•  
  •  
 

Abstract

Background: Antimicrobial resistance (AMR) causes approximately 4.95 million deaths annually. Although artificial intelligence (AI) may enhance AMR detection, surveillance, and antimicrobial use, evidence remains limited regarding how health students’ knowledge, perception, and willingness influence AI adoption for AMR control.

Purpose: This study aimed to examine the direct and mediating relationships between health students’ knowledge, perception, and willingness toward AI-based approaches for combating antimicrobial resistance in Indonesia using structural equation modeling.

Methods: A cross-sectional study involving 4,369 health students across Indonesia was conducted using a validated questionnaire. Data on knowledge, perception, and willingness were analyzed using Structural Equation Modeling (SEM), SmartPLS, and Confirmatory Factor Analysis (CFA).

Results: A total of 4,369 health students surveyed across Indonesia, most were female (83.2%) and enrolled in bachelor's programs (68.5%). Knowledge showed a strong positive effect on perception (β = 0.859, p < 0.001) and a moderate effect on willingness (β = 0.268, p < 0.001). Willingness had a small but significant effect on perception (β = 0.046, p < 0.001) and partially mediated the relationship between knowledge and perception (β = 0.012, p < 0.001).

Conclusions: Knowledge strongly influences health students’ perceptions and willingness to adopt AI for AMR control, with willingness acting as a partial mediator. Integrating AI-related knowledge and practical learning opportunities into health education may enhance future readiness for AI-assisted AMR management.

Download

Share

COinS