COMPARISON OF ARTIFICIAL INTELLIGENCE PERFORMANCES OBTAINED IN DATASET CLASSIFICATIONS USING RESPIRATORY DATA

Abstract

Diagnosis of disease with respiratory data is very important today as it was in the past. These diagnoses, which are mostly based on human experience, have begun to leave their place to machines with the development of technology. Especially with the emergence of the COVID-19 epidemic, studies on the ability of artificial intelligence to diagnose diseases by using respiratory data have increased. Sharing open-source data has paved the way for studies on this subject.Artificial intelligence makes important contributions in many fields. In the field of health, significant accuracy results have been obtained in studies on respiratory sounds. In this article, a literat ure review on respiratory sounds and artificial intelligence achievements was made. 34 articles -that were selected from IEEE, Elsevier, Pubmed, and ScienceDirect digital databases and published after 2010- were used for comparisons. As keywords, "breathing sounds and", "respiratory sound classification", together with "artificial intelligence" and "machine learning" were chosen. In this study, artificial intelligence methods used in 34 publications selected by literature review were compared in terms of the performances obtained in the training.