Antimicrobial resistance and machine learning: past, present, and future

Area of Science:

• * Computational biology and bioinformatics.
• * Infectious disease research.
• * Data science applications in healthcare.

Background:

• * Machine learning is increasingly applied to predict antimicrobial resistance.
• * This is the first bibliometric review of this rapidly developing research area.
• * Understanding research trends and key players is crucial for future advancements.

Purpose of the Study:

• * To conduct the first bibliometric analysis of machine learning in antimicrobial resistance prediction.
• * To identify leading countries, organizations, journals, and authors in the field.
• * To analyze research trends, collaborations, and citation networks.

Main Methods:

• * Bibliometric indicators: article count, citation count, Hirsch index (H-index).
• * Software utilized: VOSviewer and Biblioshiny for network and trend analysis.
• * Data sources: Analysis of publications related to machine learning and antimicrobial resistance.

Main Results:

• * The United States leads with 254 articles (37.57%), followed by China and the UK.
• * Elsevier, Springer Nature, MDPI, and Frontiers Media SA are top publishers.
• * Frontiers in Microbiology and Scientific Reports are leading journals.
• * Significant increase in research and publications observed.
• * Focus on advanced algorithms for accurate resistance forecasting.

Conclusions:

• * The field of machine learning for antimicrobial resistance prediction is expanding rapidly.
• * The United States is the dominant contributor to research output.
• * Continued development of sophisticated machine learning algorithms is essential for combating antibiotic resistance.