Evidence Hub

Bibliometric analysis of the application of artificial intelligence techniques in bacteriology: a PRISMA-guided research agenda

Velasco Cardona DC, Cardona-Acevedo S, Valencia-Arias A, Pérez-Delgado O, Pinella Vega M

Frontiers in microbiology, 2025

Abstract

Introduction: The integration of artificial intelligence (AI) into bacteriology has marked a pivotal advancement by enabling the analysis of large-scale microbiological datasets. Despite growing adoption, significant research gaps persist, hindering the full exploitation of AI's potential in bacterial research and diagnostics.

Objective: To analyze global scientific production on the application of AI techniques in bacteriology and propose a future research agenda based on bibliometric trends.

Methods: This study conducts a bibliometric analysis of artificial intelligence (AI) applications in bacteriology, explicitly guided by the PRISMA 2020 framework. Unlike traditional reviews, this approach combines PRISMA's methodological rigor with bibliometric techniques to map scientific production. Metadata were retrieved from Scopus and Web of Science using predefined search strategies. Quantitative indicators, co-occurrence networks, and thematic mapping were applied to examine the field's temporal evolution and conceptual structure. The findings provide an evidence-based overview of research trends and gaps, supporting the design of a future research agenda on AI integration in bacteriology.

Results: The findings reveal exponential growth in scientific output, especially between 2022 and 2024. Leading authors include Singh and Waegeman, with high-impact journals such as Frontiers in Microbiology and MSystems. The United States and China are the most productive countries. Thematic…

How strong is the evidence?

Evidence Hub reads this as a systematic review, done in computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.

How the five levels of evidence work. The level is assigned automatically from the abstract and can be wrong, so check the paper.

Read the paper

Related studies

Go deeper in Evidence Hub

Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.

Open this study Sign up free