Large language models for automated and audience-tailored labeling of latent classes
JAMIA Open · 06.03.2026 · 9 (2)
DOI: 10.1093/jamiaopen/ooag058 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 28.04.2026. Verfasst von Fatemeh Gholi Zadeh Kharrat und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, University of California, San Francisco, CA 94143, United States. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of Arthritis and Musculoskeletal and Skin Diseases of the National Institutes of Health.
Abstract (Originalsprache)
Objective
This study compares multiple LLMs, including ChatGPT, DeepSeek, and Llama, to generate meaningful, audience-adapted labels for the existing latent classes among patients with chronic low back pain (cLBP).
Methods
Phenotypes were derived from baseline data from two cohorts within the NIH HEAL BACPAC consortium: BACKHOME, a large nationwide e-cohort (train set: N = 3025), and COMEBACK, a deep phenotyping cohort (test set: N = 450). The analysis included pain characteristics, psychosocial factors, lifestyle habits, and social determinants of health. ChatGPT-4o (OpenAI), DeepSeek-R1, and Llama 3.3 (Meta) were applied to generate class labels for each combination of audience (clinician, patient, and caregiver), tone (formal, empathetic, and informal), and technicality (high, medium, and low).
Results
Latent Class Model (LCM) identified four distinct behavioral phenotypes in patients with cLBP: High Distress and Maladaptive Behaviors, Resilient and Adaptive Coping, Intermediate Maladaptive Patterns, and Emotionally Regulated with High Pain Burden. Previously validated by domain experts, these profiles served as the basis for automated labeling using three LLMs (ChatGPT-4o, DeepSeek-R1, and Llama 3.3). Using different tones and complexity levels, each model produced class labels specific to clinicians, patients, and caregivers. The generated class names for all LLMs closely matched expert-defined traits like emotional regulation, resilience, and high distress, indicating strong conceptual alignment and the capacity of LLMs to generate precise, audience-specific labels for intricate behavioral and psychological profiles.
Conclusions
These results highlight the possibility of integrating LLM-driven labeling into research and clinical practice, helping to achieve more transparent knowledge translation, improved decision-making, and personalized care.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Orthopaedic Surgery, University of California, San Francisco, CA 94143, United States.
- Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94158, United States.
- Tempus Dictum, Inc, Olympia, WA 98502, United States.
- Department of Family and Community Medicine, Osher Center for Integrative Health, University of California, San Francisco, CA 94115, United States.
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, CA 94143, United States.
ORCID-Profile: C Anthony Hunt, Jeffrey Lotz
Förderung
- National Institute of Arthritis and Musculoskeletal and Skin Diseases of the National Institutes of Health
Zitieren
APA
Gholi Zadeh Kharrat, F., Werfelmann, R., Ropella, G. E., Mehling, W., Hunt, C. A., Lotz, J., Peterson, T. A., & REACH Investigators (2026). Large language models for automated and audience-tailored labeling of latent classes. JAMIA Open, 9(2). https://doi.org/10.1093/jamiaopen/ooag058
Vancouver
Gholi Zadeh Kharrat F, Werfelmann R, Ropella GE, Mehling W, Hunt CA, Lotz J, et al. Large language models for automated and audience-tailored labeling of latent classes. JAMIA Open. 2026;9(2). doi:10.1093/jamiaopen/ooag058
BibTeX
@article{GholiZadehKharrat2026,
author = {Gholi Zadeh Kharrat, Fatemeh and Werfelmann, Rob and Ropella, Glen Ep and Mehling, Wolf and Hunt, C Anthony and Lotz, Jeffrey and Peterson, Thomas A and REACH Investigators, REACH Investigators},
title = {Large language models for automated and audience-tailored labeling of latent classes},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {2},
doi = {10.1093/jamiaopen/ooag058}
}
EUVIMED