Dynamic CBME in action: rule-based digital case-based learning to evaluate antibiotic-stewardship reasoning in MBBS learners

BACKGROUND: Antimicrobial resistance is a major global public health threat, necessitating improved antibiotic stewardship. India's Competency-Based Medical Education (CBME) framework requires robust methods to assess and cultivate clinical reasoning. This study evaluated a rule-based Digital Case-Based Learning (DCBL) module with algorithm-triggered formative feedback for antibiotic-stewardship decision-making among undergraduate medical learners. METHODS: A quasi-experimental, single-group pre-post study evaluated three rule-based DCBL micro-cases (upper respiratory tract infection [URTI], urinary tract infection [UTI], and acute watery diarrhoea) in 271 third- and fourth-phase MBBS learners at a tertiary-care teaching hospital in South India. Script Concordance Test (SCT) performance was assessed using parallel pre- and post-test forms. Usability and workload were measured using the System Usability Scale (SUS) and two NASA Task Load Index (NASA-TLX) items. RESULTS: Overall SCT scores changed from 5.65 +/- 4.73 to 6.05 +/- 4.48 (mean change = 0.40; 95% CI: -0.41 to 1.21; p = 0.33; Cohen's d = 0.059). The UTI case showed a statistically significant domain-specific improvement (mean change = 0.58; p = 0.003; Cohen's d = 0.18), which falls below the conventional small-effect threshold. URTI and diarrhoea cases showed no significant change. The mean SUS score was 62.4 +/- 18.7; 76.0% of learners rated platform usability as average or good, with moderate cognitive workload. CONCLUSION: A single-session rule-based DCBL intervention was feasible and acceptable in routine CBME teaching and showed a domain-specific SCT signal in the UTI case. The overall SCT change was not statistically significant and should not be interpreted as evidence of effectiveness or generalised across antibiotic-stewardship scenarios. Controlled, multisite, longitudinal studies are needed to confirm these preliminary findings.