INTELLIGENT DATA ANALYSIS IN BIOMEDICAL RESEARCH: ARTIFICIAL NEURAL NETWORKS

2021

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.33396/1728-0869-2021-4-55-64
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Substantial amounts of biomedical data are being accumulated every year. Large datasets are accumulated in specialized repositories, electronic document management systems, medical information systems, and other repositories. Classical statistical analysis does not always provide opportunities for analysis of these large datasets; therefore, intelligent data analysis (IDA) is becoming more popular in biomedical research. This paper is an introduction to artificial neural networks - one of the most popular methods of IDA. An artificial neural network is an attempt to build a mathematical analog of the brain and mathematically simulate the transmission of a nerve impulse between neurons. We present an example of the application of artificial neural networks in medical research using SPSS and Statistica software packages. The article describes a medical research question, an example of a dataset and a guide on construction and training of an artificial neural network as well as interpretation of the results.