Using Artificial Intelligence for Drug Discovery: A Bibliometric Study and Future Research Agenda

Abstract

Drug discovery is usually a rule-based process that is carefully carried out by pharmacists. However, a new trend is emerging in research and practice where artificial intelligence is being used for drug discovery to increase efficiency or to develop new drugs for previously untreatable diseases. Nevertheless, so far, no study takes a holistic view of AI-based drug discovery research. Given the importance and potential of AI for drug discovery, this lack of research is surprising. This study aimed to close this research gap by conducting a bibliometric analysis to identify all relevant studies and to analyze interrelationships among algorithms, institutions, countries, and funding sponsors. For this purpose, a sample of 3884 articles was examined bibliometrically, including studies from 1991 to 2022. We utilized various qualitative and quantitative methods, such as performance analysis, science mapping, and thematic analysis. Based on these findings, we furthermore developed a research agenda that aims to serve as a foundation for future researchers.

Artificial Intelligence for Cancer Detection—A Bibliometric Analysis and Avenues for Future Research

“…With an AI system's advancing complexity, it is increasingly difficult to understand how it comes up with its results and predictions. This holds true for the most of today's AI and machine learning algorithms, which are very complex and [21,115] considered black boxes. Although XAI is hard to achieve, it is necessary for certain use-cases in critical areas like law or medicine [116][117][118].…”

“…We chose Scopus as the scientific database for our data collection. Scopus is a well-known database that has been used by several other bibliometric studies in the past [21,47,48,[50][51][52]. Additionally, Scopus covers more journals than Web of Science and was therefore found to be suitable to identify as much research as possible [26].…”

“…For the creation of our search string, we oriented ourselves to other recent bibliometric studies that investigated AI within medicine [53] and pharmacy [21]. Our search string consists of two parts, one that covers the technical terms and another that consists of the application domain.…”

“…In 2022, 1213 publications had already been published before we collected the data for our study (23 September). Since it appears like statistically more publications are published in the last months of a year [21], we assume that the trend of increasing publications will be ongoing in 2022. Based on an extrapolation, we assume the total number of publications for 2022 will be 1872, with an estimate of 659 articles published after 23 September.…”

“…Due to their benefits, bibliometric studies have gained in popularity in recent years. Bibliometric approaches have been used in many different areas and disciplines, including pharmacy [21][22][23], oncology [24], or business and management [25]. By collecting and analyzing prior research, a bibliometric study can help to advance a field by systematically summarizing existing results.…”