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 Experiment Video

Updated: Jul 4, 2026

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

A Multi-Modular Human-AI Workflow for LLM-Assisted Thematic Analysis: Application to COPD Telerehabilitation

Yunbing Bai1, Joseph Finkelstein1

  • 1College of Medicine - Tucson, University of Arizona.

Studies in Health Technology and Informatics
|July 3, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Association of Remote Patient Monitoring with Care Utilization in Patients with Chronic Cardiopulmonary Conditions.

Studies in health technology and informatics·2026
Same author

Machine Learning Approaches for Mortality Prediction in ARDS.

Studies in health technology and informatics·2026
Same author

Estimating Mosaic Loss of the Y Chromosome in Male Bladder Cancer Participants Using "All of Us" Data.

Studies in health technology and informatics·2026
Same author

Early Prediction of Delirium in ICU Patients Using Machine Learning Analysis of Admission Data.

Studies in health technology and informatics·2026
Same author

Multimodule Human-Artificial Intelligence Collaboration Pipeline for Large Language Model-Assisted Thematic Analysis Across Digital Health Interview Studies: Comparative Evaluation Study.

JMIR medical informatics·2026
Same author

Clinico-genomic nomograms for estimation of survival risk in metastatic castrate-resistant prostate cancer.

JNCI cancer spectrum·2026

Structured workflows enhance large language model (LLM) qualitative analysis. Grouping strategies in LLM-assisted analysis closely matched human themes, improving data fidelity.

Area of Science:

  • Artificial Intelligence
  • Qualitative Research Methods
  • Health Informatics

Background:

  • Large language models (LLMs) show promise for qualitative data analysis.
  • The impact of workflow design on LLM thematic fidelity requires further investigation.

Purpose of the Study:

  • To evaluate a structured human-AI collaboration framework for qualitative analysis using LLMs.
  • To compare the thematic fidelity of different workflow strategies in LLM-assisted analysis.

Main Methods:

  • Employed Claude Opus 4.6 to analyze 16 COPD patient interview transcripts.
  • Utilized a workflow involving code extraction, combination, and theme generation.
  • Tested hierarchical and direct grouping strategies.
  • Compared AI-generated themes with human-derived themes using cosine similarity and advanced matching algorithms.
Keywords:
Generative AILLMQualitativeThematic Analysis

Related Experiment Videos

Last Updated: Jul 4, 2026

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

Main Results:

  • Output volume varied significantly across strategies (53-357 codes, 11-17 themes).
  • Direct grouping (0.891) and L3 grouping (0.890) demonstrated the highest cosine similarity to human-generated themes.
  • Grouping-based workflows effectively preserved information and reduced redundancy.

Conclusions:

  • Structured, grouping-based workflows enhance thematic generation in LLM-assisted qualitative analysis.
  • These methods improve the fidelity and efficiency of qualitative data analysis using artificial intelligence.