Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

You might also read

Related Articles

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

Sort by

Same authorSame journal

Surgery for early structural osteoarthritis of the hip and knee: the SCORE evidence synthesis and economic evaluation.

Health technology assessment (Winchester, England)·2026

Same author

Pilot of a novel patient-led intervention for postdischarge from hospital management of older patients' care in general practice.

Family medicine and community health·2026

Same author

Artificial intelligence software to help detect fractures on X-rays in urgent care: An Early Value Assessment.

Health technology assessment (Winchester, England)·2026

Same author

Cost-effectiveness of radiologist reading of chest CT scans assisted by software with artificial intelligence-derived algorithms for the detection and analysis of lung nodules.

BJR artificial intelligence·2026

Same author

Determinants and gaps influencing zero-dose immunization and maternal Health service utilization in Nigeria: a cross-sectional household survey across six Nigerian states.

Global health action·2026

Same author

A Sexual health and healthy relationships intervention for Further Education (SaFE): a synopsis of results from a pilot cluster randomised controlled trial including an assessment of the feasibility of record linkage and a health economic analysis.

Public health research (Southampton, England)·2026

Search research articles

Related Experiment Video

Updated: Aug 16, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Increasing comprehensiveness and reducing workload in a systematic review of complex interventions using automated

Olalekan A Uthman¹, Rachel Court¹, Jodie Enderby¹

¹Warwick Medical School, University of Warwick, Coventry, UK.

Health Technology Assessment (Winchester, England)

|December 23, 2022

Summary

Machine learning classifiers can significantly reduce the workload of screening abstracts for systematic reviews on complex interventions, achieving high performance comparable to human reviewers.

Keywords:

MACHINE LEARNING REDUCING WORKLOAD TEXT CLASSIFICATION

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

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

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

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Aug 16, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

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

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

Published on: December 6, 2024

Area of Science:

Machine Learning
Artificial Intelligence
Health Technology Assessment

Background:

Systematic reviews of complex interventions for cardiovascular disease primary prevention are labor-intensive.
Automated machine learning (ML) classifiers were developed to assist in title and abstract screening.
The goal was to create an ML algorithm that matches human screening performance.

Purpose of the Study:

To develop and evaluate automated machine learning classifiers for screening titles and abstracts in systematic reviews.
To assess the performance of deep learning models in identifying relevant studies for cardiovascular disease primary prevention interventions.

Main Methods:

A three-phase process was used, involving labeling 16,611 articles.
Five deep learning models were evaluated: parallel convolutional neural network (CNN), stacked CNN, parallel-stacked CNN, recurrent neural network (RNN), and CNN-RNN.
Performance was measured using recall, precision, and work saved, aiming for at least 95% recall.

Main Results:

The best-performing model, parallel CNN, achieved 96.4% recall and 99.1% precision.
This model demonstrated a potential workload reduction of 89.9%.
The study utilized only title and abstract text for classification.

Conclusions:

Machine learning offers significant potential to streamline the abstract screening process in systematic reviews of complex interventions.
Further research is needed to enhance classifier performance and integration into systematic review workflows.