Applying Natural Language Processing to Single-Report Prediction of Metastatic Disease Response Using the OR-RADS Lexicon

Simple Summary Lack of standardization among radiologists in writing radiological reports impacts the ability to interpret cancer response to treatment at a large-scale. This is an issue since large-scale data collection is necessary to generate Real World Evidence (RWE) towards understanding the effectiveness of cancer treatments and developing personalized patient treatment decisions. This study aims to examine the utility of applying natural language processing (NLP) for large-scale interpretation of disease response using the standardized oncologic response categories known as the OR-RADS to facilitate RWE collection. This study demonstrates the feasibility of applying NLP to predict disease response in cancer patients, exceeding human performance, thus encouraging use of the standardized OR-RADS categories among radiologists and researchers to improve large-scale response prediction accuracy.Abstract Generating Real World Evidence (RWE) on disease responses from radiological reports is important for understanding cancer treatment effectiveness and developing personalized treatment. A lack of standardization in reporting among radiologists impacts the feasibility of large-scale interpretation of disease response. This study examines the utility of applying natural language processing (NLP) to the large-scale interpretation of disease responses using a standardized oncologic response lexicon (OR-RADS) to facilitate RWE collection. Radiologists annotated 3503 retrospectively collected clinical impressions from radiological reports across several cancer types with one of seven OR-RADS categories. A Bidirectional Encoder Representations from Transformers (BERT) model was trained on this dataset with an 80-20% train/test split to perform multiclass and single-class classification tasks using the OR-RADS. Radiologists also performed the classification to compare human and model performance. The model achieved accuracies from 95 to 99% across all classification tasks, performing better in single-class tasks compared to the multiclass task and producing minimal misclassifications, which pertained mostly to overpredicting the equivocal and mixed OR-RADS labels. Human accuracy ranged from 74 to 93% across all classification tasks, performing better on single-class tasks. This study demonstrates the feasibility of the BERT NLP model in predicting disease response in cancer patients, exceeding human performance, and encourages the use of the standardized OR-RADS lexicon to improve large-scale prediction accuracy.