A blended problem-based learning/case-based learning/artificial intelligence teaching model for medical laboratory technology interns: a quasi-experimental study

INTRODUCTION: The 1-year clinical practicum in China's 4-year medical laboratory technology (MLT) program often fails to bridge the gap between theoretical knowledge and clinical practice. This study evaluated the effect of a blended learning model that integrated problem-based learning (PBL), case-based learning (CBL), and artificial intelligence (AI) on clinical training outcomes among MLT interns. METHODS: A total of 77 MLT interns (August 2024-April 2026) were assigned to a control group (traditional lecture-based teaching, n = 38) or an intervention group (blended PBL/CBL/AI teaching, n = 39). Objective outcomes were measured by phased theoretical and practical skills tests; subjective outcomes were collected through questionnaires. RESULTS: No baseline differences were found between groups (all P > .05). The intervention group scored statistically significantly higher in theoretical knowledge (mean [SD], 77.15 [8.51] vs 71.55 [8.12]; P = .004) and practical skills (mean [SD], 70.38 [12.27] vs. 64.08 [9.58]; P = .02) and reported higher satisfaction across all 12 teaching dimensions (P < .05). In AI-integrated teaching, the intervention group showed higher satisfaction in 5 of 6 dimensions, particularly in ease of use (P < .001), except for question-posing ability (P = .40). DISCUSSION: The blended PBL/CBL/AI internship model substantially enhanced theoretical knowledge, practical skills, and student satisfaction. Despite the limitations of its single-center design and small sample size, this model provides a valuable reference for internship reform.