In this computer world, huge data are generated in several fields. Statistics in the healthcare engineering provides data about many diseases and corresponding patient’s information. These data help to evaluate a huge amount of data for identifying the unknown patterns in the diseases and are also utilized for predicting the disease. Hence, this work is to plan and implement a new computer-aided technique named modified Ensemble Learning with Weighted RBM Features (EL-WRBM). Data collection is an initial process, in which the data of various diseases are gathered from UCI repository and Kaggle. Then, the gathered data are pre-processed by missing data filling technique. Then, the pre-processed data are performed by deep belief network (DBN), in which the weighted features are extracted from the RBM regions. Then, the prediction is made by ensemble learning with classifiers, namely, support vector machine (SVM), recurrent neural network (RNN), and deep neural network (DNN), in which hyper-parameters are optimized by the adaptive spreading rate-based coronavirus herd immunity optimizer (ASR-CHIO). At the end, the simulation analysis reveals that the suggested model has implications to support doctor diagnoses.

在这个计算机世界中，在多个领域产生了巨大的数据。医疗保健工程中的统计学提供了许多疾病的数据和相应的患者信息。这些数据有助于评估大量数据以识别疾病中的未知模式，也可用于预测疾病。因此，这项工作是计划和实施一种新的计算机辅助技术，称为具有加权 RBM 特征的改进集成学习 (EL-WRBM)。数据收集是一个初始过程，其中从 UCI 存储库和 Kaggle 收集各种疾病的数据。然后，通过缺失数据填充技术对收集到的数据进行预处理。然后，预处理数据由深度信念网络 (DBN) 执行，其中从 RBM 区域提取加权特征。然后，预测是通过分类器的集成学习进行的，即支持向量机（SVM）、递归神经网络（RNN）和深度神经网络（DNN），其中超参数由基于自适应传播率的冠状病毒群优化免疫优化器 (ASR-CHIO)。最后，仿真分析表明，所建议的模型对支持医生诊断具有重要意义。