Accessibility settings

This paper is in the following e-collection/theme issue:

Generative Language Models Including ChatGPT (903) Clinical Information and Decision Making (2167) Research Instruments, Questionnaires, and Tools (809) Artificial Intelligence (2482) Applications of AI (395) Foundation Models and Their Applications in AI (68)

Published on in Vol 28 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/87802, first published .
Scientist in lab coat examines DNA model on computer screen while holding test tube

Performance Evaluation of GPT-5, Grok 4, and DeepSeek R1 in Interpreting Complete Blood Count Reports for Hematologic Diseases: Retrospective Comparative Study

Performance Evaluation of GPT-5, Grok 4, and DeepSeek R1 in Interpreting Complete Blood Count Reports for Hematologic Diseases: Retrospective Comparative Study

Authors of this article:

Xianfei Ye1, 2, 3 Author Orcid Image ;   Xinglun Qi1 Author Orcid Image ;   Lina Fan1 Author Orcid Image ;   Qian Yu1 Author Orcid Image ;   Suming Zhou1 Author Orcid Image ;   Chunyun Ren1 Author Orcid Image ;   Dagan Yang1 Author Orcid Image
Article Authors Cited by Tweetations Metrics

Xianfei Ye   1, 2, 3 , MM ;   Xinglun Qi   1 , BS ;   Lina Fan   1 , BS ;   Qian Yu   1 , BMed ;   Suming Zhou   1 , BS ;   Chunyun Ren   1 , MM ;   Dagan Yang   1 , MS

1 Department of Laboratory Medicine, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China

2 Key Laboratory of Clinical In Vitro Diagnostic Techniques of Zhejiang Province, Hangzhou, China

3 Institute of Laboratory Medicine, Zhejiang University, Hangzhou, China

Corresponding Author:

  • Dagan Yang, MS
  • Department of Laboratory Medicine
  • The First Affiliated Hospital, Zhejiang University School of Medicine
  • 79 Qingchun Road
  • Hangzhou, Zhejiang
  • China
  • Phone: 86 0571-87236383
  • Email: yangdagan@zju.edu.cn