Utilization of Bioinorganic Nanodrugs and Nanomaterials for the Control of Infectious Diseases Using Deep Learning.

Abstract

As one of the main causes of morbidity and mortality, viral infections have a major impact on the well-being and economics of every nation in the globe. The ability to predictably diagnose viral infections improves the provision of good healthcare as well as the control and prevention of these conditions. Nanomaterials have gained widespread usage in the medical industry recently due to the rapid advancement of nanotechnology and their exceptional chemical and physical qualities, such as their small size and synthesized surface properties. The utilization of nanoparticles for illness detection, surveillance, control, preventive, and therapy, such as the treatment of bacterial infections, is referred to as nanomedicine. Nanomedicine is a comprehensive discipline that is founded on the usage of nanotechnology for clinical objectives. Nanoparticles, which have a nanoscale dimension and exhibit highly controllable optical and physical characteristics as well as the ability to bind to a large variety of chemicals, are among the most popular nanomaterials in nanomedicine. A deep learning framework of autoencoder for categorization study on viral infections is built based on actual hospital patient history of viral infections from August 2015 to August 2020. The information comprises of 10,950 cases, comprising outpatients and inpatients, encompassing the infectious diseases. Of such 10,950 instances, training set made up 70% or 7665 instances, and testing data made up 30% or 3285 instances. The data processing was done using the presented recurrent neural network-artificial bee colony (RNN-ABC) method. Sparse data densifying processes are done through the autoencoder to enhance the system learning outcome. The suggested autoencoder system was also evaluated to other widely used models, including support vector machine, logistic regression, random forest, and Naïve Bayes. In comparison to other approaches, the study's findings demonstrate how well the suggested autoencoder model can predict viral diseases. The methods used for this research can aid in removing reported lags in current monitoring systems, hence reducing society's expenses.