicosis in ceramic workers]. / Seramik fabrikasi isçilerinde silikozis.

This study is aimed to evaluate the incidence of silicosis and the relation of it with personal and work-related factors among workers exposed to silica in ceramic factory. Workers were evaluated by respiratory symptoms, physical examination, pulmonary function and radiological findings. Occupational and Enviromental Pulmonary Disease Evaluation Questionnaire of the Turkish Thoracic Society Enviromental and Occupational Pulmonary Diseases Working Group was used. 365 of 626 workers had exposure to silica and the rest 261 were concerned as control group. There was no difference between mean age, duration of work and smoking pack year among the groups (p> 0.05). Cough and sputum rates were higher in silicosis group FEV1 and FVC values were lower in silica group but this was not statistically significant. When the two subgroups of silica group (the workers in high dust concentration and the ones in low concentration) were compared, the high concentrated group had significantly more sputum but the other symptoms and pulmonary functional parameters were not different significantly. 24 workers had parenchymal densities adjusted with pneumoconiosis. The workers with the pneumoconistic finding, had a higher mean age and longer duration of work. As a conclusion, ceramic industry has risk for silicosis. And the risk increase by time and age.

3D web based learning of medical equipment employed in intensive care units.

In this paper, both synchronous and asynchronous web based learning of 3D medical equipment models used in hospital intensive care unit have been described over the moodle course management system. 3D medical equipment models were designed with 3ds Max 2008, then converted to ASE format and added interactivity displayed with Viewpoint-Enliven. 3D models embedded in a web page in html format with dynamic interactivity-rotating, panning and zooming by dragging a mouse over images-and descriptive information is embedded to 3D model by using xml format. A pilot test course having 15 h was applied to technicians who is responsible for intensive care unit at Medical Devices Repairing and Maintenance Center (TABOM) of Turkish High Specialized Hospital.