Medical laboratories generate data every day that contain important information about pathogens and their susceptibility to antibiotics. However, this information may remain scattered across test reports, instrument records, and separate databases, limiting its usefulness in understanding broader infection patterns. This creates an opportunity to design an intelligent medical system that connects these sources and transforms their results into organised knowledge, helping specialists monitor pathogens and changes in resistance patterns. The proposed system would collect microorganism identification results and antimicrobial susceptibility test results, linking them with biosensor data where available and appropriate for the intended purpose. Relevant information could include specimen type, collection date, clinical department, and testing method. The value of this integration lies in placing each result within its context: an individual laboratory finding may answer a specific diagnostic question, while aggregated results can reveal trends that warrant investigation. The design process begins with identifying data sources and standardising how information is recorded. Organism and antibiotic names, measurement units, testing methods, and the standards used to interpret results should be consistently documented. Preliminary readings must also be distinguished from results authorised by specialists. This emphasis on standardisation and quality aligns with the World Health Organization’s approach to antimicrobial resistance surveillance, which relies on the systematic collection, analysis, and sharing of standardised data. Biosensor data require particular care during integration. One sensor may indicate the presence of a pathogen-associated molecule, while another measures a different biological response. The target detected by each device and its performance limitations must therefore be documented, and signals should not all be treated as equivalent results. Detecting a pathogen also does not establish its antibiotic resistance; resistance determination requires a dedicated test or additional evidence whose validity has been established. Once the data are organised, statistical analysis and Machine Learning algorithms can be used to investigate relationships among pathogens, specimens, and resistance patterns. System functions could include displaying resistance proportions for each bacterium–antibiotic combination, tracking changes over time, and identifying unusual increases requiring review. Predictive models could be added later, provided that their tasks are precisely defined and uncertainty is communicated in their outputs. How results are counted affects the meaning of the indicators displayed. Repeated testing of the same patient may overrepresent certain cases, while an increase in positive specimens may reflect more testing rather than greater infection prevalence. The system therefore needs clear rules for handling duplicates and selecting appropriate denominators for each indicator, according to the purpose of the analysis. The GLASS manual emphasises data quality checks and the management of duplicate results to reduce bias in resistance estimates. Outputs could be presented through a dashboard that allows specialists to examine results by period, department, specimen type, and pathogen. When an unusual signal appears, the system would display the underlying data so that specialists can review the basis of the alert. An alert remains a starting point for investigation: confirming an outbreak or infection transmission requires laboratory and epidemiological inquiry beyond identifying numerical associations. The project offers an opportunity for collaboration between the Biological Resistance Technologies discipline and the Intelligent Medical Systems Department. Microbiology specialists would contribute to selecting indicators, interpreting results, and verifying their meaning, while programming and data analysis specialists would develop connections between sources, analytical models, and user interfaces. This partnership would help direct development towards practical laboratory needs. Before clinical use, the system would require evaluation of data transfer accuracy, indicator validity, and the performance of any predictive model on independent data. False alerts and missed events should also be measured, together with the system’s suitability for existing workflows. The World Health Organization emphasises external validation, data quality, and clearly defined intended uses for healthcare artificial intelligence systems, alongside information protection and human oversight. Designing an intelligent medical system to monitor pathogens and antibiotic resistance is a project in building connected health knowledge. Its value is realised when it preserves the reliability of results, makes analytical limitations clear, and provides specialists with information they can review. By combining microbiological expertise with computational engineering, such tools can strengthen surveillance, improve the use of laboratory data, and provide a more reliable foundation for research and healthcare decisions. Al-Mustaqbal University – Iraq’s Number One University.