Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learning
This work addresses the need for efficient information extraction from medical reports, though it is incremental as it builds on existing transformer methods.
The paper tackled the problem of extracting pathologies from cervical spine radiology reports by using a multi-task learning approach, achieving performance comparable to or better than multiple BERT-based models finetuned on individual tasks.
Pretrained Transformer based models finetuned on domain specific corpora have changed the landscape of NLP. Generally, if one has multiple tasks on a given dataset, one may finetune different models or use task specific adapters. In this work, we show that a multi-task model can beat or achieve the performance of multiple BERT-based models finetuned on various tasks and various task specific adapter augmented BERT-based models. We validate our method on our internal radiologist's report dataset on cervical spine. We hypothesize that the tasks are semantically close and related and thus multitask learners are powerful classifiers. Our work opens the scope of using our method to radiologist's reports on various body parts.