Leveraging GPT-4 for Identifying Cancer Phenotypes in Electronic Health Records: A Performance Comparison between GPT-4, GPT-3.5-turbo, Flan-T5 and spaCy’s Rule-based & Machine Learning-based methods

Kriti Bhattarai, Inez Y. Oh, Jonathan Moran Sierra, Jonathan Tang, Philip Payne, Zachary B. Abrams, Albert M. Lai

Abstract

GPT-4 improves clinical phenotype identification due to its robust pre-training and remarkable pattern recognition capability on the embedded tokens. It demonstrates data-driven effectiveness even with limited context in the input. While rule-based models remain useful for some tasks, GPT models offer improved contextual understanding of the text, and robust clinical phenotype extraction.
BibTeX
@inproceedings{bhattarai2024leveraging,
  author = {Kriti Bhattarai and Inez Y. Oh and Jonathan Moran Sierra and Jonathan Tang and Philip Payne and Zachary B. Abrams and Albert M. Lai},
  title = {{Leveraging GPT-4 for Identifying Cancer Phenotypes in Electronic Health Records: A Performance Comparison between GPT-4, GPT-3.5-turbo, Flan-T5 and spaCy’s Rule-based \& Machine Learning-based methods}},
  booktitle = {JAMIA},
  year = {2024},
  doi = {10.1093/jamiaopen/ooae060},
}

Loading related content...

Figure