Data Challenge - Machine Learning-Driven Mapping and Modeling of Antimicrobial Resistance Trends Using the ATLAS Dataset

I am writing to express interest in accessing the ATLAS dataset to conduct advanced analyses of antimicrobial resistance (AMR) trends with a specific focus on WHO-priority pathogens relevant to Kenya: Escherichia coli, Klebsiella pneumoniae, Acinetobacter baumannii, Staphylococcus aureus, Streptococcus pneumoniae, Shigella spp., Salmonella spp., and Pseudomonas aeruginosa. These organisms are associated with significant morbidity and mortality in Kenya and are central to national and global AMR control strategies. This study will apply machine learning models to map resistance patterns in these key bacterial species over the past 20 years, leveraging ATLAS’s unique strengths: regular updates, inclusion of Kenyan and paediatric data, and broad coverage of antibiotics resistance. Subgroup analyses will be stratified by geographical location, age, gender, and health economics (e.g., health expenditure, deprivation) to uncover localized drivers of resistance. The second phase will involve epidemiological and health economic modelling to assess the clinical and financial impact of resistance in these pathogens. This will inform targeted stewardship interventions (e.g., optimized empirical prescribing), support more effective infection prevention and control strategies, and improve treatment outcomes by identifying the most effective antimicrobial options per subgroup and setting. By focusing on WHO-priority pathogens, this research directly support the Kenya national action plan for AMR, enhances surveillance, and generates context-specific evidence to guide clinical, public health, and policy decisions. It will also strengthen health systems by providing the analytical foundation for sustainable and equitable AMR interventions in Kenya and similar LMIC settings.