Scholarlink

Background <p>Chronic pain poses a significant global health burden, with pertinent contextual information relevant to it encapsulated in free text format across sources such as electronic health records (EHRs), published literature, and social media. Natural language processing (NLP), including recent advances in large language models (LLMs), presents a transformative opportunity to analyze this unstructured data, but the literature is fragmented across disciplines, and there is a need to consolidate existing knowledge, identify gaps in the literature, and inform future research directions in this emerging field.</p> Objective <p>This review aims to investigate and characterize NLP-based methods designed for chronic pain research.</p> Methods <p>A structured search was conducted across five databases (PubMed, Web of Science, Scopus, IEEE Xplore, ACL Anthology) for English-language studies published between 2014 and 2025. Included studies were analyzed for design, research question, data sources, NLP methods, population characteristics, and reproducibility.</p> Results <p>From 155 records, 34 met inclusion criteria. The majority of studies (23/34; 67%) were published in the past three years. Most studies (12/34) relied on EHR data, with others utilizing social media data (n=7), synthesizing literature (n=2), or leveraging other data sources. Earlier studies focused on rule-based methods, while recent work adopted transformer-based models (e.g., BERT, RoBERTa, BioBERT) and LLMs (e.g., GPT-3.5 for zero- or few-shot learning frameworks). Common challenges included limited dataset diversity, lack of standardized evaluation frameworks, and poor reproducibility practices.</p> Conclusions <p>While the application of NLP for chronic pain research is promising, the review revealed a paucity of research on the topic, with opportunities for future explorations such as validation of generalizable approaches involving diverse data and cohorts, multimodal data validation systems, public release of data and models, and the development of standardized evaluation metrics to enhance reproducibility and equity in chronic pain research. The emerging use of NLP offers clinicians new ways to observe patient needs, communicate more clearly, and make pain care more responsive and humane.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A scoping review of applications of natural language processing for chronic pain research

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月2日

查看全文
  • Swati Rajwal,
  • Selen Bozkurt,
  • Jeanmarie Perrone,
  • Anne Marie McKenzie-Brown,
  • Abeed Sarker

摘要

Background

Chronic pain poses a significant global health burden, with pertinent contextual information relevant to it encapsulated in free text format across sources such as electronic health records (EHRs), published literature, and social media. Natural language processing (NLP), including recent advances in large language models (LLMs), presents a transformative opportunity to analyze this unstructured data, but the literature is fragmented across disciplines, and there is a need to consolidate existing knowledge, identify gaps in the literature, and inform future research directions in this emerging field.

Objective

This review aims to investigate and characterize NLP-based methods designed for chronic pain research.

Methods

A structured search was conducted across five databases (PubMed, Web of Science, Scopus, IEEE Xplore, ACL Anthology) for English-language studies published between 2014 and 2025. Included studies were analyzed for design, research question, data sources, NLP methods, population characteristics, and reproducibility.

Results

From 155 records, 34 met inclusion criteria. The majority of studies (23/34; 67%) were published in the past three years. Most studies (12/34) relied on EHR data, with others utilizing social media data (n=7), synthesizing literature (n=2), or leveraging other data sources. Earlier studies focused on rule-based methods, while recent work adopted transformer-based models (e.g., BERT, RoBERTa, BioBERT) and LLMs (e.g., GPT-3.5 for zero- or few-shot learning frameworks). Common challenges included limited dataset diversity, lack of standardized evaluation frameworks, and poor reproducibility practices.

Conclusions

While the application of NLP for chronic pain research is promising, the review revealed a paucity of research on the topic, with opportunities for future explorations such as validation of generalizable approaches involving diverse data and cohorts, multimodal data validation systems, public release of data and models, and the development of standardized evaluation metrics to enhance reproducibility and equity in chronic pain research. The emerging use of NLP offers clinicians new ways to observe patient needs, communicate more clearly, and make pain care more responsive and humane.