A comparative study of zero-shot inference with large language models and supervised modeling in breast cancer pathology classification
This addresses the challenge of time-consuming data annotation for clinical NLP studies, potentially speeding up research and increasing the use of NLP in observational clinical studies, though it is incremental as it compares existing methods on a new dataset.
The study tackled the problem of reducing the need for large annotated datasets in clinical NLP by comparing zero-shot inference with LLMs (GPT-4 and GPT-3.5) against supervised models (random forests, LSTM-Att, UCSF-BERT) on a breast cancer pathology classification task with 13 categories, finding that GPT-4 performed as well or better than the best supervised model, with an average macro F1 score of 0.83 vs. 0.75.
Although supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs can reduce the need for large-scale data annotations. We curated a manually-labeled dataset of 769 breast cancer pathology reports, labeled with 13 categories, to compare zero-shot classification capability of the GPT-4 model and the GPT-3.5 model with supervised classification performance of three model architectures: random forests classifier, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model. Across all 13 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, the LSTM-Att model (average macro F1 score of 0.83 vs. 0.75). On tasks with high imbalance between labels, the differences were more prominent. Frequent sources of GPT-4 errors included inferences from multiple samples and complex task design. On complex tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of large-scale data labeling. However, if the use of LLMs is prohibitive, the use of simpler supervised models with large annotated datasets can provide comparable results. LLMs demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for curating large annotated datasets. This may result in an increase in the utilization of NLP-based variables and outcomes in observational clinical studies.