Peng Jingyue, Zhang Hongying, Tu Xiaohua, Zhang Xuemei, Wu Qiuhan, Wang Yijun, Xiao Deng
Department of Rehabilitation Medicine, The Affiliated Rehabilitation Hospital of Chongqing Medical University, No. 50 Xiexiao Road, Chongqing, 400050, China.
Department of Science and Education, The Affiliated Rehabilitation Hospital of Chongqing Medical University, No. 50 Xiexiao Road, Chongqing, 400050, China.
BMC Med Educ. 2025 Aug 27;25(1):1207. doi: 10.1186/s12909-025-07770-y.
In recent years, artificial intelligence (AI) has been adopted as an innovative teaching method. However, no studies have comprehensively evaluated the effectiveness of AI in the context of medical education in China. This study aimed to assess the effectiveness of AI-assisted teaching methods versus traditional teaching methods regarding their impact on medical education outcomes in China.
We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and retrieved studies published in the Web of Science, PubMed, EMBASE, the Cochrane Library, the Chinese National Knowledge Infrastructure, VIP Database and the Chinese Wanfang Database from January 2015 to December 2024. The standardized mean difference (SMD) with a 95% confidence interval (CI) was calculated, and heterogeneity was evaluated using statistics, with subsequent meta-regression analysis employed to identify the contributing factors.
Twelve studies involving 824 medical students were included. All studies provided usable data on examination scores. The pooled analysis revealed a significant difference in favor of AI-assisted teaching compared with traditional teaching methods (SMD = 2.06, 95% CI: 1.35–2.76). In addition, AI-assisted teaching significantly increased student satisfaction in eight studies (OR = 5.80, 95% CI: 3.30–10.18). Meta-regression analysis indicated that randomization, study duration and type of AI technologies were the primary factors contributing to heterogeneity.
The AI-assisted approach to medical education in China was shown to be more effective than traditional teaching methods in improving examination scores and student satisfaction, offering substantial evidence for the adoption of AI in medical education. These results highlighted the potential advantages of incorporating AI into medical teaching practices. Future research should focus on investigating the effectiveness of AI-assisted teaching across diverse educational systems and applications.
The online version contains supplementary material available at 10.1186/s12909-025-07770-y.
近年来，人工智能（AI）已被用作一种创新的教学方法。然而，尚无研究全面评估人工智能在中国医学教育背景下的有效性。本研究旨在评估人工智能辅助教学方法与传统教学方法对中国医学教育成果的影响。
我们遵循系统评价和Meta分析的首选报告项目（PRISMA）指南，检索了2015年1月至2024年12月在Web of Science、PubMed、EMBASE、Cochrane图书馆、中国知网、维普数据库和中国万方数据库上发表的研究。计算标准化平均差（SMD）及其95%置信区间（CI），并使用统计学方法评估异质性，随后进行Meta回归分析以确定影响因素。
纳入了12项涉及824名医学生的研究。所有研究均提供了关于考试成绩的可用数据。汇总分析显示，与传统教学方法相比，人工智能辅助教学有显著差异（SMD = 2.06，95% CI：1.35 - 2.76）。此外，在八项研究中，人工智能辅助教学显著提高了学生满意度（OR = 5.80，95% CI：3.30 - 10.18）。Meta回归分析表明，随机化、研究持续时间和人工智能技术类型是导致异质性的主要因素。
在中国医学教育中，人工智能辅助教学方法在提高考试成绩和学生满意度方面比传统教学方法更有效，为在医学教育中采用人工智能提供了充分证据。这些结果突出了将人工智能纳入医学教学实践的潜在优势。未来的研究应侧重于调查人工智能辅助教学在不同教育系统和应用中的有效性。
在线版本包含可在10.1186/s12909-025-07770-y获取的补充材料。
