Antimicrobial Resistance (AMR) is a critical global health challenge, undermining the efficacy of antimicrobial drugs against microorganisms like bacteria, fungi, and viruses. Multidrug Resistance (MDR) arises when microorganisms become resistant to multiple antimicrobial agents. The World Health Organization classifies AMR bacteria into Priority List-I (critical), II (high), and III (medium), prompting action from nearly 170 countries. Six priority bacterial strains account for over 70% of AMR-related fatalities, contributing to more than 1.3 million direct deaths annually and linked to over 5 million deaths globally. Enterobacteriaceae, including Escherichia coli, Salmonella enterica, and Klebsiella pneumoniae, significantly contribute to AMR fatalities. This systematic literature review explores how Machine Learning (ML) and Multitargeted Drug Design (MTDD) can combat AMR in Enterobacteriaceae. We followed PRISMA guidelines and comprehensively analysed current prospects and limitations by mining PubMed and Scopus literature databases. Innovative strategies integrating AI algorithms with advanced computational techniques allow for the analysis of vast datasets, identification of novel drug targets, prediction of resistance mechanisms, and optimization of drug molecules to overcome resistance. MTDD approaches hold promise for developing combination therapies that target multiple bacterial survival pathways, reducing the risk of resistance development. Leveraging ML and MTDD is crucial for advancing our fight against AMR in Enterobacteriaceae.
Keywords: Antimicrobial Resistance; Enterobacteriaceae; Machine Learning; Multidrug Resistance; Multitargeted Drug Designing.