Certain investigations on different optimization methods for chronic disease classification

Abstract

newlineIn recent years, the solitary reasons of mortality in the world are newlinechronic diseases such as heart diseases, diabetes, chronic kidney diseases etc. newlineThese diseases should be diagnosed earlier, however the technique is costly newlineas well as it leads to many complications. Considering the complexities, newlinedatamining performs major part in classifying the chronic diseases newlineaccurately. A new approach to classify chronic disease is by merging the newlineMulti-Objective Firefly Optimization Algorithm (MOFFA) and Random newlineForest (RF). The main goal is generating an efficient and heterogeneous newlineDecision Trees while determining the optimum training sets to run at the newlinesame time. Rather utilizing traditional approaches like bootstrap, Multi- newlineObjective Firefly Optimization algorithm and Random Forest algorithm is newlineproposed in this method. As a result, to train Random Forest various training newlinesets are generated with alternative instances and attributes. As a result, the newlineperformance of Random Forests can be improved, and thus the prediction newlineaccuracy. The effectiveness of the proposed method is explored by newlinejuxtaposing the effectiveness of the proposed method with other classifiers newlinefor different datasets. The proposed work is tested on six UCI datasets. newlineAccording to the findings, the proposed MOFFA-RF algorithm surpass other newlineclassifiers by accuracy of 88% on CKD, 87% on CVD, 82% on Diabetes, newline88% on Hepatitis, 88% on WBC and 76% on ILPD. newlineThrough analyzing healthcare data and extracting patterns the newlinehealthcare administrators, victims and health care communities will get newlineadvantage if the diseases are early predicted. Majority of the existing works newlinefocused on increasing the accuracy of the techniques and didn t concentrate newlineon other performance measures. newline newline