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

A Fentanyl-Responsive Microneedle Patch for Harm Reduction.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Albuminuria, but not eGFR, tracks diabetic retinopathy severity and retinal ischemia: population-based discovery, clinical replication, and OCTA evidence.

Frontiers in endocrinology·2026
Same author

Adjunctive ab-interno goniotomy in chronic angle-closure glaucoma: a retrospective proof-of-concept pilot study using doubly robust learning.

Frontiers in ophthalmology·2026
Same author

Unveiling the pharmacological basis of Rhodiola crenulata for atopic dermatitis: A multi-model approach combining zebrafish, mouse studies, and intelligent computational analysis.

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

Cardiac arrest in an adolescent following an overdose of antidepressants comprising sertraline, quetiapine fumarate, and lamotrigine: Case report.

International journal of clinical pharmacology and therapeutics·2026
Same author

Span-Morphing Wing Using Multistable Honeycomb Metamaterial Structures.

Materials (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jan 9, 2026

Microscopy-based Assays for High-throughput Screening of Host Factors Involved in Brucella Infection of Hela Cells
15:29

Microscopy-based Assays for High-throughput Screening of Host Factors Involved in Brucella Infection of Hela Cells

Published on: August 5, 2016

8.6K

Machine learning-based prediction model for chronic brucellosis: a multi-feature approach using clinical and

Rong Wang1,2, Bin Niu1,2, Chenming Zhang1,3

  • 1Department of Infectious Diseases, The First Hospital of Shanxi Medical University, Taiyuan, China.

Frontiers in Cellular and Infection Microbiology
|December 5, 2025
PubMed
Summary

Machine learning models can predict chronic brucellosis progression using routine data. The random forest model showed the best performance, aiding early risk stratification for human brucellosis (HB).

Keywords:
brucellosischronic progressionmachine learningrisk predictionrisk stratification

More Related Videos

Diagnosis and Surgical Treatment of Human Brucellar Spondylodiscitis
06:23

Diagnosis and Surgical Treatment of Human Brucellar Spondylodiscitis

Published on: May 23, 2021

5.3K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

Related Experiment Videos

Last Updated: Jan 9, 2026

Microscopy-based Assays for High-throughput Screening of Host Factors Involved in Brucella Infection of Hela Cells
15:29

Microscopy-based Assays for High-throughput Screening of Host Factors Involved in Brucella Infection of Hela Cells

Published on: August 5, 2016

8.6K
Diagnosis and Surgical Treatment of Human Brucellar Spondylodiscitis
06:23

Diagnosis and Surgical Treatment of Human Brucellar Spondylodiscitis

Published on: May 23, 2021

5.3K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

Area of Science:

  • Infectious Diseases
  • Machine Learning in Medicine
  • Clinical Prediction Models

Background:

  • Chronic progression affects nearly one-third of human brucellosis (HB) patients, leading to long-term disability.
  • Lack of reliable early prediction tools hinders timely risk stratification and individualized management of HB.
  • This study addresses the need for predictive tools using routinely available clinical and laboratory data.

Purpose of the Study:

  • To develop and validate machine learning (ML) models for predicting chronic progression in human brucellosis.
  • To identify key clinical and laboratory predictors for chronic brucellosis development.
  • To create a web-based tool for early risk stratification of chronic brucellosis.

Main Methods:

  • Retrospective analysis of 555 confirmed brucellosis patients' clinical and laboratory data.
  • Feature selection using Boruta and recursive feature elimination.
  • Construction and evaluation of six supervised ML models (RF, LightGBM, XGBoost, LR, MLP, SVM) using discrimination, calibration, and clinical utility metrics. SHapley Additive exPlanations (SHAP) for interpretability.

Main Results:

  • 25.9% of patients progressed to chronic brucellosis.
  • Chronic cases showed distinct biochemical profiles (e.g., lower ALT, AST, TG; higher HDL-C, ALB, BUN, UA).
  • The Random Forest (RF) model achieved the highest AUC (0.782) and demonstrated robust performance, identifying TG, HDL-C, UA, eosinophil count, PA, ALT, BUN, and GLB as key predictors.

Conclusions:

  • The RF model, using eight routine variables, offers moderate discrimination and well-calibrated probability estimates for chronic brucellosis risk.
  • The developed tool may aid early risk stratification when integrated with clinical judgment.
  • External validation in multicenter, prospective studies is crucial to confirm the model's predictive performance.