Improved Ant Colony on Feature Selection and Weighted Ensemble to Neural Network Based Multimodal Disease Risk Prediction (WENN-MDRP) Classifier for Disease Prediction Over Big Data

Abstract

As the big data is growing in biomedical and healthcare communities, so are precise analyses of medical data aids, premature disease identification, patient care as well as community services. On the other hand, the accuracy of the analysis decreases, if t he medical data quality is imperfect. As a result, the choice of features from the dataset turns out to be an extremely significant task. Feature selection has exposed its efficiency in numerous applications by means of constructing modest and more comprehensive models, enlightening learning performance and preparing clean and clear data. The proposed method analyzes the difficulties of feature selection for big data analytics. Improved Ant Colony Optimization based Feature Selection (IACO) algorithm is presented for resolving this issue. The reconstruction of missing data before the incomplete data available was performed with help of latent factor mode. Therefore, it was not easy t o choose the best features from the structured and unstructured data. the unheard technique which is called Weighted Ensemble Based Neural Network for multimodal disease risk prediction(WENN-MDRP) algorithm is implemented in order to provide the best features selection among structured as well as unstructured data. The research method provides improved prediction accuracy when matched with conventional techniques. In the MATLAB environment, the presented classifiers are implemented. The outcomes are computed in regard to reca ll, precision, accuracy, f-measure and error rate.

Disease prognosis using machine learning algorithms based on new clinical dataset

“…For disease prediction with big data in healthcare, Joel and Priya [24], employed extended CNN. The hospital is built using this approach, which offers great accuracy, performance, and convergence speed in the medical industry.…”