Analysis of the Application Effect of an AI-Powered Personalized Adaptive Learning Model in Standardized Residency Training for Tumor Metastasis
Objective: To explore the application effect of an AI-powered personalized adaptive learning model in the standardized residency training (SRT) teaching of tumor metastasis. Methods: A total of 62 SRT trainees rotating through the Department of Medical Oncology in the hospital from December 2024 to December 2025 were selected and divided into a control group and an observation group using a random number table method, with 31 trainees in each group. The control group received traditional SRT teaching, while the observation group was provided with an AI-powered personalized adaptive learning platform in addition to traditional teaching. The platform automatically pushed stratified resources based on trainees’ learning profiles, conducted simulated case training, and dynamically adjusted learning paths. After the 4-week training, the two groups’ Objective Structured Clinical Examination (OSCE) scores, delayed test scores in the 4th week post-training, knowledge retention rates, and self-directed learning behavior indicators were compared. Results: The observation group’s scores in each OSCE station and total score, delayed test scores, knowledge retention rate, weekly average self-directed learning duration, learning task completion rate, and error correction rate were all significantly higher than those of the control group (all P < 0.05). Conclusion: The AI-powered personalized adaptive learning model helps bridge the individual differences among SRT trainees in the specialized study of tumor metastasis, enhances comprehensive clinical capabilities, delays knowledge forgetting, and improves self-directed learning behaviors. It can serve as a feasible path for the digital teaching reform of oncology specialized residency training.
[1] Zhu CT, Li L, Li ZQ, et al., 2025, Clinical Practice Guidelines for Intraoperative Autotransfusion in Patients with Malignant Tumors. Chinese Journal of Blood Transfusion, 38(2): 149–167.
[2] Wang H, Wang Y, Shen N, et al., 2024, Application of Artificial Intelligence Teaching Case Database in Clinical Thinking Training of Resident Physicians. Hospital Management Forum, 41(1): 60–63.
[3] Zhou YK, Liu P, Liu SJ, et al., 2026, Exploration on the Application of Generative Artificial Intelligence in the Standardized Residency Training Examination of Critical Care Medicine. Medical Journal of Peking Union Medical College, 17(1): 286–291.
[4] Zhou YK, Sun J, Liu SJ, et al., 2025, Application and Challenges of Generative Artificial Intelligence in Theoretical and Case Analysis Examinations for Resident Physicians. Medical Journal of Peking Union Medical College, 2025(16): 5.
[5] Yin FX, Xu R, Xie Q, et al., 2024, Application of Flipped Classroom Combined with MDT Teaching Model in Standardized Residency Training of Breast Cancer. Chinese Journal of General Practice, 22(8): 1420–1423.
[6] Li JS, Ma LY, Lan QY, et al., 2024, Three-station OSCE Skill Assessment for Standardized Residency Training in Radiation Oncology. Chinese Journal of Radiation Oncology, 33(11): 1064–1069.
[7] Jiang ZH, Feng SC, Wang WM, 2024, Practical Exploration of Generative Large Language Models in the Construction of Medical Examination Question Banks. Chinese Medical Education Journal, 44(8): 561–569.
[8] Xie WJ, Wang ZY, 2025, Application and Challenges of Artificial Intelligence in Postgraduate Medical Education. Chinese Medical Education Journal, 45(3): 187–193.
[9] Zhang RY, Zhou YB, Peng YC, 2025, Analysis of the Collaborative Governance Path of Artificial Intelligence Empowering Medical Education. Chinese Medical Education Journal, 45(7): 496–501.
