Predictive models for chronic renal disease using decision trees, naïve bayes and case-based methods

Data mining can be used in healthcare industry to “mine” clinical data to discover hidden information for intelligent and affective decision making. Discovery of hidden patterns and relationships often goes intact, yet advanced data mining techniques can be helpful as remedy to this scenario. This thesis mainly deals with Intelligent Prediction of Chronic Renal Disease (IPCRD). Data covers blood, urine test, and external symptoms applied to predict chronic renal disease. Data from the database is initially transformed to Weka (3.6) and Chi-Square method is used for features section. After normalizing data, three classifiers were applied and efficiency of output is evaluated. Mainly, three classifiers are analyzed: Decision Tree, Naïve Bayes, K-Nearest Neighbour algorithm. Results show that each technique has its unique strength in realizing the objectives of the defined mining goals. Efficiency of Decision Tree and KNN was almost same but Naïve Bayes proved a comparative edge over others. Further sensitivity and specificity tests are used as statistical measures to examine the performance of a binary classification. Sensitivity (also called recall rate in some fields) measures the proportion of actual positives which are correctly identified while Specificity measures the proportion of negatives which are correctly identified. CRISP-DM methodology is applied to build the mining models. It consists of six major phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment.

Urinary osteopontin predicts incident chronic kidney disease, while plasma osteopontin predicts cardiovascular death in elderly men

Background and objectives The matricellular protein osteopontin is involved in the pathogenesis of both kidney and cardiovascular disease. However, whether circulating and urinary osteopontin levels are associated with the risk of these diseases is less studied. Design, setting, participants and measurements A community-based cohort of elderly (Uppsala Longitudinal Study of Adult Men [ULSAM; n=741; mean age: 77 years]) was used to study the associations between plasma and urinary osteopontin, incident chronic kidney disease, and the risk of cardiovascular death during a median of 8 years of follow-up. Results There was no significant cross-sectional correlation between plasma and urinary osteopontin (Spearman rho=0.07, p=0.13). Higher urinary, but not plasma osteopontin, was associated with incident chronic kidney disease in multivariable models adjusted for age, cardiovascular risk factors, baseline glomerular filtration rate (GFR), urinary albumin/creatinine ratio, and inflammatory markers interleukin 6 and high sensitivity C-reactive protein (Odds ratio for 1-standard deviation (SD) of urinary osteopontin, 1.42, 95% CI (1.00-2.02), p=0.048). Conversely, plasma osteopontin, but not urinary osteopontin, was independently associated with cardiovascular death (multivariable hazard ratio per SD increase, 1.35, 95% CI (1.14-1.58), p<0.001, and 1.00, 95% CI (0.79-1.26), p=0.99, respectively). The addition of plasma osteopontin to a model with established cardiovascular risk factors significantly increased the C-statistics for the prediction of cardiovascular death (p<0.002). Conclusions Higher urinary osteopontin specifically predicts incident chronic kidney disease while plasma osteopontin specifically predicts cardiovascular death. Our data put forward osteopontin as an important factor in the detrimental interplay between the kidney and the cardiovascular system. The clinical implications, and why plasma and urinary osteopontin mirror different pathologies, remains to be established.