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

Development of Machine Learning Models to Predict Candidemia in Hospitalized Adult Patients.

Kenyu Hashimoto1,2,3, Koutarou Matsumoto4, Kenta Murotani5,6

  • 1Department of Biostatistics, Graduate School of Medicine, Kurume University.

The Kurume Medical Journal
|May 17, 2026
PubMed
Summary

Related Concept Videos

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

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

Sort by
Same author

Three versus six weeks of corticosteroids for mild immune-related pneumonitis: a randomized trial.

American journal of respiratory and critical care medicine·2026
Same author

Relationships between pre-, post-, and inter-ictal psychiatric symptoms in patients with epilepsy.

PCN reports : psychiatry and clinical neurosciences·2026
Same author

PERSIST-PWI trial: Rationale and design of a multicenter randomized controlled trial comparing pulmonary vein isolation alone with pulmonary vein isolation plus posterior wall isolation using pulsed field ablation in patients with persistent atrial fibrillation.

Heart rhythm O2·2026
Same author

Nationwide Implementation of Non-Mandatory Preventive Medicine Programmes in Japanese Municipalities: A Descriptive Cross-Sectional Survey and Evidence-Practice Gap Analysis.

Research square·2026
Same author

Reply to: "Amino acid strategy in early postoperative parenteral nutrition".

JPEN. Journal of parenteral and enteral nutrition·2026
Same author

Bile-Derived Exosomal miR-196a/-196b as Diagnostic Biomarkers Associated With Tumor Progression in Biliary Tract Cancer.

Cancer science·2026

We developed machine learning models using electronic medical record data to predict candidemia, a bloodstream infection. The LASSO logistic regression model showed high accuracy, aiding early diagnosis and treatment.

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Infectious Disease Epidemiology

Background:

  • Candidemia is a serious bloodstream infection with high mortality.
  • Early diagnosis and intervention are crucial for improving patient outcomes.
  • Predictive models using electronic medical record (EMR) data can aid early detection.

Purpose of the Study:

  • To develop a generalizable machine learning model for predicting candidemia.
  • To utilize readily available electronic medical record (EMR) data for prediction.
  • To identify predictive models using information available on or before blood culture collection.

Main Methods:

  • Adult patients from Shin Koga Hospital (April 2014-March 2022) with blood cultures were included.
  • Two datasets were prepared: complete case (13 variables) and imputed full-variable (36 variables).
Keywords:
LASSO logistic regressioncandidemiadecision supportelectronic medical recordmachine learningpredictive model

Related Experiment Videos

  • Four machine learning models (XGBoost, Random Forest, LASSO logistic regression, logistic regression) were evaluated using AUROC and 5-fold cross-validation.

    • Main Results:

    • A total of 919 patients were analyzed, with 5.1% experiencing candidemia.
    • LASSO logistic regression achieved the highest performance.
    • The area under the receiver operating characteristic curve (AUROC) was 0.880 for the complete case dataset and 0.913 for the imputed dataset.

    Conclusions:

    • Two LASSO logistic regression models were developed using EMR data.
    • These models demonstrate potential for early candidemia diagnosis.
    • The models can support timely therapeutic interventions for candidemia.