David Otieno is a Clinical Research Scientist at the Kenya Medical Research Institute(KEMRI), where he conducts research on infectious diseases with a focus on antimicrobialresistance, microbial genomics, and host–microbiome interactions. He has extensiveexperience in clinical and laboratory research, including molecular biology, microbiology,genomics, biobanking, and epidemiological studies. David has contributed tomultidisciplinary research projects involving infectious disease surveillance, antimicrobialresistance, and translational health research, collaborating with national and internationalpartners.He is currently pursuing research on investigating how probiotics reduce antibioticresistance gene carriage in infants' gut microbiomes using functional omics approaches. Hisresearch aims to generate evidence that informs strategies to combat antimicrobial resistanceand improve global health. David is passionate about translating scientific discoveries intopublic health impact, strengthening research capacity in Africa, and fostering collaborationsthat advance infectious disease research and innovation.

Title: MicroBIS A novel AI/ML based platform for bacterial and antimicrobial resistance identificationand prediction. - Abstarct: Antimicrobial Resistance (AMR), one of the top 10 global health threats, poses a critical publichealth challenge with a projected 10 million deaths annually by 2050 if left unchecked1,2. In 2019, 1.27million deaths were attributed to AMR, with data gaps in low- and middle-income countries (LMICs)impeding global efforts3,4. Fragmented databases limit the understanding of regional AMR burdens andhinder the development of data-driven interventions. For pharmaceutical companies, these gaps stifleresearch and drug development. Datasets like the Pfizer-ATLAS program are essential for real-time trackingof antibiotic resistance and for building predictive models to forecast AMR. Machine learning (ML)- basedtools offer potential solutions for support clinical decision-making, personalized antibiotic prescriptions andAMR surveillance.MethodsThe microBIS platform combines a web server, AI/ML processing, and a user-friendly client interface. TheMERN Stack workflow was used for web development and Python-based toolslike Random Forest and PyBact for AI/ML modeling. Biochemical test results simulated and the PfizerATLAS datasets were used to train the platform's models to identify bacteria and predict AMR.ResultsThe microBIS app offers intuitive interfaces for bacterial identification and AMR prediction. It usesbiochemical test panels (8 or 20 tests)for bacteria identification, achieving a 79% accuracywith the 20-panel and 31% with the 8-pane. When predicting the top 5 bacterial species,accuracy increased to 99% for the 20-panel and 74% for the 8-panel. Certain tests, like citrate production,showed higher predictive value. For AMR prediction, the Machine Learning (ML)model trained on the PfizerATLAS dataset achieved 56% accuracy in predicting antimicrobial susceptibility profiles. Key predictorsincluded bacterial phenotypes and species.ConclusionsmicroBIS bridges the gap between accessible biochemical assays and advanced ML tools,offering acost-effective, scalable solution for bacterial identification and AMR prediction. It empowers healthcareproviders and researchers in resource-limited settings with rapid diagnosticcapabilities,enhancingclinicaldecision-makingandAMRsurveillance.ByintegratingAMRdatasetsandpredictiveanalytics,microBISenablesbettercaredeliveryandsupportstheglobal fight against AMR