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

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

472
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:
472

You might also read

Related Articles

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

Sort by
Same author

Progression of dengue during an outbreak (2024) in Dhaka, Bangladesh: a hospital based longitudinal study.

The Lancet regional health. Southeast Asia·2026
Same author

Cost-effectiveness of bubble continuous positive airway pressure in treating severe pneumonia and hypoxaemia in under-five children in Ethiopia.

PloS one·2026
Same author

The hidden burden of viral hepatitis: a comparative study of KAP and infections among rohingya refugees and host communities in Bangladesh.

BMC public health·2026
Same author

Healthcare resources for inborn errors of immunity in the Asia-Pacific region.

Journal of human immunity·2026
Same author

Educating Anesthesiology Residents and Their Support Persons to Improve Understanding and Increase Wellness: A Multisite Study.

Anesthesia and analgesia·2026
Same author

Perceptions of factors influencing Ebola vaccine acceptance among community members, healthcare workers, and response personnel in Eastern Democratic Republic of the Congo.

PloS one·2026

Related Experiment Video

Updated: Jan 11, 2026

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

2.1K

Predicting Pediatric Sepsis and Mortality Using Wearable Device Data and Machine Learning in Bangladesh.

Atin Jindal1, Stephanie C Garbern1,2, Shira Dunsiger3

  • 1Department of Medicine, Warren Alpert Medical School, Brown University, Providence, Rhode Island.

The American Journal of Tropical Medicine and Hygiene
|November 18, 2025
PubMed
Summary
This summary is machine-generated.

Wearable biosensors and machine learning can predict pediatric sepsis, septic shock, and mortality in low-resource settings. This technology offers a promising alternative to traditional diagnostic methods, improving patient outcomes.

More Related Videos

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies
15:00

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies

Published on: February 3, 2023

2.9K

Related Experiment Videos

Last Updated: Jan 11, 2026

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

2.1K
Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies
15:00

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies

Published on: February 3, 2023

2.9K

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence in Medicine
  • Pediatric Critical Care

Background:

  • Sepsis poses a significant threat to children, particularly in resource-limited areas where advanced diagnostic tools are unavailable.
  • Current sepsis diagnostics, like the Phoenix Sepsis Score (PSS), depend heavily on laboratory tests, hindering timely diagnosis in low-resource settings.

Purpose of the Study:

  • To assess the efficacy of continuous physiological data from low-cost wearable biosensors and machine learning (ML) models in predicting pediatric sepsis, septic shock, and mortality.
  • To evaluate the potential of these technologies as a viable alternative to traditional diagnostic methods in resource-constrained intensive care units (ICUs).

Main Methods:

  • A prospective observational study involving 96 pediatric ICU patients with suspected sepsis in Dhaka, Bangladesh.
  • Physiological data collected via wearable biosensor patches; sepsis, septic shock, and mortality identified using clinical exams, lab tests, and PSS criteria.
  • Least Absolute Shrinkage and Selection Operator (LASSO) regression models developed and validated using leave-one-group-out cross-validation (LOGO-CV) on biosensor data.

Main Results:

  • The biosensor-only ML model achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.78 for sepsis prediction.
  • Models demonstrated strong predictive capabilities for septic shock (AUROC = 0.85) and mortality (AUROC = 0.87).
  • Including manual oxygen saturation (SpO2) improved the sepsis prediction AUROC to 0.89, highlighting the value of combined data.

Conclusions:

  • Wearable biosensors coupled with ML models show significant potential for predicting pediatric sepsis, septic shock, and mortality in low-resource settings.
  • This approach can support clinical decision-making without reliance on extensive laboratory infrastructure.
  • Further external validation and integration with mobile health (mHealth) are recommended for real-world clinical application.