EUVIMEDOpdag EUVIMED
Crossref

Building and Evaluating an Orthodontic Natural Language Processing Model for Automated Clinical Note Information Extraction

Jay S Patel iD, Divakar Karanth

Orthodontics & Craniofacial Research · 2025-12 · 28 (S1)

DOI: 10.1111/ocr.12944 ↗

At a glance

Journal article in Orthodontics & Craniofacial Research, published online on 2025-06-14. Written by Jay S Patel and 1 co-authors. Institution: Center for Dental Informatics and Artificial Intelligence, Department of Oral Health Sciences, Temple University Kornberg School of Dentistry, Philad…. Major MEDLINE topics: Natural Language Processing, Malocclusion, Orthodontics, Electronic Health Records. Cited 3 times so far (Crossref); 40 references.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Introduction

Malocclusion presents functional and aesthetic challenges, necessitating accurate diagnosis and treatment. However, variability in orthodontic treatment planning persists due to subjective assessments, limiting consistency and objectivity. Electronic dental records (EDRs) contain vast patient data that could address these challenges, but much of the rich clinical information is documented as free text, complicating analysis. This study aims to develop an Orthodontic Natural Language Processing (ONLP) model to extract structured orthodontics‐related information from unstructured EDRs and identify critical features influencing malocclusion using machine learning (ML).

Methods

Data from 7693 orthodontic patients were analysed to train, test and validate the ONLP and ML models. A gold‐standard dataset was created through manual review. The ONLP model utilised supervised (Named Entity Recognition—NER) and unsupervised (K‐means clustering) approaches to structure information from free text. Machine learning models, including Logistic Regression, Gaussian Naive Bayes, Random Forest and XGBoost, were subsequently applied to identify feature importance for malocclusion classification.

Results

The ONLP model achieved 89% sensitivity, 92% specificity and 91% accuracy in extracting orthodontics‐related information. The supervised model demonstrated 84% accuracy, 82% F1‐score and 84% recall, excelling in identifying Classes I and III malocclusions but showing reduced sensitivity for Class II. Machine learning analysis highlighted key features for malocclusion classification: maxillary crowding, overjet and arch perimeter discrepancy for Class I; maxillary spacing and anterior crossbite for Class II; and dental midline deviation and occlusal wear for Class III.

Conclusion

This study demonstrates a novel approach to automating orthodontic data extraction using the ONLP model, enabling advanced big data analytics and enhancing data‐driven orthodontic research and care.

Subjects

MeSH terms (MEDLINE)

Natural Language ProcessingMalocclusionOrthodonticsElectronic Health RecordsHumansMachine LearningFemaleMaleAdolescent

Author keywords

artificial intelligenceelectronic dental record datamachine learningmalocclusionnatural language processingorthodontic language model

Authors and institutions

  • Center for Dental Informatics and Artificial Intelligence, Department of Oral Health Sciences, Temple University Kornberg School of Dentistry, Philadelphia, Pennsylvania, USA.
  • Department of Orthodontics, University of Florida College of Dentistry, Gainesville, Florida, USA.

ORCID profiles: Jay S Patel

Cite

APA

Patel, J. S., & Karanth, D. (2025). Building and Evaluating an Orthodontic Natural Language Processing Model for Automated Clinical Note Information Extraction. Orthodontics & Craniofacial Research, 28(S1). https://doi.org/10.1111/ocr.12944

Vancouver

Patel JS, Karanth D. Building and Evaluating an Orthodontic Natural Language Processing Model for Automated Clinical Note Information Extraction. Orthodontics & Craniofacial Research. 2025;28(S1). doi:10.1111/ocr.12944

BibTeX
@article{Patel2025,
  author = {Patel, Jay S and Karanth, Divakar},
  title = {Building and Evaluating an Orthodontic Natural Language Processing Model for Automated Clinical Note Information Extraction},
  journal = {Orthodontics & Craniofacial Research},
  year = {2025},
  volume = {28},
  number = {S1},
  doi = {10.1111/ocr.12944}
}
Start for free →