Ahmed, Marwa Tareq (2026) Artificial Intelligence in Clinical Microbiology: Transforming Pathogen Identification, Antimicrobial Resistance Prediction, and Infectious Disease Surveillance. International Journal of Health Systems and Medical Sciences, 5 (1). ISSN 2833-7433

Text IJHSMS+19113+Artificial+Intelligence+in+130-141.pdf Download (396kB)

Abstract

Innovation in clinical microbiology is urgently needed in response to the global disease burden caused by microbial organisms and increasing antimicrobial resistance (AMR). Machine learning, deep learning and natural language processing technologies are quickly changing the way clinical pathology labs identify organisms, predict resistance and perform disease surveillance. A narrative review was performed using peer reviewed articles published between 2020-2025. Articles were identified using PubMed, Embase and Web of Science databases using specific MeSH terms and keywords relating to AI, machine learning, deep learning, clinical microbiology, antimicrobial resistance and disease surveillance. AI has been shown to be highly accurate with >95% accuracy with identifying species and predicting resistance phenotypes from mass spectrometry and whole genome sequencing data. Convolutional neural networks for microscopy have shown high sensitivity and specificity when compared to experts. Natural language processing has been used to extract information from electronic health records and global text to predict outbreaks days in advance. Federated learning and explainable AI are being developed to overcome privacy, regulation and trust issues. AI is a game changer in the field of clinical microbiology. It allows faster diagnosis, improved antimicrobial stewardship and improved global responses. Carefully curated global data sets, regulation and equitable implementation will ensure the true potential of AI will be realised, particularly in low and middle income countries.

Item Type:	Article
Uncontrolled Keywords:	artificial intelligence, machine learning, deep learning, clinical microbiology, antimicrobial resistance, pathogen identification, infectious disease surveillance, natural language processing, whole-genome sequencing, antibiotic stewardship
Subjects:	H Social Sciences
Depositing User:	admin eprints
Date Deposited:	05 Nov 2026 02:16
Last Modified:	05 Nov 2026 02:16
URI:	http://eprints.umsida.ac.id/id/eprint/17474

Actions (login required)

View Item