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

Reliability and Validity01:29

Reliability and Validity

Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.

You might also read

Related Articles

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

Sort by
Same author

Docetaxel-Induced Myositis in a 16-Year-Old Male With Rhabdomyosarcoma: Case Report and Literature Review.

Pediatric blood & cancer·2026
Same author

Prevalence and Health Care Disparities of Retinal Conditions: A Meta-Analysis.

JAMA ophthalmology·2026
Same author

Pregnancy-related death rates by county, race, and ethnicity in the US, 2000-2019.

Archives of public health = Archives belges de sante publique·2025
Same author

Five Data-Informed Principles for Advancing Inclusive Research in Clinical Trials: A Pharma Perspective.

Advances in therapy·2025
Same author

Combating crisis: Buffers between financial stress and relationship satisfaction before and during the COVID-19 pandemic.

Journal of family psychology : JFP : journal of the Division of Family Psychology of the American Psychological Association (Division 43)·2025
Same author

Correction: Advancing inclusive research calculator for oncology disease areas: A resource to support the development of enrollment targets in diversity action plans for industry sponsors.

PloS one·2025

Related Experiment Video

Updated: May 30, 2026

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Random forests for verbal autopsy analysis: multisite validation study using clinical diagnostic gold standards.

Abraham D Flaxman1, Alireza Vahdatpour, Sean Green

  • 1Institute for Health Metrics and Evaluation, University of Washington, 2301 Fifth Ave,, Suite 600, Seattle, WA 98121, USA. abie@uw.edu.

Population Health Metrics
|August 6, 2011
PubMed
Summary

A new Random Forest (RF) method for computer-coded verbal autopsy (CCVA) outperforms physician-certified verbal autopsy (PCVA) in accuracy and efficiency. This advanced CCVA technique is recommended for analyzing verbal autopsies (VAs).

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: May 30, 2026

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Area of Science:

  • Public Health
  • Epidemiology
  • Medical Informatics

Background:

  • Physician-certified verbal autopsy (PCVA) is the standard for determining causes of death but is slow and costly.
  • Computer-coded verbal autopsy (CCVA) offers a faster, cheaper, and reliable alternative.
  • This study introduces and validates a novel CCVA technique using machine learning.

Purpose of the Study:

  • To introduce and validate a new computer-coded verbal autopsy (CCVA) technique.
  • To compare the performance of the new CCVA method against physician-certified verbal autopsy (PCVA).
  • To assess the CCVA method's accuracy using clinical diagnostic criteria as a gold standard.

Main Methods:

  • Adapted the Random Forest (RF) machine learning method to predict causes of death.
  • Trained RF models to distinguish between causes of death and combined results using a novel ranking technique.
  • Assessed performance using chance-corrected concordance and cause-specific mortality fraction (CSMF) accuracy, comparing RF to PCVA across adult, child, and neonatal VAs, with and without health care experience (HCE) data.

Main Results:

  • The RF method demonstrated equal or superior performance compared to PCVA across most metrics and age groups.
  • RF showed significantly higher chance-corrected concordance for adults and children, with or without HCE.
  • CSMF accuracy was generally higher for RF, with a slight exception for neonates with HCE data.

Conclusions:

  • The developed RF method for CCVA surpasses PCVA in accuracy and efficiency for adult and child verbal autopsies.
  • The RF method is recommended as the preferred technique for analyzing verbal autopsies due to its speed, cost-effectiveness, and reliability.
  • This validates CCVA as a viable and superior alternative to traditional PCVA for mortality data collection.