This research paper investigates the application of deep learning-based clinical coding approaches in outpatient settings. It addresses the lack of research in this area despite its distinct challenges and potential for efficiency. For the study, a large outpatient dataset was collected and four state-of-the-art clinical coding approaches were adapted to this setting. The study found that there are potential benefits in applying more innovations from inpatient coding benchmarks to the outpatient setting. The paper concludes that some coding tasks in outpatient settings could be completely automated with a low error rate.
Publication date: 22 Dec 2023
Project Page: Not Provided
Paper: https://arxiv.org/pdf/2312.13533
