# Towards an Automated SOAP Note: Classifying Utterances from Medical Conversations

arXiv: https://arxiv.org/abs/2007.08749 · HTML: https://mlsanity.com/paper/2007.08749/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?](https://mlsanity.com/paper/2306.16931/) (2023)
- [Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives](https://mlsanity.com/paper/2508.02853/) (2025)
- [Improving Summarization with Human Edits](https://mlsanity.com/paper/2310.05857/) (2023)
- [CLINICSUM: Utilizing Language Models for Generating Clinical Summaries from Patient-Doctor Conversations](https://mlsanity.com/paper/2412.04254/) (2024)
- [DeepScore: A Comprehensive Approach to Measuring Quality in AI-Generated Clinical Documentation](https://mlsanity.com/paper/2409.16307/) (2024)
- [ASR Error Detection via Audio-Transcript entailment](https://mlsanity.com/paper/2207.10849/) (2022)
- [An Automatic SOAP Classification System Using Weakly Supervision And Transfer Learning](https://mlsanity.com/paper/2211.14539/) (2022)
- [From Triage to Discharge: A Survey of NLP Tasks, Methods, and Open Challenges in the Emergency Department](https://mlsanity.com/paper/2608.23627/) (2026)
- [Towards Scalable SOAP Note Generation: A Weakly Supervised Multimodal Framework](https://mlsanity.com/paper/2506.10328/) (2025)
- [Skin-SOAP: A Weakly Supervised Framework for Generating Structured SOAP Notes](https://mlsanity.com/paper/2508.05019/) (2025)

## Abstract (arXiv)

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.