Computational Intelligence Based Electronic Healthcare Data Analytics Using Feature Selection with Classification by Deep Learning Architecture

EHRs (Electronic health records) are a source of big data that offer wealth clinical patient data. However, because these notes free-form texts, writing formats and styles range greatly amongst various records, text from eHRs, such as discharge rapid notes, provide analysis challenges. This research proposed novel technique in electronic healthcare based on feature selection classification utilizingDL methods. here the input is collected EH data, processed for dimensionality reduction, noise removal. A public pre-processing method dealing with HD-EHR which tries to minimize amount EHR representational features while enhancing effectiveness following analysis, classification. The has been selected utilizingweighted curvature support vector machine. Then this deep classified using sparse encoder transfer learning. experimental carried out datasets terms accuracy 96%, precision 92%, recall 77%, F-1 score 72%, MAP 65%