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

Distinguishing Between Healthy and Unhealthy Newborns Based on Acoustic Features and Deep Learning Neural Networks Tuned by Bayesian Optimization and Random Search Algorithm.

Entropy (Basel, Switzerland)·2025
Same author

Use of psychoacoustic spectrum warping, decision template fusion, and neighborhood component analysis in newborn cry diagnostic systems.

The Journal of the Acoustical Society of America·2024
Same author

Infant Cry Signal Diagnostic System Using Deep Learning and Fused Features.

Diagnostics (Basel, Switzerland)·2023
Same author

Using CCA-Fused Cepstral Features in a Deep Learning-Based Cry Diagnostic System for Detecting an Ensemble of Pathologies in Newborns.

Diagnostics (Basel, Switzerland)·2023
Same author

Newborn Cry-Based Diagnostic System to Distinguish between Sepsis and Respiratory Distress Syndrome Using Combined Acoustic Features.

Diagnostics (Basel, Switzerland)·2022
Same author

An Entropy-Based Architecture for Detection of Sepsis in Newborn Cry Diagnostic Systems.

Entropy (Basel, Switzerland)·2022

Related Experiment Video

Updated: Oct 2, 2025

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

6.5K

Machine Learning-Based Cry Diagnostic System for Identifying Septic Newborns.

Fatemeh Salehian Matikolaie1, Chakib Tadj1

  • 1Department of Electrical Engineering, École De Technologie Supérieure, Montreal, QC, H3C 1K3, Canada.

Journal of Voice : Official Journal of the Voice Foundation
|February 23, 2022
PubMed
Summary

Newborns' cry audio signals (CAS) can help diagnose sepsis. Machine learning analysis of CAS successfully distinguished septic from healthy infants, offering a noninvasive diagnostic tool.

Keywords:
Classifiers fusionDecision treeDiscriminant analysisFeature manipulationInfants’ cryMel frequency cepstral coefficientPrincipal component analysisProsodic featureSepsisSupport vector machine

More Related Videos

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

6.7K
Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings
14:40

Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings

Published on: October 25, 2015

9.5K

Related Experiment Videos

Last Updated: Oct 2, 2025

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

6.5K
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

6.7K
Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings
14:40

Instrumentation of Near-term Fetal Sheep for Multivariate Chronic Non-anesthetized Recordings

Published on: October 25, 2015

9.5K

Area of Science:

  • Neonatal care
  • Machine learning applications
  • Bioacoustics

Background:

  • Newborn cry audio signals (CAS) contain vital health information.
  • Early disease diagnosis in infants is crucial.
  • Septic infants' CAS has not been previously studied for diagnostic purposes.

Purpose of the Study:

  • To develop an automated system for diagnosing infant sepsis using CAS.
  • To analyze CAS of newborns under two months old.
  • To differentiate septic infants from healthy ones via machine learning.

Main Methods:

  • Extraction of Mel frequency cepstral coefficients and prosodic features (tilt, rhythm, intensity).
  • Evaluation using classifiers like Support Vector Machine (SVM), decision tree, and discriminant analysis.
  • Utilizing majority voting, feature manipulation, and a multiple classifier framework on expiration and inspiration CAS datasets.

Main Results:

  • The best F-score of 86% was achieved for the expiration dataset using concatenated features with quadratic SVM.
  • The best F-score of 83.90% for the inspiration dataset was obtained with the tilt feature set and quadratic discriminant.
  • Cry patterns differ significantly between septic and healthy infants.

Conclusions:

  • The proposed machine learning approach effectively identifies septic infants from their CAS.
  • This method offers a noninvasive tool for early sepsis detection in newborns.
  • CAS analysis holds significant potential for neonatal health assessment.