Answers are grounded in this paper and cite their sources.
Driven by the dual forces of educational digitalization and smart healthcare advancement, this study addresses critical shortcomings in the “Virology Laboratory Testing” course—such as outdated content, rigid pedagogical approaches, insufficient practical training, and inadequate integration of artificial intelligence (AI). We propose an AI-driven instructional model structured around four core components: knowledge graphs, digital‑intelligent scenarios, personalized learning pathways, and multi‑modal assessment. By revamping the curriculum, innovating digital‑smart teaching environments, tailoring individual learning trajectories, and reforming evaluation mechanisms, the model was implemented and evaluated through the “Viral Nucleic Acid Detection Technology” module. In this non-randomized controlled study using two intact administrative classes, students in the experimental class attained significantly higher final theoretical scores (89.7 ± 7.5) compared to the control group (78.3 ± 8.8, t (58) = 5.40, p < 0.001, Cohen’s d = 1.39). Furthermore, the experimental group demonstrated a virtual practice qualification rate 23.4% points higher than that of the control group (96.7% vs. 73.3%) and 90% (27/30) of experimental-group students attained proficiency in AI-assisted testing tasks, a competency domain not addressed by the control curriculum. The findings indicate that students in the experimental group demonstrated higher observed theoretical examination scores and practical assessment performance than those in the control group. These findings suggest that implementation of the integrated instructional model was associated with favorable learning outcomes. However, the non-randomized design and bundled nature of the intervention preclude definitive causal attribution. Trial registration Chinese Clinical Trial Registry ChiCTR2600129253, retrospectively registered; this was a non-randomized educational study using intact administrative classes.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: