Qinpeng Li,* Lili Zhan,* Xinjian Cai

Department of Clinical Laboratory Medicine, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, Guangdong, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Lili Zhan, Department of Clinical Laboratory Medicine, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Baohe Road No. 113, Longgang District, Shenzhen, Guangdong, 518116, People’s Republic of China, Email zhanlily@163.com

Background: Recent advancements in artificial intelligence (AI), particularly with large language models (LLMs), are transforming healthcare by enhancing diagnostic decision-making and clinical workflows. The application of LLMs like DeepSeek-R1 in clinical laboratory medicine demonstrates potential for improving diagnostic accuracy, supporting decision-making, and optimizing patient care.
Objective: This study evaluates the performance of DeepSeek-R1 in analyzing clinical laboratory cases and assisting with medical decision-making. The focus is on assessing its accuracy and completeness in generating diagnostic hypotheses, differential diagnoses, and diagnostic workups across diverse clinical cases.
Methods: We analyzed 100 clinical cases from Clinical Laboratory Medicine Case Studies, which includes comprehensive case histories and laboratory findings. DeepSeek-R1 was queried independently for each case three times, with three specific questions regarding diagnosis, differential diagnoses, and diagnostic tests. The outputs were assessed for accuracy and completeness by senior clinical laboratory physicians.
Results: DeepSeek-R1 achieved an overall accuracy of 72.9% (95% CI [69.9%, 75.7%]) and completeness of 73.4% (95% CI [70.5%, 76.2%]). Performance varied by question type: the highest accuracy was observed for diagnostic hypotheses (85.7%, 95% CI [81.2%, 89.2%]) and the lowest for differential diagnoses (55.0%, 95% CI [49.3%, 60.5%]). Notable variations in performance were also seen across disease categories, with the best performance observed in genetic and obstetric diagnostics (accuracy 93.1%, 95% CI [84.0%, 97.3%]; completeness 86.1%, 95% CI [76.4%, 92.3%]).
Conclusion: DeepSeek-R1 demonstrates potential for a decision-support tool in clinical laboratory medicine, particularly in generating diagnostic hypotheses and recommending diagnostic workups. However, its performance in differential diagnosis and handling specific clinical nuances remains limited. Future work should focus on expanding training data, integrating clinical ontologies, and incorporating physician feedback to improve real-world applicability. DeepSeek-R1 and the new versions under development may be promising tools for non-medical professionals and professionals in medical laboratory diagnoses.

Keywords: DeepSeek-R1, artificial intelligence, large language model, clinical decision support systems, clinical laboratory medicine