Objective:To assess the professional knowledge proficiency of mainstream large language models (LLMs) in medical laboratory education and to explore their potential as educational aids for medical laboratory technology students.Methods:A comprehensive evaluation was conducted using 400 authentic questions from the 2023 Chinese National Clinical Medical Laboratory Technician Qualification Examination. Five LLMs (Copilot, Grok, Yuanbao, Doubao, and Kimi) were tested through two-round interactions using zero-shot prompting and interaction-optimized prompting strategies. The accuracy of answers and the quality of generated content were evaluated. Performance disparities were analyzed using Cochran's Q test. Content quality was scored through the CLEAR framework (completeness, lack of false information, evidence-based reasoning, appropriateness, relevance).Results:In the first-round test, Doubao achieved the highest overall accuracy rate (375/400). The overall accuracy rates of Doubao and Yuanbao significantly outperformed Copilot and Kimi ( P<0.001). After the second-round interactive optimization, the accuracy rate of Kimi significantly improved ( P<0.05), whereas other LLMs showed slight improvements ( P>0.05). Doubao still had the highest overall accuracy rate (380/400). The overall accuracy rates of Doubao and Yuanbao significantly outperformed Copilot ( P<0.005). Evaluation based on the CLEAR framework revealed that Yuanbao, Doubao, and Kimi significantly outperformed foreign models in the dimensions of evidence-based reasoning ( P<0.003) and completeness ( P<0.05), demonstrating standardized citation of authoritative evidence and superior content quality. Conclusions:The tested LLMs possess extensive medical laboratory knowledge. The accuracy of their answers and the quality of the generated content can be improved through single-question input, specifying evidence requirements, and enabling advanced reasoning functions. Domestic LLMs are comparable to foreign LLMs in terms of accuracy, and have significant advantages in the dimensions of evidence-based reasoning and completeness. LLMs can serve as auxiliary tools for learning professional knowledge in medical laboratory technology.

Objective:To assess the professional knowledge proficiency of mainstream large language models (LLMs) in medical laboratory education and to explore their potential as educational aids for medical laboratory technology students.Methods:A comprehensive evaluation was conducted using 400 authentic questions from the 2023 Chinese National Clinical Medical Laboratory Technician Qualification Examination. Five LLMs (Copilot, Grok, Yuanbao, Doubao, and Kimi) were tested through two-round interactions using zero-shot prompting and interaction-optimized prompting strategies. The accuracy of answers and the quality of generated content were evaluated. Performance disparities were analyzed using Cochran's Q test. Content quality was scored through the CLEAR framework (completeness, lack of false information, evidence-based reasoning, appropriateness, relevance).Results:In the first-round test, Doubao achieved the highest overall accuracy rate (375/400). The overall accuracy rates of Doubao and Yuanbao significantly outperformed Copilot and Kimi ( P<0.001). After the second-round interactive optimization, the accuracy rate of Kimi significantly improved ( P<0.05), whereas other LLMs showed slight improvements ( P>0.05). Doubao still had the highest overall accuracy rate (380/400). The overall accuracy rates of Doubao and Yuanbao significantly outperformed Copilot ( P<0.005). Evaluation based on the CLEAR framework revealed that Yuanbao, Doubao, and Kimi significantly outperformed foreign models in the dimensions of evidence-based reasoning ( P<0.003) and completeness ( P<0.05), demonstrating standardized citation of authoritative evidence and superior content quality. Conclusions:The tested LLMs possess extensive medical laboratory knowledge. The accuracy of their answers and the quality of the generated content can be improved through single-question input, specifying evidence requirements, and enabling advanced reasoning functions. Domestic LLMs are comparable to foreign LLMs in terms of accuracy, and have significant advantages in the dimensions of evidence-based reasoning and completeness. LLMs can serve as auxiliary tools for learning professional knowledge in medical laboratory technology.

Objective:To evaluate the effectiveness of the course of Laboratory Medicine and Clinical Sciences in the Laboratory Medicine Faculty of Sun Yat-sen University. Methods:Twenty-four undergraduate students in Batch 2016 of Medical Laboratory Faculty were divided into small groups (4-6 students per group). They learned each case in groups before class. In the first session of each class, the case-based study (CBS) tutor would randomly assign case-related questions to the students. Students were required to present their answers in class. The CBS tutor would guide the students to discuss the case further. In the second session, a lecture associated with the case would be given by a special subject lecturer. After the course, students, tutors and lecturers were given questionnaires and were randomly interviewed to comprehensively understand the course's effectiveness. SPSS 19.0 was used for statistics.Results:Most case discussion tutors agreed that they could guide students to discuss clinical cases well in class and give comments according to students' presentations (93.75%, 15/16). Most of the lecturers agreed that they could well guide students to think about the relationship between laboratory and clinical diagnosis and treatment in class (91.67%, 11/12). Both teachers and students had very positive evaluations of the learning mode, learning content, inspiration to students, and teachers' ability of this course. All the teachers and students agreed that the learning mode of combining CBS with special subject lecture was more helpful for the students to systematically learn medical knowledge compared with a CBS session alone or a lecture alone.Conclusion:The course, Laboratory Medicine and Clinical Sciences, which combines the CBS with the traditional lecture mode, integrates the advantages of the two learning modes. It not only stimulates students' enthusiasm for active learning, deepens clinical knowledge memory, and builds a clinical thinking model, but also enriches the teaching modes of medical laboratory education.