Evolution of machine learning in biosciences: A bibliometric network analysis

Abstract

Machine learning, a rapidly evolving field of data analysis, has now become an integral part of life science research. It has been widely utilized for exploring the information encoded by the genome and beyond the genome. In this study, we surveyed the trends of scientific actors and the conceptual structure of machine learning implementation in biomedical research through the published literature retrieved from the PubMed search engine. A longitudinal cohort bibliographic coupling was executed by employing the VOS viewer tool for 4-time periods, 1964–2010, 2011–2015, 2016–2018, and 2019–2020. Scientific actors of machine learning research include 42,629 unique authors, 27,364 organizations with a mean collaboration index of 3.9. Coword analysis revealed that the conceptual framework of machine learning applications in life sciences moved from simple pattern searching to omic science and medical imaging analytic approaches and from Bayes’ theorem to deep learning algorithms. It is observed that presently machine learning is extensively utilized in investigating emerging situations like coronavirus disease. To epitomize, researchers capitalized on advancements in machine learning tools and high-throughput technologies to delve into the intricate and evolving concepts of biology and medicine.