Role of artificial intelligence and machine learning in the prediction of infectious diseases: A comprehensive review of bacterial, viral, and fungal pathogens
Year: 2026
Type: article
Abstract: Infectious diseases are still a significant cause of morbidity and mortality in the world and are very costly in terms of health and socio-economic burden. Innovative surveillance, diagnostic and predictive strategies are needed, given the increasing risk of antimicrobial resistance (AMR), the emergence of new pandemics, and the re-emergence of neglected pathogens. Artificial Intelligence and Machine Learning are revolutionizing technologies that can harness actionable insights from complex biological, clinical, genomic, imaging and epidemiological datasets. The existing Artificial Intelligence and Machine Learning applications were classified into three core pathogen areas of bacterial, viral, and fungal infectious diseases. Several studies reported that artificial intelligence and machine learning models achieved superior predictive performance compared to conventional approaches within their respective datasets and evaluation settings. Supervised learning approaches, such as random forest and gradient boosting algorithms, performed very well in many bacterial infections, potentially with area-under-the-curve values up to >0.95 for predicting AMR from Whole Genome Sequencing data and predicting sepsis in patients. In the field of viral diseases, deep learning architectures such as long short-term memory, transformers, and graph neural networks were used to facilitate swift predictions of outbreaks, real-time surveillance of mutations, and support for vaccine development. In fungal infections, microscopic images were used to obtain classification accuracy >99% for species-level identification using graph neural networks, and early detection of invasive candidemia in intensive care units was improved.
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W7205007330