Letter to the editor: "How do experts classify sepsis cases for sepsis surveillance? Lessons learned from a...

Behavioural Artificial Intelligence Technology (BAIT) has recently been proposed to codify expert reasoning for sepsis surveillance. We provide preliminary cross-institutional data from two Southeast Asian hospitals (N = 1042 suspected sepsis episodes), demonstrating challenges in multi-national generalizability, misclassification of non-infectious inflammatory states, and underutilization of process-of-care indicators. Incorporating contextual variables and hybrid integration of process measures improved classification accuracy and alignment with expert adjudication. These findings offer actionable strategies to enhance BAIT models, supporting globally relevant and pragmatic sepsis surveillance.