EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Clinical Workflow Efficiency in Flow Cytometry Reporting with LLMs

Thomas E Tavolara, Jake Meyer, Christopher Garcia, Attila Kumanovics, Patrick Vanderboom

Journal of Clinical Immunology · 24.03.2026 · 46 (1)

DOI: 10.1007/s10875-026-02006-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Immunology, online erschienen am 24.03.2026. Verfasst von Thomas E Tavolara und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, USA. tavolara.thomas@mayo.edu. Hauptthemen laut MEDLINE: Flow Cytometry, Workflow. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mayo Clinic Midwest Clinical Practice Committee.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate interpretation of clinical test results is essential for diagnosing and managing complex immunological disorders. We explored the potential of large language models (LLMs) to automate interpretative reports for immunodeficiency and immune competence assessment via quantitative lymphocyte profiling and B-cell subset phenotyping (QLP/BSP).

Methods

An LLM was fine-tuned using parameter-efficient techniques on a dataset consisting of immunophenotyping test results and corresponding interpretive reports. Model performance was compared against a retrieval-based method and expert pathologist reports. A novel automated evaluation framework assessed both the accuracy of cell population comments and the clinical relevance of generated interpretations. A custom application was built to simulate clinical workflows and measure the impact on pathologist efficiency and accuracy.

Results

Fine-tuned LLMs achieved accuracy comparable to expert pathologists in identifying and commenting on abnormal cell type counts and frequencies, in comparison the retrieval-based method exhibited substantial error rates. There was no significant difference between the rate at which abnormalities for cell subtypes were commented on between the LLMs and pathologists. More importantly, LLMs significantly reduced the time required for a single pathologist to finalize reports with a mean reduction in time of 29%.

Conclusion

Our results suggest that LLMs hold promise for enhancing efficiency and consistency in the clinical laboratory setting. By automating aspects of interpretive reporting, LLMs can potentially reduce pathologist workload and improve the turnaround time for critical diagnostic information, while requiring expert pathologist oversight.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Flow CytometryWorkflowHumansLarge Language ModelsImmunophenotyping

Stichwörter der Autor:innen

Clinical Workflow EfficiencyFlow Cytometry ReportingImmunophenotypingInterpretive Reporting AutomationLarge Language Models (LLMs)Primary Immunodeficiency Diagnostics

Autor:innen und Institutionen

  • Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, USA. tavolara.thomas@mayo.edu.
  • Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, USA.

Förderung

  • Mayo Clinic Midwest Clinical Practice Committee

Zitieren

APA

Tavolara, T. E., Meyer, J., Garcia, C., Kumanovics, A., & Vanderboom, P. (2026). Enhancing Clinical Workflow Efficiency in Flow Cytometry Reporting with LLMs. Journal of Clinical Immunology, 46(1). https://doi.org/10.1007/s10875-026-02006-0

Vancouver

Tavolara TE, Meyer J, Garcia C, Kumanovics A, Vanderboom P. Enhancing Clinical Workflow Efficiency in Flow Cytometry Reporting with LLMs. Journal of Clinical Immunology. 2026;46(1). doi:10.1007/s10875-026-02006-0

BibTeX
@article{Tavolara2026,
  author = {Tavolara, Thomas E and Meyer, Jake and Garcia, Christopher and Kumanovics, Attila and Vanderboom, Patrick},
  title = {Enhancing Clinical Workflow Efficiency in Flow Cytometry Reporting with LLMs},
  journal = {Journal of Clinical Immunology},
  year = {2026},
  volume = {46},
  number = {1},
  doi = {10.1007/s10875-026-02006-0}
}
Kostenlos starten →