Generating more faithful and consistent SOAP notes using attribute-specific parameters

Sanjana Ramprasad, Elisa Ferracane, Sai P. Selvaraj
Proceedings of the 8th Machine Learning for Healthcare Conference, PMLR 219:631-649, 2023.

Abstract

The widespread adoption of SOAP notes for documenting diverse aspects of patient information in healthcare has been prevalent. However, the conventional process of manual note-taking is laborious and can distract healthcare providers from addressing patients’ needs. Prior work by Krishna et al. (2021a) has introduced an end-to-end pipeline for generating SOAP notes, but model-generated notes are susceptible to inaccuracies, irrelevant and missing information. In this work, we assess the performance of large language models (GPT-3.5) for SOAP note generation, compare them with fine-tuned models using automated metrics, and propose a solution to improve the consistency and faithfulness of notes by incorporating attribute-specific information via SOAP section information. To achieve this, we integrate an extra layer of unique section-specific cross-attention parameters to existing encoder-decoder architectures. Our approach is evaluated using a comprehensive suite of automated metrics and expert human evaluators, demonstrating that it leads to more accurate, relevant, and faithful information.

Cite this Paper

BibTeX
@InProceedings{pmlr-v219-ramprasad23a, title = {Generating more faithful and consistent SOAP notes using attribute-specific parameters}, author = {Ramprasad, Sanjana and Ferracane, Elisa and Selvaraj, Sai P.}, booktitle = {Proceedings of the 8th Machine Learning for Healthcare Conference}, pages = {631--649}, year = {2023}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo and Yeung, Serene}, volume = {219}, series = {Proceedings of Machine Learning Research}, month = {11--12 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v219/ramprasad23a/ramprasad23a.pdf}, url = {https://proceedings.mlr.press/v219/ramprasad23a.html}, abstract = {The widespread adoption of SOAP notes for documenting diverse aspects of patient information in healthcare has been prevalent. However, the conventional process of manual note-taking is laborious and can distract healthcare providers from addressing patients’ needs. Prior work by Krishna et al. (2021a) has introduced an end-to-end pipeline for generating SOAP notes, but model-generated notes are susceptible to inaccuracies, irrelevant and missing information. In this work, we assess the performance of large language models (GPT-3.5) for SOAP note generation, compare them with fine-tuned models using automated metrics, and propose a solution to improve the consistency and faithfulness of notes by incorporating attribute-specific information via SOAP section information. To achieve this, we integrate an extra layer of unique section-specific cross-attention parameters to existing encoder-decoder architectures. Our approach is evaluated using a comprehensive suite of automated metrics and expert human evaluators, demonstrating that it leads to more accurate, relevant, and faithful information.} }
Endnote
%0 Conference Paper %T Generating more faithful and consistent SOAP notes using attribute-specific parameters %A Sanjana Ramprasad %A Elisa Ferracane %A Sai P. Selvaraj %B Proceedings of the 8th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2023 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %E Serene Yeung %F pmlr-v219-ramprasad23a %I PMLR %P 631--649 %U https://proceedings.mlr.press/v219/ramprasad23a.html %V 219 %X The widespread adoption of SOAP notes for documenting diverse aspects of patient information in healthcare has been prevalent. However, the conventional process of manual note-taking is laborious and can distract healthcare providers from addressing patients’ needs. Prior work by Krishna et al. (2021a) has introduced an end-to-end pipeline for generating SOAP notes, but model-generated notes are susceptible to inaccuracies, irrelevant and missing information. In this work, we assess the performance of large language models (GPT-3.5) for SOAP note generation, compare them with fine-tuned models using automated metrics, and propose a solution to improve the consistency and faithfulness of notes by incorporating attribute-specific information via SOAP section information. To achieve this, we integrate an extra layer of unique section-specific cross-attention parameters to existing encoder-decoder architectures. Our approach is evaluated using a comprehensive suite of automated metrics and expert human evaluators, demonstrating that it leads to more accurate, relevant, and faithful information.
APA
Ramprasad, S., Ferracane, E. & Selvaraj, S.P.. (2023). Generating more faithful and consistent SOAP notes using attribute-specific parameters. Proceedings of the 8th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 219:631-649 Available from https://proceedings.mlr.press/v219/ramprasad23a.html.

Related Material