Related Experiment Video

Updated: Jul 10, 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

Machine Learning to Identify Bacteremia and Meningitis in Febrile Infants: A Systematic Review

Giacomo Ferraris1, Sara Tazzoli1, Camilla Folisi1

  • 1Department of Women's and Children's Health, Padua University Hospital, Italy.

Pediatrics
|July 8, 2026
PubMed
Abstract

Insights

Machine learning models show promise in identifying febrile infants at risk for invasive bacterial infections (IBIs), offering improved specificity over traditional methods. Further validation and standardization are needed for clinical integration.

Area of Science:

  • Pediatric Infectious Diseases
  • Medical Informatics
  • Diagnostic Accuracy

Background:

  • Accurate identification of febrile infants at risk for invasive bacterial infections (IBIs) is crucial for reducing morbidity and avoiding unnecessary procedures.
  • Machine learning (ML) is being evaluated for its potential to enhance diagnostic accuracy in this population.

Purpose of the Study:

  • To systematically review the diagnostic performance of ML-based models for identifying febrile infants (up to 90 days) with IBIs.

Main Methods:

  • Searched multiple databases (MEDLINE, Scopus, etc.) through December 2024 for eligible studies.
  • Included studies used ML models on febrile infants (≤90 days) for IBI identification, reporting diagnostic metrics with culture-confirmed infections as the reference standard.
  • Extracted study characteristics and accuracy measures; assessed risk of bias; heterogeneity precluded meta-analysis.

Main Results:

  • Six studies evaluated various ML models (logistic regression, random forests, neural networks, etc.).
  • Sensitivity ranged from 57% to 100%, specificity from 30% to 94%, and ROC-AUC from 0.57 to 0.9.
  • Several ML models demonstrated superior specificity compared to traditional tools (e.g., PECARN) for predicting IBIs.

Conclusions:

  • ML models show promising performance for IBI risk identification in infants, outperforming traditional tools in specificity.
  • Limitations include retrospective data, limited reporting, and lack of external validation.
  • Future research requires explainability analysis, broader validation, standardization, and careful clinical integration for adoption.

Related Concept Videos

Bacterial Meningitis I: Introduction01:22

Bacterial Meningitis I: Introduction

Bacterial meningitis is a severe, life-threatening inflammation of the meninges, particularly the pia mater and arachnoid mater, affecting the subarachnoid space, ventricles, and cerebrospinal fluid (CSF). If untreated, it can lead to significant neurological complications or death.Causative AgentsCommon pathogens vary with age and immune status. In adults, major organisms include Streptococcus pneumoniae, Neisseria meningitidis, and Haemophilus influenzae. Streptococcus agalactiae (group B...
Bacterial Meningitis01:24

Bacterial Meningitis

Bacterial meningitis is a severe infectious disease involving inflammation of the meninges, the protective membranes surrounding the brain and spinal cord. It occurs when pathogenic bacteria cross the blood–brain barrier and enter the cerebrospinal fluid. Common causative organisms include Neisseria meningitidis, Streptococcus pneumoniae, Haemophilus influenzae type b, Listeria monocytogenes, and Escherichia coli K1. The exact route of entry varies by pathogen and host condition.Routes of Entry...
Viral Meningitis01:18

Viral Meningitis

Viral meningitis is the most common form of meningitis and is often referred to as aseptic meningitis to indicate the absence of bacterial involvement. It is generally milder than bacterial meningitis, with symptoms including fever, headache, stiff neck, drowsiness, nausea, photophobia, and vomiting. Rarely, more severe manifestations or death may occur. Common causative agents include enteroviruses, particularly coxsackie A and B viruses and echoviruses, all members of the Enterovirus genus...
Bacterial Meningitis II: Pathophysiology01:26

Bacterial Meningitis II: Pathophysiology

Bacterial meningitis typically begins when pathogens such as Neisseria meningitidis and Streptococcus pneumoniae colonize the nasopharynx and invade the bloodstream. This process is facilitated by bacterial virulence factors, such as polysaccharide capsules, which resist phagocytosis and complement-mediated killing. Less commonly, bacteria reach the central nervous system via contiguous spread from infections like otitis media or sinusitis, through congenital or acquired dural defects, or...
Rapid Identification of Pathogens01:25

Rapid Identification of Pathogens

MALDI-TOF MS has transformed clinical microbiology by offering a rapid and reliable method for pathogen identification. The traditional approach to microbial identification typically involves time-consuming culture techniques and biochemical tests, which can delay the initiation of appropriate antimicrobial therapy. MALDI-TOF MS avoids these delays by using characteristic ribosomal protein mass patterns of microbial cells, enabling accurate species-level identification within minutes.Principle...