The study investigated the integration of large-scale language models (LLM) into a medical cell biology laboratory course for first-year medical students in China to improve their bioethical competence. They divided students from three majors into five groups and compared four domestic LLMs: DeepSeek, Doubao, KIMI and ChatGLM. The courses were conducted in three phases: instructor-led introduction, experiential practice with the LLM focused on procedural, conceptual and psychological challenges, and assessment by questionnaires and laboratory reports. Questionnaires from 86 students showed high satisfaction; for Medical Imaging Technology students, DeepSeek (mean 4.3, SD 0.7) and KIMI (mean 4.3, SD 0.8) were rated significantly higher than Doubao (mean 3.9, SD 0.7) and ChatGLM (mean 3.3, SD 0.6). KIMI was preferred by students of health surveillance and quarantine (mean 4.4, SD 0.5) and medical prevention (mean 4.5, SD 0.5). Students expressed concerns about academic inaccuracies, bias and the impact on independent thinking. The study concludes that KIMI and DeepSeek in particular support the integration of bioethics into medical laboratory courses and help shape ethically competent future physicians.