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 Concept Videos

Flow Cytometry01:23

Flow Cytometry

The development of flow cytometry techniques began in 1934 with initial attempts by Andrew Moldavan, a bacteriologist who counted the cells in a flowing capillary system. Moldavan pumped cells through a capillary tube focused under a microscope for visualization. The invention of photometry allowed the measurement of differentially-stained cells, and Louis Kamentsky developed the first multiparameter flow cytometer in 1965 to identify and count the cancer cells in cervical tissue specimens.
In...

You might also read

Related Articles

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

Sort by
Same author

Why and How to Monitor Deployed AI Systems in Health Care.

NEJM catalyst innovations in care delivery·2026
Same author

Challenges in AI Based Tumor Board Case Summarization and Recommendations.

Research square·2026
Same author

Physician-Reported Safety Outcomes of AI-Generated Hospital Course Summaries.

JAMA network open·2026
Same author

Use of a large language model integrated within the electronic medical record for the evaluation of surgical site infections - Northern California, 2025.

Infection control and hospital epidemiology·2026
Same author

MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same author

DHODH as a targetable metabolic Achilles' heel for chemotherapy-resistant B-ALL.

Blood·2026

Related Experiment Video

Updated: Jul 12, 2026

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data
05:12

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data

Published on: January 16, 2019

Automating clinical history extraction for flow cytometry panel selection using an EHR-integrated large language

Rebecca Rojansky1, Timothy Keyes2, Jean Oak1

  • 1Department of Pathology, Stanford University School of Medicine, Stanford, California, USA.

Cytometry. Part B, Clinical Cytometry
|July 10, 2026
PubMed
Summary

Large language models (LLMs) can automate clinical history extraction for flow cytometry panel selection, significantly reducing manual review time. However, direct panel selection accuracy requires further refinement for clinical integration.

Keywords:
ChatGPTLLMautomationflow cytometry

More Related Videos

A Semi-automated Approach to Preparing Antibody Cocktails for Immunophenotypic Analysis of Human Peripheral Blood
08:17

A Semi-automated Approach to Preparing Antibody Cocktails for Immunophenotypic Analysis of Human Peripheral Blood

Published on: February 8, 2016

Related Experiment Videos

Last Updated: Jul 12, 2026

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data
05:12

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data

Published on: January 16, 2019

A Semi-automated Approach to Preparing Antibody Cocktails for Immunophenotypic Analysis of Human Peripheral Blood
08:17

A Semi-automated Approach to Preparing Antibody Cocktails for Immunophenotypic Analysis of Human Peripheral Blood

Published on: February 8, 2016

Area of Science:

  • Hematology
  • Clinical Pathology
  • Artificial Intelligence in Medicine

Background:

  • Accurate flow cytometry immunophenotyping for hematologic malignancies relies on comprehensive clinical context often fragmented in electronic health records (EHRs).
  • Current manual review of clinical documentation by clinical laboratory scientists (CLS) for antibody panel selection is time-intensive.

Purpose of the Study:

  • To evaluate the performance of ChatEHR, an EHR-integrated large language model (LLM), in automating clinical history extraction and supporting flow cytometry panel selection.
  • To compare the LLM-driven workflow with the existing CLS-driven workflow for accuracy and efficiency.

Main Methods:

  • ChatEHR was evaluated on 100 cases for its ability to extract and categorize prior hematologic diagnoses and assist in flow cytometry panel selection.
  • Performance was benchmarked against manual CLS review, with hematopathologist-reviewed panel selections serving as the reference standard.
  • Processing times and error categories were analyzed for both workflows.

Main Results:

  • ChatEHR demonstrated comparable accuracy to CLS in extracting prior hematologic diagnoses (78% vs. 78%) and significantly reduced processing time (20.3s vs. 41s).
  • Direct panel selection accuracy for ChatEHR was lower (47% vs. 78%), with primary errors in decision-tree logic, diagnostic conflation, and data interpretation.
  • An estimated 120 staff hours could be saved annually by automating clinical history extraction.

Conclusions:

  • LLM-based clinical history extraction shows promise for reducing manual chart review burden in flow cytometry workflows.
  • A hybrid approach integrating LLM extraction with rules-based algorithms offers a practical solution for scalable automation while maintaining diagnostic reliability.
  • Hematopathologist oversight remains crucial for ensuring appropriate panel selection and diagnostic accuracy.