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.

Effects of chronic renal disease on the transport of vitamin A in plasma and urine of dogs

OBJECTIVE To determine plasma and urine concentrations of retinol, retinyl esters, retinol-binding protein (RBP), and Tamm-Horsfall protein (THP) in dogs with chronic renal disease (CRD). ANIMALS 17 dogs with naturally developing CRD and 21 healthy control dogs. PROCEDURE A diagnosis of CRD was established on the basis of clinical signs, plasma concentrations of creatinine and urea, and results of urinalysis. Concentrations of retinol and retinyl esters were measured by use of reverse-phase high-performance liquid chromatography. Concentrations of RBP and THP were measured by use of sensitive ELISA systems. RESULTS Dogs with CRD had higher plasma concentrations of retinol, which were not paralleled by differences in plasma concentrations of RBP. Calculated ratio of urinary total vitamin A (sum of concentrations of retinol and retinyl esters to creatinine concentration) and ratio of the concentration of urinary retinyl esters to creatinine concentration did not differ between groups. However, we detected a significantly higher retinol-to-creatinine ratio in the urine of dogs with CRD, which was paralleled by a higher urinary RBP-to-creatinine ratio. Thus, in dogs with CRD, the estimated fractional clearance of total vitamin A, retinol, and RBP was increased. Furthermore, dogs with CRD had a reduced urinary THP-to-creatinine ratio. CONCLUSIONS AND CLINICAL RELEVANCE Results of this study documented that CRD affects the concentrations of retinol in plasma and urine of dogs. Analysis of the data indicates that measurement of urinary RBP and urinary THP concentrations provides valuable information that can be helpful in follow-up monitoring of dogs with CRD.

Chronic renal failure in an English bull terrier with polycystic kidney disease

An entire female English bull terrier, aged five years and one month, was diagnosed with polycystic kidney disease by renal ultrasonography. It had thickening and abnormal motion of the mitral valve on 2D and M mode echocardiography, and left ventricular outflow tract obstruction, characterised by turbulence in the left ventricular outflow tract and elevated aortic blood flow velocity, detected by colour flow and spectral Doppler echocardiography, respectively. Two years later, haematology, serum biochemistry and urinalysis data suggested the presence of compensated renal failure. The dog was euthanased at 10 years and eight months of age, with haematology, serum biochemistry and urinalysis data indicating decompensated chronic renal failure. Postmortem examination confirmed polycystic kidney disease, chronic renal disease, mitral and aortic valvular myxomatous degeneration, and mixed mammary neoplasia. This case demonstrates that bull terriers with polycystic kidney disease may develop associated chronic renal failure.

An Appraisal of End-of-Life Care in Persons with Chronic Kidney Disease Dying in Hospital Wards

AIM: To review end-of-life care provided by renal healthcare professionals to hospital in-patients with chronic kidney disease, and their carers, over a 12-month period in Northern Ireland.

METHODS: Retrospective review of 100 patients.

RESULTS: Mean age at death was 72 years (19-95) and 56% were male. Eighty three percent of patients had a 'Not For Attempted Resuscitation' order during their last admission and this was implemented in 42%. Less than 20% of all patients died in a hospital ward. No patients had an advanced care plan, although 42% had commenced the Liverpool Care Pathway for the Dying Patient. Patients suffered excessive end-of-life symptoms. In addition, there was limited documentation of carer involvement and carer needs were not formally assessed.

CONCLUSION: End-of-life care for patients with advanced chronic renal disease can be enhanced. There is significant variation in the recording of discussions regarding impending death and little preparation. There is poor recording of the patients' wishes regarding death. Those with declining functional status, including those frequently admitted to hospital require holistic assessment regarding end-of-life needs. More effective communication between the patient, family and multi-professional team is required for patients who are dying and those caring for them.

Increased tubulointerstitial recruitment of human CD141(hi) CLEC9A(+) and CD1c(+) myeloid dendritic cell subsets in renal fibrosis and chronic kidney disease

Dendritic cells (DCs) play critical roles in immune-mediated kidney diseases. Little is known, however, about DC subsets in human chronic kidney disease, with previous studies restricted to a limited set of pathologies and to using immunohistochemical methods. In this study, we developed novel protocols for extracting renal DC subsets from diseased human kidneys and identified, enumerated, and phenotyped them by multicolor flow cytometry. We detected significantly greater numbers of total DCs as well as CD141(hi) and CD1c(+) myeloid DC (mDCs) subsets in diseased biopsies with interstitial fibrosis than diseased biopsies without fibrosis or healthy kidney tissue. In contrast, plasmacytoid DC numbers were significantly higher in the fibrotic group compared with healthy tissue only. Numbers of all DC subsets correlated with loss of kidney function, recorded as estimated glomerular filtration rate. CD141(hi) DCs expressed C-type lectin domain family 9 member A (CLEC9A), whereas the majority of CD1c(+) DCs lacked the expression of CD1a and DC-specific ICAM-3-grabbing nonintegrin (DC-SIGN), suggesting these mDC subsets may be circulating CD141(hi) and CD1c(+) blood DCs infiltrating kidney tissue. Our analysis revealed CLEC9A(+) and CD1c(+) cells were restricted to the tubulointerstitium. Notably, DC expression of the costimulatory and maturation molecule CD86 was significantly increased in both diseased cohorts compared with healthy tissue. Transforming growth factor-β levels in dissociated tissue supernatants were significantly elevated in diseased biopsies with fibrosis compared with nonfibrotic biopsies, with mDCs identified as a major source of this profibrotic cytokine. Collectively, our data indicate that activated mDC subsets, likely recruited into the tubulointerstitium, are positioned to play a role in the development of fibrosis and, thus, progression to chronic kidney disease.

Apparent treatment-resistant hypertension and chronic kidney disease: another cardiovascular-renal syndrome?

To identify patients at increased risk of cardiovascular (CV) outcomes, apparent treatment-resistant hypertension (aTRH) is defined as having a blood pressure above goal despite the use of 3 or more antihypertensive therapies of different classes at maximally tolerated doses, ideally including a diuretic. Recent epidemiologic studies in selected populations estimated the prevalence of aTRH as 10% to 15% among patients with hypertension and that aTRH is associated with elevated risk of CV and renal outcomes. Additionally, aTRH and CKD are associated. Although the pathogenesis of aTRH is multifactorial, the kidney is believed to play a significant role. Increased volume expansion, aldosterone concentration, mineralocorticoid receptor activity, arterial stiffness, and sympathetic nervous system activity are central to the pathogenesis of aTRH and are targets of therapies. Although diuretics form the basis of therapy in aTRH, pathophysiologic and clinical data suggest an important role for aldosterone antagonism. Interventional techniques, such as renal denervation and carotid baroreceptor activation, modulate the sympathetic nervous system and are currently in phase III trials for the treatment of aTRH. These technologies are as yet unproven and have not been investigated in relationship to CV outcomes or in patients with CKD.

The effects of lowering LDL cholesterol with simvastatin plus ezetimibe in patients with chronic kidney disease (Study of Heart and Renal Protection):a randomised placebo-controlled trial

Lowering LDL cholesterol with statin regimens reduces the risk of myocardial infarction, ischaemic stroke, and the need for coronary revascularisation in people without kidney disease, but its effects in people with moderate-to-severe kidney disease are uncertain. The SHARP trial aimed to assess the efficacy and safety of the combination of simvastatin plus ezetimibe in such patients.

Periodontal disease characterization in dogs with normal renal function or chronic renal failure

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Ultrasound analysis of a canine patient with renal disease and chronic liver disease undergoing treatment with intravenous stem cells

With the improvement in quality of life of animals, it is increasingly frequent clinical care of elderly patients, which present renal disorders, including chronic renal failure. Recent studies report the use of stem cells to treat renal failure, which would improve the levels of urea and creatinine, and in renal ultrasound evaluation. With the present work, the idea is to report a case of ultrasonographic evaluation in a patient with chronic renal failure, liver disease and splenic nodule, which underwent stem cell therapy, where there was an improvement in the sonographic evaluation of part of the liver.

Frequency and clinical predictors of coronary artery disease in chronic renal failure renal transplant candidates

Background/aims: Cardiovascular diseases are major causes of mortality in chronic renal failure patients before and after renal transplantation. Among them, coronary disease presents a particular risk; however, risk predictors have been used to diagnose coronary heart disease. This study evaluated the frequency and importance of clinical predictors of coronary artery disease in chronic renal failure patients undergoing dialysis who were renal transplant candidates, and assessed a previously developed scoring system. Methods: Coronary angiographies conducted between March 2008 and April 2013 from 99 candidates for renal transplantation from two transplant centers in Sao Paulo state were analyzed for associations between significant coronary artery diseases (>= 70% stenosis in one or more epicardial coronary arteries or >= 50% in the left main coronary artery) and clinical parameters. Results: Univariate logistic regression analysis identified diabetes, angina, and/or previous infarction, clinical peripheral arterial disease and dyslipidemia as predictors of coronary artery disease. Multiple logistic regression analysis identified only diabetes and angina and/or previous infarction as independent predictors. Conclusion: The results corroborate previous studies demonstrating the importance of these factors when selecting patients for coronary angiography in clinical pretransplant evaluation.

Analysis of the association of an MMP1 promoter polymorphism and transcript levels with chronic periodontitis and end-stage renal disease in a Brazilian population

Chronic periodontitis (CP) and end-stage renal disease (ESRD) are complex inflammatory conditions. Higher levels of MMP-1 were found in fluids and gingival tissues from CP patients and in the blood and tissues from ESRD patients. MMP1-1607 (1G/2G) is a functional polymorphism, as it alters MMP-1 expression. Objective: The aim of this study was to investigate the association of the MMP1-1607 (1G/2G) polymorphism with CP and ESRD and evaluate differences in transcript levels between the groups. Design: A total of 254 individuals were divided into four groups: Group 1, without CP and without chronic kidney disease (CKD) (n = 67); Group 2, with CP and without CKD (n = 60); Group 3, without CP and with CKD stages (ESRD) (n = 52), and Group 4, with CP and with ESRD (n = 75). The MMP1-1607 polymorphism was analysed by PCR-RFLP. MMP1 gene transcripts from gingival tissues were analysed by real-time PCR. Results: No association was found between the MMP1-1607 polymorphism and CP or ESRD. Increased levels of MMP1 transcripts were observed in CP patients with or without ESRD. No differences were observed in the transcript levels according to the genotypes. Conclusion: It was concluded that the MMP1-1607 polymorphism was not associated with either CP or ESRD. However, higher levels of MMP1 gene transcripts were found at gingival sites of CP in patients both with and without ESRD. (C) 2012 Elsevier Ltd. All rights reserved.

The role of myocardial scintigraphy in the assessment of cardiovascular risk in patients with end-stage chronic kidney disease on the waiting list for renal transplantation

The usefulness of stress myocardial perfusion scintigraphy for cardiovascular (CV) risk stratification in chronic kidney disease remains controversial. We tested the hypothesis that different clinical risk profiles influence the test. We assessed the prognostic value of myocardial scintigraphy in 892 consecutive renal transplant candidates classified into four risk groups: very high (aged epsilon 50 years, diabetes and CV disease), high (two factors), intermediate (one factor) and low (no factor). The incidence of CV events and death was 20 and 18, respectively (median follow-up 22 months). Altered stress testing was associated with an increased probability of cardiovascular events only in intermediate-risk (one risk factor) patients [30.3 versus 10, hazard ratio (HR) 2.37, confidence interval (CI) 1.693.33, P 0.0001]. Low-risk patients did well regardless of scan results. In patients with two or three risk factors, an altered stress test did not add to the already increased CV risk. Myocardial scintigraphy was related to overall mortality only in intermediate-risk patients (HR 2.8, CI 1.55.1, P 0.007). CV risk stratification based on myocardial stress testing is useful only in patients with just one risk factor. Screening may avoid unnecessary testing in 60 of patients, help stratifying for risk of events and provide an explanation for the inconsistent performance of myocardial scintigraphy.

Can we predict which patients will evolve to chronic kidney disease after nephrectomy for cortical renal tumors?

Introduction: While some studies show that patients submitted to radical nephrectomy have a higher risk of developing chronic kidney disease (CKD), some studies report that carefully selected living kidney donors do not present a higher risk for CKD. Here, we aim to study predictive factors of CKD after radical nephrectomy. Materials and Methods: Between January 2006 to January 2010, 107 patients submitted to radical nephrectomy for cortical renal tumors at our institution were enrolled in this study. Demographic data were recorded, modified Charlson-Romano Index was calculated, and creatinine clearance was estimated using abbreviated Modification of Diet in Renal Disease (MDRD) study equation. Pathological characteristics, surgical access and surgical complications were also reviewed. The end-point of the current study was new onset estimated glomerular filtration rate (eGFR) less than 60 and less than 45 mL/minute/1.73 m(2). Results: Age, preoperative eGFR, Charlson-Romano Index and hypertension were predictive factors of renal function loss, when the end-point considered was eGFR lower than 60 mL/minute/1.73 m(2). Age and preoperative eGFR were predictive factors of renal function loss, when the end-point considered was eGFR lower than 45 mL/minute/1.73 m2. Moreover, each year older increased 1.1 times the risk of eGFR lower than 60 and 45 mL/minute/1.73 m(2). After multivariate logistic regression, only age remained as an independent predictive factor of eGFR loss. Conclusion: Age is an independent predictive factor of GFR loss for patients submitted to radical nephrectomy for cortical renal tumors.

Circulating Fibrocytes, their role in renal fibrosis and molecular pathways involved. Possible biomarkers of fibrogenesis in chronic kidney disease

Circulating Fibrocytes (CFs) are bone marrow-derived mesenchymal progenitor cells that express a similar pattern of surface markers related to leukocytes, hematopoietic progenitor cells and fibroblasts. CFs precursor display an ability to differentiate into fibroblasts and Myofibroblasts, as well as adipocytes. Fibrocytes have been shown to contribute to tissue fibrosis in the end-stage renal disease (ESRD), as well as in other fibrotic diseases, leading to fibrogenic process in other organs including lung, cardiac, gut and liver. This evidence has been confirmed by several experimental proofs in mice models of kidney injury. In the present study, we developed a protocol for the study of CFs, by using peripheral blood monocytes cells (PBMCs) samples collected from healthy human volunteers. Thanks to a flow cytometry method, in vitro culture assays and the gene expression assays, we are able to study and characterize this CFs population. Moreover, results confirmed that these approaches are reliable and reproducible for the investigation of the circulating fibrocytes population in whole blood samples. Our final aim is to confirm the presence of a correlation between the renal fibrosis progression, and the different circulating fibrocyte levels in Chronic Kidney Disease (CKD) patients. Thanks to a protocol study presented and accepted by the Ethic Committee we are continuing the study of CFs induction in a cohort of sixty patients affected by CKD, divided in three distinct groups for different glomerular filtration rate (GFR) levels, plus a control group of thirty healthy subjects. Ongoing experiments will determine whether circulating fibrocytes represent novel biomarkers for the study of CKD progression, in the early and late phases of this disease.