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

Deductive Reasoning

Deductive Reasoning

Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...

You might also read

Related Articles

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

Sort by

Same author

From Clinical Decision Support to Equity-Aware Decision Support: A Conceptual Architecture for Digital Health Systems.

Studies in health technology and informatics·2026

Same author

Autistic Trait Level and Reaction Time in Older Adults: The Influence of Sex and Task upon Study Outcome.

Autism in adulthood·2026

Same author

Access to general practice: why policy must be rural-proofed.

The British journal of general practice : the journal of the Royal College of General Practitioners·2026

Same author

American Thyroid Association 2026 Guidelines for Thyroid Disease in Preconception, Pregnancy, and Postpartum.

Thyroid : official journal of the American Thyroid Association·2026

Same author

Membership Inference or Data Split Bias? Identifying False Positives in Synthetic Medical Image Privacy Audits.

Studies in health technology and informatics·2026

Same author

Enhancing Ontology Engineering with Large Language Models: A Stage-Wise Human-in-the-Loop Study.

Studies in health technology and informatics·2026

Search research articles

Related Experiment Video

Updated: May 24, 2026

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 Hybrid Delphi-Inspired Expert-LLM Workflow for Efficient Evidence Screening in Systematic Reviews.

Omid Pournik¹, Emma Watts^2,3, Emma Richards³

¹Department of Electronic, Electrical and Systems Engineering, University of Birmingham, UK.

Studies in Health Technology and Informatics

|May 23, 2026

Summary

This summary is machine-generated.

This study introduces a hybrid expert-large language model (LLM) workflow for systematic reviews, significantly reducing manual screening time by 70% while maintaining high accuracy. This AI-powered approach enhances efficiency in evidence-based healthcare research.

Keywords:

ChatGPT Evidence Screening Expert Consensus Large Language Models Systematic Review Thyroid Cancer

More Related Videos

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

Related Experiment Videos

Last Updated: May 24, 2026

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 Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

Area of Science:

Medical Informatics
Artificial Intelligence in Healthcare
Evidence-Based Medicine

Background:

Systematic reviews are crucial for evidence-based healthcare but are time-consuming due to manual screening.
A significant number of studies are excluded during the initial screening phase, contributing to the workload.

Purpose of the Study:

To develop and evaluate a hybrid expert-LLM workflow to decrease human workload in systematic reviews.
To maintain accuracy and transparency during the evidence screening process.

Main Methods:

A hybrid workflow combining expert consensus and ChatGPT-5 was developed for classifying 14,858 records on thyroid nodule malignancy risk.
Expert clinicians and informaticians refined irrelevant concepts into exclusion rules for structured prompts.
The LLM classified abstracts, and a random sample of 100 records was verified by human reviewers.

Main Results:

The hybrid expert-LLM workflow achieved 96% concordance (κ = 0.91) with human reviewers.
The workflow demonstrated a reduction in manual screening time by approximately 70%.
Only one false exclusion was identified, indicating high accuracy.

Conclusions:

A transparent, Delphi-inspired expert-LLM workflow can automate early-stage evidence screening accurately and reproducibly.
This approach offers substantial efficiency gains in systematic reviews while preserving human oversight.
The study presents a practical method for integrating generative AI into systematic review methodology and digital health research.