• Mohammed Imran
• Dr.S. Shahar Banu

Chronic disease prediction is one of the key research in healthcare. Chronic diseases growing as burden to healthcare, because these patients require therapy throughout life. A person can only survive without kidneys for an average time of 18 days. So, it is important to have effective methodology for early prediction of chronic kidney disease. In healthcare field, the accurate prediction plays the major role in finding the risk and level of the disease in the patient. The exact prediction will give lot of benefits like lifesaving, avoiding therapy for entire life and financial costs. This work proposes a Probability Weighted AdaBoost to predict chronic kidney disease based on various attributes. Re-Weight calculation of AdaBoost has been modified in proposed method based on incorrectly classified instances of False Chronic kidney disease, False Non-Chronic kidney disease to compare the performance of a proposed algorithm, existing algorithms like Naïve Bayes, Decision Tree, AdaBoost and Support Vector Machine, are used. Results show that the proposed method outperforms all the prevailing algorithms.

Chronic kidney Diseases, Prediction Models, Accuracy, Disease Classification, AdaBoost, Probability Weighted AdaBoost.

"Chronic Disease Prediction Using Probability Weighted Adaboost", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 1, page no.f306-f318, January-2022, Available :http://www.jetir.org/papers/JETIR2201546.pdf

"Chronic Disease Prediction Using Probability Weighted Adaboost", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 1, page no. ppf306-f318, January-2022, Available at : http://www.jetir.org/papers/JETIR2201546.pdf