Cross-Institutional Dental EHR Entity Extraction via Generative AI and Synthetic Notes

TL;DR

This study leverages GPT-4 generated synthetic notes and NLP models to improve the extraction of diagnostic information from unstructured dental records, significantly enhancing accuracy in periodontal diagnosis classification.

Contribution

It introduces a novel approach combining synthetic data from LLMs with NLP models to improve dental diagnostic information extraction from clinical notes.

Findings

Achieved 0.99 accuracy in periodontal status extraction at Site 1

Achieved 0.98 accuracy at Site 2

Outperformed existing methods in diagnostic extraction accuracy

Abstract

This research addresses the issue of missing structured data in dental records by extracting diagnostic information from unstructured text. The updated periodontology classification system's complexity has increased incomplete or missing structured diagnoses. To tackle this, we use advanced AI and NLP methods, leveraging GPT-4 to generate synthetic notes for fine-tuning a RoBERTa model. This significantly enhances the model's ability to understand medical and dental language. We evaluated the model using 120 randomly selected clinical notes from two datasets, demonstrating its improved diagnostic extraction accuracy. The results showed high accuracy in diagnosing periodontal status, stage, and grade, with Site 1 scoring 0.99 and Site 2 scoring 0.98. In the subtype category, Site 2 achieved perfect scores, outperforming Site 1. This method enhances extraction accuracy and broadens its use across dental contexts. The study underscores AI and NLP's transformative impact on healthcare delivery and management. Integrating AI and NLP technologies enhances documentation and simplifies administrative tasks by precisely extracting complex clinical information. This approach effectively addresses challenges in dental diagnostics. Using synthetic training data from LLMs optimizes the training process, improving accuracy and efficiency in identifying periodontal diagnoses from clinical notes. This innovative method holds promise for broader healthcare applications, potentially improving patient care quality.