Evaluation of DeepSeek ‐Generated Biochemistry Clinical Cases for Teaching Purpose
Biochemistry and Molecular Biology Education · 2026-07 · 54 (4) · 397-407
DOI: 10.1002/bmb.70063 ↗At a glance
Journal article in Biochemistry and Molecular Biology Education, published online on 2026-06-11. Written by Shuai Tan and 7 co-authors. Institution: Department of Endocrinology Children's Hospital of Chongqing Medical University, National Clinical Research Center for Child Health and Disorders, Ch…. Major MEDLINE topics: Biochemistry, Teaching, Artificial Intelligence. 25 references. The full text is freely available in PubMed Central. Funded by: National First-Class Undergraduate Course Construction Project, 2024 Teaching Reform Research Foundation of Chengdu Medical College (Key Project), Natural Science Foundation of Chengdu Medical College.
Abstract (original language)
To overcome limitations in traditional case‐based teaching, this study developed an AI‐driven workflow using DeepSeek to generate contemporary, interdisciplinary clinical biochemistry cases. Through human‐AI collaboration, eight structured cases covering key topics such as carbohydrate and lipid metabolism were created, each including a clinical description, molecular mechanisms, and Q&A, followed by instructor review. Fifteen medical students and 15 instructors evaluated the cases using a 5‐point Likert scale across multiple dimensions, while student performance was compared between a group using AI‐generated cases and a control group. The AI generated each case in 10–15 min, significantly faster than manual development. Cases presented a logical progression from molecular mechanism to clinical management and incorporated recent advances such as CRISPR and PCSK9 inhibitors. Content integration received the highest ratings, though instructors scored pedagogical applicability lower. Error analysis indicated that AI excelled in maintaining logical consistency, whereas human reviewers enhanced precision in clinical details. Students who used the AI‐generated cases achieved significantly higher examination scores than the control group ( p < 0.05). In conclusion, DeepSeek‐generated cases are efficient, interdisciplinary, and innovative. Human review remains essential for ensuring clinical rigor, particularly in nuanced scenarios. This collaborative approach enhances both the efficiency of case development and the educational quality of biochemistry teaching materials.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Endocrinology Children's Hospital of Chongqing Medical University, National Clinical Research Center for Child Health and Disorders, Chongqing, China.
- School of Finance and Accounting, Chengdu Jincheng College, Chengdu, China.
- School of Biosciences and Technology, Sichuan Higher Education Institute Key Laboratory of Major Disease Target Discovery and Protein Drug Development, Chengdu Medical College, Chengdu, China.
- Teaching Center of General Courses, Chengdu Medical College, Chengdu, China.
- School of Pharmacy, Key Laboratory of Sichuan Province for Specific Structure of Small Molecule Drugs, Chengdu Medical College, Chengdu, China.
ORCID profiles: Shuai Tan, Kun Zhang, Yiran Sun, Quekun Peng
Funding
- National First-Class Undergraduate Course Construction Project
- 2024 Teaching Reform Research Foundation of Chengdu Medical College (Key Project)
- Natural Science Foundation of Chengdu Medical College
Cite
APA
Tan, S., Ni, S., Zhang, K., Yang, Y., Tan, H., Li, L., Sun, Y., & Peng, Q. (2026). Evaluation of DeepSeek ‐Generated Biochemistry Clinical Cases for Teaching Purpose. Biochemistry and Molecular Biology Education, 54(4), 397-407. https://doi.org/10.1002/bmb.70063
Vancouver
Tan S, Ni S, Zhang K, Yang Y, Tan H, Li L, et al. Evaluation of DeepSeek ‐Generated Biochemistry Clinical Cases for Teaching Purpose. Biochemistry and Molecular Biology Education. 2026;54(4):397-407. doi:10.1002/bmb.70063
BibTeX
@article{Tan2026,
author = {Tan, Shuai and Ni, Shijie and Zhang, Kun and Yang, Yuhan and Tan, Hao and Li, Liang and Sun, Yiran and Peng, Quekun},
title = {Evaluation of DeepSeek ‐Generated Biochemistry Clinical Cases for Teaching Purpose},
journal = {Biochemistry and Molecular Biology Education},
year = {2026},
volume = {54},
number = {4},
pages = {397--407},
doi = {10.1002/bmb.70063}
}
EUVIMED