Traditional methods like antimicrobial susceptibility testing (AST), mainly used for antimicrobial resistance (AMR) surveillance in Africa, are insufficient because they cannot provide information on the genetic basis for AMR, and they also have limitations in predicting the emergence of AMR. Next-generation sequencing (NGS) offers greater throughput and has the potential to be used not only for predicting the emergence of resistance but also for early detection during outbreaks. The rapidly reducing cost of NGS has led to its adoption in routine clinical microbiology laboratories in developed countries. Contrarily, in Africa, the cost of NGS remains a significant barrier to its adoption in research and clinical settings. This necessitates innovative solutions to address African countries’ challenges in tackling AMR. We aim to address this gap by predicting resistance gene profiles from existing AST data. We offer a cost-effective and accessible way to gain genotypic insights for faster outbreak detection and improved African public health interventions. We aim to conduct exploratory visualisation and analysis of the surveillance datasets to determine existing challenges surrounding antibiotic stewardship in Africa, identify systematic relationships between minimal inhibitory concentration (MIC) data reports and other dependencies, and compare findings relative to other developed countries, to establish pain points in the surveillance settings that set back the fight against AMR in Africa. We would also train machine learning (ML) models on existing AMR global datasets, including phenotypic and genotypic data, to identify resistance patterns. These models will be trained to identify relationships between phenotypic profiles (MIC and resistance profiles) and specific resistance determinant genes. Since genomic surveillance is limited due to resources, this algorithm could assist in prioritising isolates with unusual resistance profiles for further genomic sequencing and help identify high-risk pathogenic strains.