A Brief Bibliometric Survey of Explainable AI in Medical Field

Abstract

Background: This study aims to analyze the work done in the field of explainability related to artificial intelligence, especially in the medical field from 2004 onwards using the bibliometric methods. Methods: different articles based on the topic leukemia detection were retrieved using one of the most popular database- Scopus. The articles are considered from 2004 onwards. Scopus analyzer is used for different types of analysis including documents by year, source, county and so on. There are other different analysis tools such as VOSviewer Version 1.6.15. This is used for the analysis of different units such as co-authorship, co-occurrences, citation analysis etc. Results: In our study, the Scopus search has the outcome of a total of 91 articles on explainability of AI from 2004 onwards. The topic is so popular and is newly introduced. The maximum articles are published in the year 2020. Computer science area contributed the largest number of articles of 37% and United states contributed most of the articles in the field. Network analysis of different parameters shows a good potential of the topic in terms of research. Conclusions: Scopus keyword search outcome has 91 articles with English language having the largest number of 90 and one is contributed in German language. Authors, documents, country, affiliation etc are statically analyzed and indicates the potential of the topic. Network analysis of different parameters indicates that, there is a lot of scope to contribute in the further research in terms of explainability in medical fields including diagnosis in imaging. There are advanced algorithms of computer vision, deep learning and machine learning are utilized in medical diagnosis as far as imaging is concerned. Explainable AI frameworks will prove to increase the trustability in medical diagnosis.

Ähnliche Arbeiten