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

264
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:
264

You might also read

Related Articles

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

Sort by
Same author

Fairness of Machine Learning Algorithms for Predicting Foregone Preventive Dental Care for Adults.

JAMA network open·2023
Same author

A Machine Learning Prediction Model for Immediate Graft Function After Deceased Donor Kidney Transplantation.

Transplantation·2023
Same author

Machine Learning for Hypertension Prediction: a Systematic Review.

Current hypertension reports·2022
Same author

Predictors of tooth loss: A machine learning approach.

PloS one·2021
Same author

[Quality of diet and daily spending on food by adults with cardiovascular disease in Brazil].

Cadernos de saude publica·2020
Same author

Risk factors for adverse outcomes among pregnant and postpartum women with acute respiratory distress syndrome due to COVID-19 in Brazil.

International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics·2020

Related Experiment Video

Updated: Oct 27, 2025

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
19:15

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

86.8K

Neonatal mortality prediction with routinely collected data: a machine learning approach.

André F M Batista1, Carmen S G Diniz2, Eliana A Bonilha3

  • 1Department of Epidemiology, School of Public Health, University of São Paulo, 715 Av Dr Arnaldo, Sao Paulo, SP, 01246-904, Brazil.

BMC Pediatrics
|July 22, 2021
PubMed
Summary

Machine learning accurately predicts neonatal mortality risk using routine birth data. This approach identifies high-risk infants, enabling targeted interventions and improving survival rates.

Keywords:
Artificial intelligenceBirth recordsBrazilMachine learningNeonatal mortalityPrediction

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.1K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Related Experiment Videos

Last Updated: Oct 27, 2025

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
19:15

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

86.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.1K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Area of Science:

  • Public Health
  • Machine Learning in Healthcare
  • Neonatal Mortality Research

Background:

  • Global neonatal mortality rates are declining slower than anticipated.
  • Accurate prediction of neonatal mortality risk is crucial for intervention.
  • Routine birth record data offers a potential resource for risk prediction.

Purpose of the Study:

  • To develop and validate a machine learning model for predicting neonatal mortality risk.
  • To utilize routinely collected birth record data for risk prediction.
  • To assess the performance of different machine learning algorithms in identifying high-risk newborns.

Main Methods:

  • Probabilistic linkage of birth and death records in São Paulo, Brazil (2012-2018).
  • Training five machine learning algorithms on data from 2012-2016 (941,308 births).
  • Testing predictive performance on unseen data from 2017 (186,854 births).

Main Results:

  • Extreme Gradient Boosting (XGBoost) achieved the highest predictive performance (AUC 0.97, F1-score 0.55).
  • The top 5% of predicted high-risk births encompassed over 90% of actual neonatal deaths.
  • Minimal data (WHO's five indicators + 3 additional variables) maintained high predictive accuracy (AUC 0.97).

Conclusions:

  • Machine learning models can effectively predict neonatal mortality risk using routinely collected data.
  • High-risk infants can be identified with excellent accuracy, enabling targeted interventions.
  • The approach demonstrates potential for improving neonatal outcomes in resource-limited settings.