Analyzing patient perspectives with large language models: a cross-sectional study of sentiment and thematic classification on exception from informed consent

Large language models (LLMs) can improve text analysis efficiency in healthcare. This study explores the application of LLMs to analyze patient perspectives within the exception from informed consent (EFIC) process, which waives consent in emergency research. Our objective is to assess whether LLMs can analyze patient perspectives in EFIC interviews with performance comparable to human reviewers. We analyzed 102 EFIC community interviews from 9 sites, each with 46 questions, as part of the Pediatric Dose Optimization for Seizures in Emergency Medical Services study. We evaluated 5 LLMs, including GPT-4, to assess sentiment polarity on a 5-point scale and classify responses into predefined thematic classes. Three human reviewers conducted parallel analyses, with agreement measured by Cohen's Kappa and classification accuracy. Polarity scores between LLM and human reviewers showed substantial agreement (Cohen's kappa: 0.69, 95% CI 0.61-0.76), with major discrepancies in only 4.7% of responses. LLM achieved high thematic classification accuracy (0.868, 95% CI 0.853-0.881), comparable to inter-rater agreement among human reviewers (0.867, 95% CI 0.836-0.901). LLMs enabled large-scale visual analysis, comparing response statistics across sites, questions, and classes. LLMs efficiently analyzed patient perspectives in EFIC interviews, showing substantial sentiment assessment and thematic classification performance. However, occasional underperformance suggests LLMs should complement, not replace, human judgment. Future work should evaluate LLM integration in EFIC to enhance efficiency, reduce subjectivity, and support accurate patient perspective analysis.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2025-02-20
DOI
https://doi.org/10.1038/s41598-025-89996-w
Citations
6
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
3.93

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Analyzing patient perspectives with large language models: a cross-sectional study of sentiment and thematic classification on exception from informed consent

Joy Kim, Todd P. Chang, Caleb E. Ward, Johanna C. Innes et al.
6 citations
Scientific Reports
Artificial Intelligence in Healthcare and Education
3.93
article

Analyzing patient perspectives with large language models: a cross-sectional study of sentiment and thematic classification on exception from informed consent

Joy Kim, Todd P. Chang, Caleb E. Ward, Johanna C. Innes, Daniel K. Nishijima, Chandan Singh, Kathleen Adelgais, Manish I. Shah, Maija Holsti, Shannon Rodgers, Catherine R. Counts, John M. VanBuren, Aaron E. Kornblith, Harold K. Simon, Buzz McClain
article en
6 citations

Abstract

Large language models (LLMs) can improve text analysis efficiency in healthcare. This study explores the application of LLMs to analyze patient perspectives within the exception from informed consent (EFIC) process, which waives consent in emergency research. Our objective is to assess whether LLMs can analyze patient perspectives in EFIC interviews with performance comparable to human reviewers. We analyzed 102 EFIC community interviews from 9 sites, each with 46 questions, as part of the Pediatric Dose Optimization for Seizures in Emergency Medical Services study. We evaluated 5 LLMs, including GPT-4, to assess sentiment polarity on a 5-point scale and classify responses into predefined thematic classes. Three human reviewers conducted parallel analyses, with agreement measured by Cohen's Kappa and classification accuracy. Polarity scores between LLM and human reviewers showed substantial agreement (Cohen's kappa: 0.69, 95% CI 0.61-0.76), with major discrepancies in only 4.7% of responses. LLM achieved high thematic classification accuracy (0.868, 95% CI 0.853-0.881), comparable to inter-rater agreement among human reviewers (0.867, 95% CI 0.836-0.901). LLMs enabled large-scale visual analysis, comparing response statistics across sites, questions, and classes. LLMs efficiently analyzed patient perspectives in EFIC interviews, showing substantial sentiment assessment and thematic classification performance. However, occasional underperformance suggests LLMs should complement, not replace, human judgment. Future work should evaluate LLM integration in EFIC to enhance efficiency, reduce subjectivity, and support accurate patient perspective analysis.

Scientific ReportsVol. 15(1)
University of Southern California (US), Cincinnati Children's Hospital Medical Center (US), George Washington University Hospital (US), Microsoft (United States) (US), Nationwide Children's Hospital (US), Primary Children's Hospital (US), Children's Hospital of Los Angeles (US), Emory University (US), Oregon Health & Science University (US), Palo Alto University (US), University of California, San Francisco (US), University of Washington (US), University of Utah (US), San Francisco Public Library (US), Children's Healthcare of Atlanta (US), Jacobs (United States) (US), University of California, Davis (US), University of Colorado Denver (US), Stanford University (US)
U.S. Department of Health and Human Services, Emory University, Cincinnati Children's Hospital Medical Center, Nationwide Children's Hospital, Seattle Children's Research Institute, Scheme for Promotion of Academic and Research Collaboration, National Institutes of Health, Health Resources and Services Administration, School of Medicine, Emory University, University at Buffalo, National Institute of Neurological Disorders and Stroke, National Institute of Child Health and Human Development, Maternal and Child Health Bureau, Eunice Kennedy Shriver National Institute of Child Health and Human Development
Openalex Percentile: Top 7%
Artificial Intelligence in Healthcare and Education
3.93
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.