scholarly journals An Approach for improving the Prediction of Chronic Kidney Disease using Machine learning

2020 ◽  
pp. 530-536
Author(s):  
Pooja Sharma ◽  
Saket J Swarndeep
Keyword(s):  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Kidney Diseases ◽  
Detection System ◽  
Machine Learning Techniques ◽  
Training Algorithms ◽  
Deep Network ◽  
Novel Approach ◽  
Disease Study

According the 2010 global burden of disease study, Chronic Kidney Diseases (CKD) was ranked 18th in the list of causes of total no. of deaths worldwide. 10% of the population worldwide is affected by CKD. The prediction of CKD can become a boon for the population to predict the health. Various method and techniques are undergoing the research phase for developing the most accurate CKD prediction system. Using Machine learning techniques is the most promising one in this area due to its computing function and Machine learning rules. Existing Systems are working well in predicting the accurate result but still more attributes of data and complicity of health parameter make the root layer for the innovation of new approaches. This study focuses on a novel approach for improving the prediction of CKD. In our proposed system we will implement the deep learning algorithms like Deep Neural Network. Chronic kidney disease detection system using deep network is shown here. This system of deep network accepts disease-symptoms as input and it is trained according to various training algorithms. After the network is trained, this trained network system is used for detection of kidney disease in the human body.

scholarly journals Survey for the Prediction of Chronic Kidney Disease using Machine Learning

2019 ◽  
pp. 154-158
Author(s):  
Pooja Sharma ◽  
Saket J Swarndeep
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Kidney Diseases ◽  
Detection System ◽  
Machine Learning Techniques ◽  
Network System ◽  
Data Set ◽  
Neural Network System

According the 2010 global burden of disease study, Chronic Kidney Diseases (CKD) was ranked 18th in the list of causes of total no. of deaths worldwide. 10% of the population worldwide is affected by CKD. The prediction of CKD can become a boon for the population to predict the health. Various method and techniques are undergoing the research phase for developing the most accurate CKD prediction system. Using Machine Learning techniques is the most promising one in this area due to its computing function and Machine Learning rules. Existing Systems are working well in predicting the accurate result but still more attributes of data and complicity of health parameter make the root layer for the innovation of new approaches. This study focuses on a novel approach for improving the prediction of CKD. In recent time Neural network system has discovered its use in disease diagnoses, which is depended upon prediction from symptoms data set. Chronic kidney disease detection system using neural network is shown here. This system of neural network accepts disease-symptoms as input and it is trained according to various training algorithms. After neural network is trained using back propagation algorithms, this trained neural network system is used for detection of kidney disease in the human body.

scholarly journals An Approach to Classify Chronic Kidney Diseases using Scintigraphy Images

2019 ◽  
Author(s):  
Pedro Pedrosa Rebouças Filho ◽  
Suane Pires Pinheiro Da Silva ◽  
Jefferson Silva Almeida ◽  
Elene Firmeza Ohata ◽  
Shara Shami Araujo Alves ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Kidney Diseases ◽  
Extraction Methods ◽  
Support Vector ◽  
Svm Classifier ◽  
K Nearest Neighbors ◽  
Chronic Kidney Diseases ◽  
Occurrence Matrix

Chronic kidney diseases cause over a million deaths worldwide every year. One of the techniques used to diagnose the diseases is renal scintigraphy. However, the way that is processed can vary depending on hospitals and doctors, compromising the reproducibility of the method. In this context, we propose an approach to process the exam using computer vision and machine learning to classify the stage of chronic kidney disease. An analysis of different features extraction methods, such as Gray-Level Co-occurrence Matrix, Structural Co-occurrence Matrix, Local Binary Patters (LBP), Hu's Moments and Zernike's Moments in combination with machine learning methods, such as Bayes, Multi-layer Perceptron, k-Nearest Neighbors, Random Forest and Support Vector Machines (SVM), was performed. The best result was obtained by combining LBP feature extractor with SVM classifier. This combination achieved accuracy of 92.00% and F1-score of 91.00%, indicating that the proposed method is adequate to classify chronic kidney disease in two stages, being a high risk of developing end-stage renal failure and other outcomes, and otherwise.

scholarly journals Data Analysis on Chronic Kidney Disease Prognosis

2020 ◽  
Vol 8 (6S) ◽  
pp. 130-132
Keyword(s):  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Data Analysis ◽  
Kidney Disease ◽  
Kidney Diseases ◽  
Chronic Kidney Diseases ◽  
Optimum Result ◽  
Disease Prognosis

We have taken our dataset from UCI Machine Learning Repository. Our study is about Chronic Kidney Diseases based on 24 input attributes to produce one output attribute i.e. a patient is suffering from chronic kidney disease or not. We have used three major attributes in our study i.e. PCV, RBCC and Hemoglobin with respect to Age for optimum result. These attributes play major role in our study.

scholarly journals Prevalence of hereditary tubulointerstitial kidney diseases in the German Chronic Kidney Disease study

2021 ◽  
Author(s):  
Bernt Popp ◽  
Arif B. Ekici ◽  
Karl X. Knaup ◽  
Karen Schneider ◽  
Steffen Uebe ◽  
...  
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Kidney Diseases ◽  
Diagnostic Yield ◽  
Genetic Disorder ◽  
Clinical Criteria ◽  
Pathogenic Variants ◽  
Increased Risk ◽  
Monogenic Diseases ◽  
Disease Study

ABSTRACTExome sequencing (ES) studies in chronic kidney disease (CKD) cohorts could identify pathogenic variants in ∼10% of patients. This implies underdiagnosis of hereditary CKD. Tubulointerstitial kidney diseases, showing no typical clinical/histologic finding but tubulointerstitial fibrosis, are particularly difficult to diagnose.We used a custom designed targeted panel (29 genes) and MUC1-SNaPshot to sequence 271 DNA samples, selected by clinical criteria from 5,217 individuals in the German Chronic Kidney Disease (GCKD) cohort.We identified 33 pathogenic small variants. Of these 27 (81.8%) were in COL4-genes, the largest group being 15 COL4A5-variants with nine unrelated individuals carrying c.1871G>A, p.(Gly624Asp). We found three cysteine variants in UMOD, a novel missense, and a novel splice variant in HNF1B and the homoplastic MTTF variant m.616T>C. Copy-number analysis identified a heterozygous COL4A5-deletion, and a HNF1B-duplication/-deletion, respectively. Overall, pathogenic variants were present in 12.5% (34/271) and variants of unknown significance in 9.6% (26/271) of selected individuals. Bioinformatic predictions paired with gold standard diagnostics for MUC1 (SNaPshot) could not identify the typical cytosine duplication (“c.428dupC”) in any individual, implying that ADTKD-MUC1 is rare.Our study shows that >10% of individuals with certain clinical features carry disease variants in genes associated with tubulointerstitial kidney diseases. COL4-genes constitute the largest fraction, implying they are overlooked using clinical Alport-syndrome criteria. We also identified variants easily missed by some ES pipelines. Finally, our results indicate that the filtering criteria applied enrich for an underlying genetic disorder.SIGNIFICANCE STATEMENTCKD affects >10% of the global population and recent studies imply that a considerable portion can be attributed to monogenic diseases, which are likely underappreciated in the clinical routine. Tubulointerstitial kidney diseases are a particularly difficult group of hereditary kidney diseases to diagnose both clinically and genetically. To investigate the prevalence of these disorders in a large CKD cohort we established a set of clinical criteria and designed a custom panel sequencing pipeline. Based on the diagnostic yield of 12.5%, we recommend an algorithm to clinically select and genetically evaluate patients with increased risk for a hereditary tubulointerstitial kidney disease.

scholarly journals Computer-Aided Diagnosis of Chronic Kidney Disease in Developing Countries: A Comparative Analysis of Machine Learning Techniques

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 25407-25419 ◽  
Author(s):  
Alvaro Sobrinho ◽  
Andressa C. M. Da S. Queiroz ◽  
Leandro Dias Da Silva ◽  
Evandro De Barros Costa ◽  
Maria Eliete Pinheiro ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Developing Countries ◽  
Comparative Analysis ◽  
Kidney Disease ◽  
Computer Aided Diagnosis ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Computer Aided ◽  
Aided Diagnosis
Sign in / Sign up

Export Citation Format

Share Document