Optimizing the implementation and use of artificial intelligence (AI) and data in clinical microbiology, infectious diseases, hospital epidemiology, and public health and growing expertise to support clinical and research applications.

Aims and objectives

The study group will cover the following major topics: AI, machine learning, digital innovation, data and methodological standardization and interoperability. We will address multiple themes:

• Applications of AI and data including to clinical microbiology, infectious diseases, antimicrobial stewardship, infection prevention and control, surveillance, hospital epidemiology, and public health.
• Best practice in developing new AI approaches including study design, reporting, and applications of specific methodologies, e.g. classical machine learning methods, deep learning, interpretable methods, addressing bias, federated learning, large language models, data sharing, equity etc.
• Data access, governance, standardization, and interoperability to develop collaborations to assemble and share data effectively and at scale.
• Implementation standards and best practice to support AI and data platform development, decision support systems, safety monitoring, and oversight of real-world implementations of AI.
• Public and clinical engagement
• Training and capacity building across a wide spectrum of pre-existing capabilities to support interpreting results, evaluating tools, understanding methods, and developing new approaches from high- to low- and middle-income settings. 

Within the data theme the study group will focus on FAIR use of data (Findability, Accessibility, Interoperability, and Reusability). We aim to establish a framework for lab-data exchange in cooperation with experts involved in the European Health Data Space (EHDS) and other expert groups.