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

You might also read

Related Articles

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

Sort by
Same author

Liquid biopsy in pediatric acute lymphoblastic leukemia.

Frontiers in oncology·2026
Same author

Emergence of tet(X6) and bla<sub>IMP-45</sub> in a multidrug-resistant Pseudomonas asiatica strain isolated from chicken.

BMC microbiology·2026
Same author

Pandemic-Associated Sensitization Patterns and Burden in Chinese Children with Allergic Rhinitis: A Retrospective Phase-Stratified Study.

Journal of asthma and allergy·2026
Same author

Ginsenoside Rd attenuates renal aging and fibrosis through inhibition of angiotensin II type 1 receptor signaling.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

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

Journal of medical Internet research·2026
Same author

Macrolide Resistance of <i>Mycoplasma pneumoniae</i> Among Children in Hangzhou: A 2024-2025 Post-Pandemic Surveillance Study.

Infection and drug resistance·2026

Related Experiment Video

Updated: Sep 20, 2025

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K

Machine learning algorithms with body fluid parameters: an interpretable framework for malignant cell screening in

Xianfei Ye1, Xinfeng Zhao2, Yinyu Lou1

  • 1Department of Laboratory Medicine, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, P.R. China.

Clinical Chemistry and Laboratory Medicine
|May 29, 2025
PubMed
Summary

A new machine learning (ML) model uses routine hematology analyzer data from cerebrospinal fluid (CSF) to effectively screen for malignant cells. This approach offers a promising, accessible method for early cancer detection in CSF samples.

Keywords:
body fluidcerebrospinal fluidhigh fluorescence cellsmachine learningmalignant cells

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Detection and Monitoring of Tumor Associated Circulating DNA in Patient Biofluids
06:53

Detection and Monitoring of Tumor Associated Circulating DNA in Patient Biofluids

Published on: June 8, 2019

8.8K

Related Experiment Videos

Last Updated: Sep 20, 2025

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Detection and Monitoring of Tumor Associated Circulating DNA in Patient Biofluids
06:53

Detection and Monitoring of Tumor Associated Circulating DNA in Patient Biofluids

Published on: June 8, 2019

8.8K

Area of Science:

  • Clinical diagnostics
  • Biomedical data analysis
  • Hematology

Background:

  • Cerebrospinal fluid (CSF) analysis is crucial for diagnosing central nervous system (CNS) conditions.
  • Cytological examination of CSF for malignant cells can be labor-intensive and requires specialized expertise.
  • Hematology analyzers offer readily available body fluid parameters that may hold diagnostic value.

Purpose of the Study:

  • To develop and validate a machine learning (ML) model for screening malignant cells in CSF.
  • To leverage routine body fluid parameters from hematology analyzers for this screening purpose.
  • To assess the model's performance and generalizability through internal and external validation.

Main Methods:

  • Analysis of 643 CSF samples using the body fluid mode of a hematology analyzer.
  • Application of LASSO regression to identify predictive biomarkers from measured parameters.
  • Evaluation of six ML algorithms, with a focus on Support Vector Machine (SVM).
  • Utilizing SHapley Additive exPlanations (SHAP) for model interpretability.
  • External validation with 136 additional CSF samples.

Main Results:

  • The SVM model achieved an Area Under the Curve (AUC) of 0.899 and a sensitivity of 0.827 in internal validation.
  • Key predictors identified by SHAP analysis included high fluorescence cells and monocyte percentage.
  • Median leukocyte (WBC) and total nucleated cell (TNC) counts were significantly lower in cytology-positive samples.
  • External validation confirmed the model's generalizability with comparable performance metrics.

Conclusions:

  • An ML model was successfully developed to predict cytological outcomes in CSF using standard hematology parameters.
  • The model demonstrates robust performance and generalizability, validated on an independent dataset.
  • This approach offers a potential non-invasive screening tool for malignant cells in CSF.