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

246
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:
246
Issues And Trends In Healthcare Delivery System01:29

Issues And Trends In Healthcare Delivery System

5.9K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.9K
Principles of Disease Surveillance01:26

Principles of Disease Surveillance

211
Disease surveillance is the systematic collection, analysis, and interpretation of health data essential to the planning, implementation, and evaluation of public health practice. This process integrates data dissemination to entities responsible for preventing and controlling disease, injury, and disability. Surveillance systems provide crucial information for action, helping public health authorities make informed decisions to manage and prevent outbreaks, ensure public safety, optimize...
211

You might also read

Related Articles

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

Sort by
Same author

Comparison of Consumer Smartwatch and Research-Grade Accelerometer-Derived Step Counts in Amyotrophic Lateral Sclerosis.

Muscle & nerve·2026
Same author

FairCareNLP: An AI-driven patient review analyzer for healthcare.

PloS one·2026
Same author

Perceived Potential and Challenges of Supporting Coronary Artery Disease Treatment Decisions With AI: Qualitative Study.

JMIR cardio·2026
Same author

Application of Machine Learning to Auto-Code Injury Data in the e-CHIRPP System: Development and Evaluation Study.

Online journal of public health informatics·2025
Same author

Factors Associated With Suicidal Ideation Among Persons With Disabilities in South Korea: Retrospective Observational Study.

JMIR formative research·2025
Same author

Generative AI and Foundation Models in Radiology: Applications, Opportunities, and Potential Challenges.

Radiology·2025

Related Experiment Video

Updated: Oct 6, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

946

Crowdsourcing for Machine Learning in Public Health Surveillance: Lessons Learned From Amazon Mechanical Turk.

Zahra Shakeri Hossein Abad1,2, Gregory P Butler3, Wendy Thompson3

  • 1Department of Biomedical Informatics, Harvard Medical School, Harvard University, Boston, MA, United States.

Journal of Medical Internet Research
|January 18, 2022
PubMed
Summary

Crowdsourcing data quality is crucial for developing reliable public health surveillance systems. This study shows that simple consensus methods overlook important task details, highlighting the need for advanced inference models to ensure accurate machine learning model training.

Keywords:
crowdsourcingdigital public health surveillancemachine learningpublic health databasesocial media analysis

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

719
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

495

Related Experiment Videos

Last Updated: Oct 6, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

946
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

719
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

495

Area of Science:

  • Digital Public Health
  • Machine Learning
  • Crowdsourcing Data Quality

Background:

  • Crowdsourcing platforms like Amazon Mechanical Turk (AMT) offer scalable solutions for data collection in public health.
  • Challenges exist in verifying crowdsourced data quality due to large volumes and rapid processing times, impacting reliability for digital public health systems.

Purpose of the Study:

  • To evaluate the application of crowdsourcing, specifically AMT, for developing digital public health surveillance systems.
  • To explore and compare different methods for inferring ground truth labels from crowd-generated data.

Main Methods:

  • Collected over 296,000 crowd-generated labels for 98,000 tweets using 610 AMT workers.
  • Developed and evaluated 4 statistical consensus methods and 7 machine learning models for truth inference, considering task meta-information.

Main Results:

  • Majority vote consensus methods can mask data uncertainty and neglect task-specific information.
  • Truth inference is context-dependent, with no single method consistently outperforming others across different datasets (physical activity, sedentary behavior, sleep quality).
  • Machine learning model performance is sensitive to crowd-label quality, with poor labels leading to inaccurate assessments.

Conclusions:

  • High-quality crowd-generated labels are essential for developing accurate machine learning models for public health surveillance.
  • A combination of advanced inference models can quantitatively measure and enhance the quality of crowd-sourced labels for training machine learning models.