Towards an Automated SOAP Note: Classifying Utterances from Medical Conversations

TL;DR

This paper develops and evaluates a deep learning approach for classifying utterances in medical conversations to facilitate automated SOAP notes, addressing the lack of benchmarking datasets and methods in this domain.

Contribution

It introduces a dataset with human and ASR transcriptions, and adapts a hierarchical deep learning model for classifying SOAP sections and speaker roles in medical dialogues.

Findings

Hierarchical context modeling improves classification accuracy

Modular adaptation enhances performance on ASR transcriptions

Benchmark dataset enables future research in automated medical documentation

Abstract

Summaries generated from medical conversations can improve recall and understanding of care plans for patients and reduce documentation burden for doctors. Recent advancements in automatic speech recognition (ASR) and natural language understanding (NLU) offer potential solutions to generate these summaries automatically, but rigorous quantitative baselines for benchmarking research in this domain are lacking. In this paper, we bridge this gap for two tasks: classifying utterances from medical conversations according to (i) the SOAP section and (ii) the speaker role. Both are fundamental building blocks along the path towards an end-to-end, automated SOAP note for medical conversations. We provide details on a dataset that contains human and ASR transcriptions of medical conversations and corresponding machine learning optimized SOAP notes. We then present a systematic analysis in which we adapt an existing deep learning architecture to the two aforementioned tasks. The results suggest that modelling context in a hierarchical manner, which captures both word and utterance level context, yields substantial improvements on both classification tasks. Additionally, we develop and analyze a modular method for adapting our model to ASR output.