AI-Driven vision large language framework for pediatric pain assessment
Frontiers in Pediatrics · 22.07.2026 · 14
DOI: 10.3389/fped.2026.1784197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Pediatrics, online erschienen am 22.07.2026. Verfasst von Bing Li und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology, Department of Pediatrics, Women and Childrens Hospital, School of Medicine, Xiamen University, Xiamen, China. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Schmerzmanagement
Abstract (Originalsprache)
Background
Accurate pediatric pain assessment is essential for effective pain management and procedural safety. However, current evaluations largely rely on subjective scales and casual behavioral observations. Although automated pain assessment methods have been proposed, they often remain complex and less reliable than expert clinicians. This study aimed to establish a proof-of-concept for a novel Pain Assessment Vision–Large Language Framework (PA-VLLF) for consistent pediatric pain evaluation.
Methods
In this observational proof-of-concept study, we developed and validated the PA-VLLF using representative keyframes extracted from real-world surveillance video recordings of venipuncture from two camera angles. The foundation framework combined ChatGPT-4o and Qwen2-VL vision-language architectures, with customized prompts and fine-tuning to generate FLACC (Facial, Legs, Activity, Cry, Consolability) scores within a human-in-the-loop framework. Data were collected and analyzed from September to December 2024. The study was approved by the institutional review board (IRB no. 294A01) and parental consent was obtained.
Results
We established a Clinical Pain Assessment (CPA) dataset of 1,248 video segments from 104 children, independently annotated by five certified pain experts over a cumulative 950 person-hours to establish a consensus baseline. In this dataset, PA-VLLF-ChatGPT successfully aligned with the collective expert consensus, achieving 86.36% accuracy on expert-labeled pain scores, performing comparably to senior experts (84.69%, p > 0.05) and outperforming machine-learning approaches in our comparisons; precision of pain-level assessment was evaluated using complementary metrics (MAX agreement and Z-Score).
Conclusions
As a successful proof-of-concept, PA-VLLF demonstrates that vision-language models can successfully internalize expert-derived clinical reasoning. By serving as a standardized, consensus-based intelligent assistant, it reduces the cognitive burden of complex visual evaluations and mitigates individual rater variance. This framework holds promise for improving pain management strategies, supporting highly consistent, AI-assisted clinical decision-making. To support future research, the CPA dataset will be accessible upon the publication of this article to qualified researchers under data privacy regulations.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Anesthesiology, Department of Pediatrics, Women and Childrens Hospital, School of Medicine, Xiamen University, Xiamen, China.
- Southern University of Science and Technology, Shenzhen, China.
- School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China.
- Department of Behavioral Development, Guangzhou Children and Women Medical Center, Guangzhou Medical University, Guangzhou, China.
- Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, the Brain Cognition and Brain Disease Institute, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
- Department of Computer Science and Technology, Tsinghua University, Beijing, China.
Zitieren
APA
Li, B., Pang, J., Cai, Y., Yu, J., Liu, Y., Tian, R., Yu, P., Liang, X., Wang, S., Wu, P., Yang, L., Wu, L., Zhao, Z., Zheng, L., Zhang, K., Wang, L., Yang, L., Itti, L., & Wen, S. (2026). AI-Driven vision large language framework for pediatric pain assessment. Frontiers in Pediatrics, 14. https://doi.org/10.3389/fped.2026.1784197
Vancouver
Li B, Pang J, Cai Y, Yu J, Liu Y, Tian R, et al. AI-Driven vision large language framework for pediatric pain assessment. Frontiers in Pediatrics. 2026;14. doi:10.3389/fped.2026.1784197
BibTeX
@article{Li2026,
author = {Li, Bing and Pang, Jinguo and Cai, Yaxin and Yu, Jing and Liu, Yong and Tian, Renrui and Yu, Peng and Liang, Xiaoling and Wang, Shiqing and Wu, Peiyuan and Yang, Lulu and Wu, Lingxiao and Zhao, Zengxiao and Zheng, Li and Zhang, Kangning and Wang, Liping and Yang, Li and Itti, Laurent and Wen, Shixian},
title = {AI-Driven vision large language framework for pediatric pain assessment},
journal = {Frontiers in Pediatrics},
year = {2026},
volume = {14},
doi = {10.3389/fped.2026.1784197}
}
EUVIMED