Volume 91, February 2026, 155343Author links open overlay panel, , , Abstract

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.

Section snippetsCRediT authorship contribution statement

Cherdpong Choenklang: Conceptualization, Data curation, Formal analysis, Validation, Writing – original draft. Nav La: Conceptualization, Data curation, Formal analysis, Validation, Writing – original draft. Schawanya K. Rattanapitoon: Conceptualization, Data curation, Formal analysis, Validation, Writing – original draft, Writing – review & editing. Nathkapach K. Rattanapitoon: Conceptualization, Data curation, Supervision, Writing – review & editing.

Ethical approval statement

Not required.

Funding source

None declared.

Declaration of competing interest

None declared.

References (4)R.A.M. Tuinte et al.How do experts classify sepsis cases for sepsis surveillance? Lessons learned from a behavioural artificial intelligence technology (BAIT) approach

J Crit Care

(2025)

C. Rhee et al.Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009–2014

JAMA

(2017)

There are more references available in the full text version of this article.

View full text

© 2025 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.