43 NATURAL LANGUAGE PROCESSING MODEL-BASED SOLUTION FOR LABELING BRAIN METASTASIS IN RADIOLOGY REPORTS

Abstract

Abstract Brain Cancer Canada Travel Award Recipient Brain metastases (BM) far exceed primary CNS tumours and constitute the majority workload for neuro-oncology care providers. Canadian Cancer Registry captures ~2800 BM identified at the primary cancer diagnosis in stage IV cancer patients, while we estimated that ~10,000 Canadians are diagnosed with BM annually. We aim to develop a natural language processing (NLP) algorithm to scan radiology reports on cancer patients to capture BM diagnoses as they occur. Using the population-based cancer registry data in Alberta Canada, we identified a cancer cohort diagnosed between 2012–2019, with follow-up reports up to 2022. All radiology reports at and post-cancer diagnosis that are related to brain/head were identified for this cohort. A subset of 1817 samples was then manually labeled for BM (yes/no) as a training dataset. We trained two BioBERT models, one using the “Findings” section and the other using the “Impressions” section of these reports. We predicted the BM label as yes when the probability estimate of either model is greater than a threshold. For testing, 1585 reports containing both the “Findings” and “Impressions” sections were selected. These reports were independently labeled by an annotator for external model evaluation. Using a threshold of 0.4, our ensembled model achieved 94.3% accuracy on BM predictions. Our model yielded an F1 score of 0.788, positive predictive value of 0.702, and sensitivity of 0.898. Model performance is currently being evaluated with radiology reports in Ontario, with results expected by the end of May.

Ähnliche Arbeiten