Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Haematological validation of a computer-based bone marrow reporting system

D T Nguyen1, L W Diamond, J D Cavenagh

  • 1Department of Haematology, St Bartholomew's Hospital, London, United Kingdom.

Journal of Clinical Pathology
|May 1, 1997
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Working memory demands modulate memory brain state engagement.

bioRxiv : the preprint server for biology·2026
Same author

Results from the T2K Experiment on Neutrino Mixing Including a New Far Detector μ-like Sample.

Physical review letters·2026
Same author

Morphological and molecular characterisations of <i>Aphelenchoides vinhphucensis</i> sp. n. associated with rice from Vietnam.

Journal of helminthology·2025
Same author

First Differential Measurement of the Single π^{+} Production Cross Section in Neutrino Neutral-Current Scattering.

Physical review letters·2025
Same author

First Measurement of the Electron-Neutrino Charged-Current Pion Production Cross Section on Carbon with the T2K Near Detector.

Physical review letters·2025
Same author

Trauma-predictive brain network connectivity adaptively responds to mild acute stress.

Proceedings of the National Academy of Sciences of the United States of America·2025

Professor Belmonte, a knowledge-based system, generated bone marrow reports equivalent to human experts. This AI system is safe and effective for assisting haematologists in creating high-quality reports.

Area of Science:

  • Medical Informatics
  • Hematology
  • Artificial Intelligence in Medicine

Background:

  • Bone marrow reporting is a critical diagnostic process in hematology.
  • Traditional bone marrow reporting relies on expert interpretation, which can be time-consuming and subject to variability.
  • The development of automated systems aims to improve efficiency and consistency in medical reporting.

Purpose of the Study:

  • To formally evaluate the safety and effectiveness of Professor Belmonte, a knowledge-based system for bone marrow reporting.
  • To compare the quality of AI-generated reports against original reports authored by hematologists.

Main Methods:

  • A knowledge-based system, Professor Belmonte, generated reports for 785 unselected bone marrow cases.
  • Three independent hematologists (consultant, senior registrar, junior registrar) evaluated the AI-generated reports.

Related Experiment Videos

  • Reports were graded based on informativeness, equivalence to original reports, or deficiencies.

    • Main Results:

    • All 785 AI-generated reports received at least satisfactory or better ratings from the evaluators.
    • A significant number of reports were rated as equivalent to or better than original reports by all three hematologists.
    • Minor discrepancies in unsatisfactory ratings were noted, but overall quality was high.

    Conclusions:

    • Professor Belmonte demonstrates comparable accuracy to human experts in generating bone marrow reports.
    • The system's knowledge base, reasoning capabilities, and software function are safe and effective.
    • Professor Belmonte serves as a valuable tool to assist hematologists in producing high-quality bone marrow reports.