• Dr. Ayesha Banu
• Zareena Begum

Chronic kidney disease (CKD), which is also a key risk factor for other diseases, kills and disables people all over the world. Because there are no evident signs in the early stages of CKD, it might go unnoticed. Medicine that decreases the progression of renal disease can be used to prevent it from progressing in patients who are diagnosed early. Clinicians can achieve their objectives more quickly by using machine learning models. This study suggests a CKD diagnosis approach based on machine learning. In the UCI machine learning repository, missing values in the CKD data set were discovered. The most similar measures from a large number of full samples were used to fill in the missing data in each partial sample using KNN imputation. Patients may forget to take measures in the real world for a variety of reasons, resulting in missing data. Six machine learning approaches were employed to construct models when the missing data set was completed: logistic regression, k-nearest neighbor, naive Bayes classifier, and feed forward neural network. With a diagnosis accuracy of 99.75 percent, Random Forest is the most accurate of these machine learning models. After ten simulations based on the errors generated by the constructed models utilizing the integrated model, an average accuracy of 99.83 percent can be achieved. As a result, we came to the conclusion that this method may be used to diagnose more complex clinical disorders.

Machine Learning, Logistic Regression, KNN, Neural Network, Random Forest.

"CHRONIC DISEASE DIAGNOSIS USING MACHINE LEARNING ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.o765-o772, May-2023, Available :http://www.jetir.org/papers/JETIR2305F98.pdf

"CHRONIC DISEASE DIAGNOSIS USING MACHINE LEARNING ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppo765-o772, May-2023, Available at : http://www.jetir.org/papers/JETIR2305F98.pdf