EUVIMEDEUVIMED entdecken
Open Access

Symptom Terminology Normalization in Traditional Chinese Medicine: Development and Evaluation of a 2-Stage Deep Learning Framework Based on Fine-Grained Semantic Classification

Junyu Yao, Xingyue Gou, Wei Lai, Yuzhu Gao, Siqi Wang, Chuangan Zhou, Hui Ye, Jing Tian, Jun Yi, Dong Cao

JMIR Medical Informatics · 25.09.2026 · 14 · e85825-e85825

DOI: 10.2196/85825 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Informatics, online erschienen am 25.09.2026. Verfasst von Junyu Yao und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Medical Information Engineering, Guangzhou University of Chinese Medicine, 232 Outer Ring East Road, Guangzhou University City, Panyu Distr…. Hauptthemen laut MEDLINE: Medicine, Chinese Traditional, Deep Learning, Terminology as Topic, Semantics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Due to the heterogeneity of symptom terminology and the lack of industry standards, the same symptom is often described using multiple expressions. Current normalization approaches struggle to comprehensively retrieve standard terms when a raw term maps to multiple symptoms.

Objective

This study aimed to address the lack of industry standards for traditional Chinese medicine (TCM) symptom terminology. This study proposed the split-then-concatenate normalization framework (STC-NF), a novel approach based on fine-grained semantic classification and a 2-stage deep learning architecture that uses electronic medical records (EMRs) as the data source.

Methods

This study proposed a 2-stage deep learning framework, “split-then-concatenate.” In the splitting stage, TCM symptom entities were categorized into 12 fine-grained semantic labels, and 3 named entity recognition (NER) models were trained to extract TCM symptom terminology from EMRs. In the concatenation stage, standard terms with the same concept as raw terms were identified using a Bidirectional Encoder Representations from Transformers (BERT)–based binary classification model. The standard terms with specific semantic labels were concatenated and reordered according to predefined rules to output structured text, thereby normalizing TCM symptom terminology.

Results

The proposed STC-NF model achieved an accuracy of 91.4% (180/197) and an F 1 -score of 360 out of 389 (92.5%) on the single-implication test set. For multi-implication terms, STC-NF achieved an accuracy of 84.3% (311/369) and an F 1 -score of 1958 out of 2316 (84.5%), outperforming sequence generation in accuracy by 33.1 percentage points. On the mixed test set containing both single- and multi-implication terms, STC-NF achieved an accuracy of 88.1% (990/1124) and an F 1 -score of 3862 out of 4385 (88.1%), exceeding the best-performing baseline model, multi-task candidate generator (MTCG), by 16.7 and 22.2 percentage points in accuracy and F 1 -score, respectively.

Conclusions

In this study, we verified that the fine-grained semantic classification and the 2-stage “split-then-concatenate” framework effectively improved performance of named entity recognition and entity alignment, providing an improved approach to normalizing TCM symptom terminology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Medicine, Chinese TraditionalDeep LearningTerminology as TopicSemanticsHumansElectronic Health Records

Stichwörter der Autor:innen

named entity normalizationnamed entity recognitionnatural language processingpretrained language modelsymptom terminologytraditional Chinese medicine

Autor:innen und Institutionen

  • School of Medical Information Engineering, Guangzhou University of Chinese Medicine, 232 Outer Ring East Road, Guangzhou University City, Panyu District, Guangzhou, Guangdong, 510006, China, 86 13246852860.
  • Yunkang School of Medicine and Health, Guangzhou Nanfang College, Guangzhou, Guangdong, China.
  • School of Foreign Studies, Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, China.
  • School of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, Guangdong, China.

Zitieren

APA

Yao, J., Gou, X., Lai, W., Gao, Y., Wang, S., Zhou, C., Ye, H., Tian, J., Yi, J., & Cao, D. (2026). Symptom Terminology Normalization in Traditional Chinese Medicine: Development and Evaluation of a 2-Stage Deep Learning Framework Based on Fine-Grained Semantic Classification. JMIR Medical Informatics, 14, e85825-e85825. https://doi.org/10.2196/85825

Vancouver

Yao J, Gou X, Lai W, Gao Y, Wang S, Zhou C, et al. Symptom Terminology Normalization in Traditional Chinese Medicine: Development and Evaluation of a 2-Stage Deep Learning Framework Based on Fine-Grained Semantic Classification. JMIR Medical Informatics. 2026;14:e85825-e85825. doi:10.2196/85825

BibTeX
@article{Yao2026,
  author = {Yao, Junyu and Gou, Xingyue and Lai, Wei and Gao, Yuzhu and Wang, Siqi and Zhou, Chuangan and Ye, Hui and Tian, Jing and Yi, Jun and Cao, Dong},
  title = {Symptom Terminology Normalization in Traditional Chinese Medicine: Development and Evaluation of a 2-Stage Deep Learning Framework Based on Fine-Grained Semantic Classification},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e85825--e85825},
  doi = {10.2196/85825}
}
Kostenlos starten →