Machine Learning on Chronic Kidney Disease Prediction

[kayagoekan]

Author

Name: Gökan Kaya

Affiliation: FH Kufstein

Keywords Chronic Kidney Desease, SVM, Pre-Processing, Classification

Abstract Chronic kidney disease, also known as Chronic Kidney Disease, is an uncharacteristic function of the kidney or a renal failure that develops over a period of months or years. Usually, chronic kidney disease is diagnosed in screening of people known to be at risk of kidney problems kidney problems, such as people with high blood pressure or diabetes and People who have a blood relative with Chronic Kidney Disease (CKD) patients. Early prediction is therefore necessary to combat the disease of the disease and for good treatment. This study proposes that using machine learning techniques for CKD like Support Vector Machine(SVM) classifier. The final output predicts whether the person has CKD or not by having a minimum number of features. It as per the instructions provided in previous sections. Carry out the steps for Cross-linking, Fundref data, adding Document History (specific to journal submission), and finally, Manuscript validation and placing the respective metadata [1] while applying the required template.

Machine Learning on Chronic Kidney Disease Prediction.pdf

[kayagoekan]

kidney_disease.csv

[MHeini]

The current paper presents an approach for using machine learning techniques, specifically Support Vector Machine (SVM) classifier, for early prediction of Chronic Kidney Disease (CKD). The paper's abstract and introduction are well written, providing a clear overview of the problem and the proposed solution. However, the paper would benefit from a more detailed discussion of the findings in relation to the research question, as well as proofreading and clearer language. Overall, the paper presents an interesting approach for early prediction of CKD using machine learning techniques.

[Calmwaters77]

This paper presents a machine learning technique, specifically the Support Vector Machine (SVM) classifier, to predict Chronic Kidney Disease (CKD). A strength of the article is the clear and detailed explanation of the methods used, making the study easy to replicate. The use of a publicly available dataset also adds to the replicability and the pre-processing step is well explained, easy to understand and covers common issues that may arise with real-world datasets. However, the introduction could include the current state of the art in diagnostics for the disease. Additionally although well written in form, there are some spelling mistakes. Overall, this paper presents a well-executed approach on using machine learning techniques for the prediction of CKD. The use of SVM and a publicly available dataset make the process replicable and the results show promising accuracy in predicting CKD.

18/20