Objectives/Backgrounds: Nowadays, heart diseases play a very big role in the universe. The Physicians in practice gives various names for heart diseases such as heart attack, cardiac attack, cardiac arrest etc. Among the computerized methods to find the heart disease, Named Entity Recognition (NER) algorithm is used to find the synonyms for the heart disease text to mine the meaning in medical reports and various applications. Methods/Statistical Analysis: The Heart disease text input data given by the physician is taken for the prepossessing and changes the input content to the desired format, then that resultant output fed as input for the prediction. This research work uses the NER to find the meanings of the heart disease text data and uses the existing two methods Deep Learning Models and whale optimization are combined and proposed a new method Optimal Deep Neural Network (ODNN) for predicting the disease. Findings: For the prediction, weights and ranges of the patient affected data via selected attributes are chosen for the analysis. The result is then classified with the Deep Neural Network to find the accuracy of the algorithms. The performance of ODNN is evaluated by means of classification measures such as precision, recall and f-measure values. Improvement: In future, the other classification algorithms or other text data algorithms were used to find for large amount of text data
Diagnosis of heart diseases by a secure Internet of Health Things system based on Autoencoder Deep Neural Network