Cargando…
Knowledge grounded medical dialogue generation using augmented graphs
Smart healthcare systems that make use of abundant health data can improve access to healthcare services, reduce medical costs and provide consistently high-quality patient care. Medical dialogue systems that generate medically appropriate and human-like conversations have been developed using vario...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9969034/ https://www.ncbi.nlm.nih.gov/pubmed/36849466 http://dx.doi.org/10.1038/s41598-023-29213-8 |
_version_ | 1784897632513032192 |
---|---|
author | Varshney, Deeksha Zafar, Aizan Behera, Niranshu Kumar Ekbal, Asif |
author_facet | Varshney, Deeksha Zafar, Aizan Behera, Niranshu Kumar Ekbal, Asif |
author_sort | Varshney, Deeksha |
collection | PubMed |
description | Smart healthcare systems that make use of abundant health data can improve access to healthcare services, reduce medical costs and provide consistently high-quality patient care. Medical dialogue systems that generate medically appropriate and human-like conversations have been developed using various pre-trained language models and a large-scale medical knowledge base based on Unified Medical Language System (UMLS). However, most of the knowledge-grounded dialogue models only use local structure in the observed triples, which suffer from knowledge graph incompleteness and hence cannot incorporate any information from dialogue history while creating entity embeddings. As a result, the performance of such models decreases significantly. To address this problem, we propose a general method to embed the triples in each graph into large-scalable models and thereby generate clinically correct responses based on the conversation history using the recently recently released MedDialog(EN) dataset. Given a set of triples, we first mask the head entities from the triples overlapping with the patient’s utterance and then compute the cross-entropy loss against the triples’ respective tail entities while predicting the masked entity. This process results in a representation of the medical concepts from a graph capable of learning contextual information from dialogues, which ultimately aids in leading to the gold response. We also fine-tune the proposed Masked Entity Dialogue (MED) model on smaller corpora which contain dialogues focusing only on the Covid-19 disease named as the Covid Dataset. In addition, since UMLS and other existing medical graphs lack data-specific medical information, we re-curate and perform plausible augmentation of knowledge graphs using our newly created Medical Entity Prediction (MEP) model. Empirical results on the MedDialog(EN) and Covid Dataset demonstrate that our proposed model outperforms the state-of-the-art methods in terms of both automatic and human evaluation metrics. |
format | Online Article Text |
id | pubmed-9969034 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-99690342023-02-28 Knowledge grounded medical dialogue generation using augmented graphs Varshney, Deeksha Zafar, Aizan Behera, Niranshu Kumar Ekbal, Asif Sci Rep Article Smart healthcare systems that make use of abundant health data can improve access to healthcare services, reduce medical costs and provide consistently high-quality patient care. Medical dialogue systems that generate medically appropriate and human-like conversations have been developed using various pre-trained language models and a large-scale medical knowledge base based on Unified Medical Language System (UMLS). However, most of the knowledge-grounded dialogue models only use local structure in the observed triples, which suffer from knowledge graph incompleteness and hence cannot incorporate any information from dialogue history while creating entity embeddings. As a result, the performance of such models decreases significantly. To address this problem, we propose a general method to embed the triples in each graph into large-scalable models and thereby generate clinically correct responses based on the conversation history using the recently recently released MedDialog(EN) dataset. Given a set of triples, we first mask the head entities from the triples overlapping with the patient’s utterance and then compute the cross-entropy loss against the triples’ respective tail entities while predicting the masked entity. This process results in a representation of the medical concepts from a graph capable of learning contextual information from dialogues, which ultimately aids in leading to the gold response. We also fine-tune the proposed Masked Entity Dialogue (MED) model on smaller corpora which contain dialogues focusing only on the Covid-19 disease named as the Covid Dataset. In addition, since UMLS and other existing medical graphs lack data-specific medical information, we re-curate and perform plausible augmentation of knowledge graphs using our newly created Medical Entity Prediction (MEP) model. Empirical results on the MedDialog(EN) and Covid Dataset demonstrate that our proposed model outperforms the state-of-the-art methods in terms of both automatic and human evaluation metrics. Nature Publishing Group UK 2023-02-27 /pmc/articles/PMC9969034/ /pubmed/36849466 http://dx.doi.org/10.1038/s41598-023-29213-8 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Varshney, Deeksha Zafar, Aizan Behera, Niranshu Kumar Ekbal, Asif Knowledge grounded medical dialogue generation using augmented graphs |
title | Knowledge grounded medical dialogue generation using augmented graphs |
title_full | Knowledge grounded medical dialogue generation using augmented graphs |
title_fullStr | Knowledge grounded medical dialogue generation using augmented graphs |
title_full_unstemmed | Knowledge grounded medical dialogue generation using augmented graphs |
title_short | Knowledge grounded medical dialogue generation using augmented graphs |
title_sort | knowledge grounded medical dialogue generation using augmented graphs |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9969034/ https://www.ncbi.nlm.nih.gov/pubmed/36849466 http://dx.doi.org/10.1038/s41598-023-29213-8 |
work_keys_str_mv | AT varshneydeeksha knowledgegroundedmedicaldialoguegenerationusingaugmentedgraphs AT zafaraizan knowledgegroundedmedicaldialoguegenerationusingaugmentedgraphs AT beheraniranshukumar knowledgegroundedmedicaldialoguegenerationusingaugmentedgraphs AT ekbalasif knowledgegroundedmedicaldialoguegenerationusingaugmentedgraphs |