ArticleJournal of the Chinese Medical Association : JCMA2024
ChatGPT's innovative application in blood morphology recognition.
Article in Journal of the Chinese Medical Association : JCMA, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 7 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
7 citing papers in PubMed, 19 citations in OpenAlex.
- Artificial intelligence-enabled cytopathological interpretation of fluorescence microscopy images via a multimodal large language model.Quantitative biology (Beijing, China) · 2026Article
- Article
- Pulmonary and Immune Dysfunction in Pediatric Long COVID: A Case Study Evaluating the Utility of ChatGPT-4 for Analyzing Scientific Articles.Journal of clinical medicine · 2025Review
- Areas of research focus and trends in the research on the application of AIGC in healthcare.Journal of health, population, and nutrition · 2025Article
- Integrating precision health with multidomain interventions to advance strategies for healthy aging.The journal of nutrition, health & aging · 2024Article
- Applications of Large Language Models in Pathology.Bioengineering (Basel, Switzerland) · 2024Review
- Assessing the accuracy and clinical utility of GPT-4O in abnormal blood cell morphology recognition.Digital healthArticle
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors at 3 institutions in 1 country.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundRecently, the rapid advancement in generative artificial intelligence (AI) technology, such as ChatGPT-4, has sparked discussions, particularly in image recognition. Accurate results are critical for hematological diagnosis, particularly for blood morphology identification. Despite advanced hematology analyzers, reliance on professional hematopathologists for manual identification remains in cases of abnormal or rare conditions, a process prone to human subjectivity and potential errors. Consequently, this study aimed to investigate the potential of ChatGPT-4 to assist with blood morphology identification.
methodsWe conducted a retrospective study using blood images obtained from the American Society of Hematology (ASH). These images comprised a range of normal and abnormal morphologies. Each sample was analyzed by expert technicians (control group) and classified using ChatGPT-4 (test group).
resultsPreliminary results showed that ChatGPT-4 could identify normal blood cells with an accuracy of 88%, exceeding the accuracy of identifying abnormal blood cells at a rate of 54%. Regarding identifying abnormal cells, the accuracy of ChatGPT-4 was slightly higher than that of the manual method, which was 49.5%.
conclusionThis study shows that although generative AI shows the potential for blood type identification, it has not yet reached the point where it can replace the professional judgment of medical staff. The results showed that ChatGPT-4 is excellent for identifying red blood cell morphology, particularly inclusion bodies. It can be used as an auxiliary tool for clinical diagnosis. However, the overall recognition accuracy must be further improved. Our study produced innovative results in this field, establishing a foundation for future studies and highlighting the potential of generative AI in aiding blood morphology recognition. Future research should focus on enhancing the effectiveness of AI to improve overall standards of medical care.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.