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 Video

Updated: May 22, 2026

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis
08:46

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis

Published on: August 12, 2020

Improved Prediction of Invasive Bacterial Infections in Febrile Infants Using Machine Learning.

Jared Kusma1,2, Jacob Phouthavong-Murphy1,3, Jennifer Stamp1,4

  • 1Phoenix Children's Hospital, Phoenix, Arizona.

Hospital Pediatrics
|May 20, 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

Assessment of Immunization Status Following Non-HSCT Chemotherapy-treated Pediatric Leukemia Survivors.

Journal of pediatric hematology/oncology·2026
Same author

Do Pain Scores Correlate With Vital Signs in Pediatric Patients With Migraine Headaches?

Hospital pediatrics·2026
Same author

Bronchiolitis Post Introduction of RSV Immunoprophylaxis: Shifting Patterns in Pediatric Hospitalizations.

Clinical pediatrics·2026
Same author

Health System Community Partnership to Design an Online Resource to Address Perinatal Information Needs for Black Families: Action Research Study.

JMIR pediatrics and parenting·2026
Same author

Infections following minimally invasive repair of pectus excavatum in pediatric patients: a multi-institutional retrospective cohort study of the Western Pediatric Surgery Research Consortium.

Pediatric surgery international·2026
Same author

Economic Evaluation of Tympanostomy Tube Placement.

The Laryngoscope·2026

Supervised learning models (SLMs) show promise for identifying invasive bacterial infections (IBIs) in febrile infants. These AI models offer comparable sensitivity and significantly higher specificity than current guidelines.

Area of Science:

  • Pediatric infectious diseases
  • Machine learning in healthcare
  • Clinical decision support systems

Background:

  • Current guidelines for febrile infants (8-60 days) assessing invasive bacterial infections (IBIs) have variable performance.
  • Risk stratification relies on clinical appearance, age, and lab results.

Purpose of the Study:

  • Develop and validate five supervised learning models (SLMs) to predict IBIs in febrile infants (8-60 days).
  • Compare the diagnostic performance of SLMs against the 2021 American Academy of Pediatrics Clinical Practice Guideline (AAP CPG).

Main Methods:

  • Retrospective cohort study of febrile infants (8-60 days) from January 2018 to December 2023.
  • Collected data included demographics, procalcitonin, CBC indices, urinalysis, viral tests, and cultures.

Related Experiment Videos

Last Updated: May 22, 2026

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis
08:46

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis

Published on: August 12, 2020

  • Trained five SLMs on a derivation set (80%) and validated internally on a validation set (20%).

    • Main Results:

    • 56% of 2057 infants met inclusion criteria; 3% had IBIs.
    • Key predictors in SLMs: procalcitonin, absolute neutrophil count, viral status, and urinalysis.
    • SLMs achieved 92%-100% sensitivity and 81%-89% specificity, outperforming AAP CPG's 60% specificity.

    Conclusions:

    • SLMs demonstrate comparable sensitivity but superior specificity to the AAP CPG for IBI risk in febrile infants.
    • These models offer potential as clinical decision support tools for early IBI detection.
    • Further external validation is required to confirm model performance.