Alleviating the medical strain: a triage method via cross-domain text classification
It is a universal phenomenon for patients who do not know which clinical department to register in large general hospitals. Although triage nurses can help patients, due to the larger number of patients, they have to stand in a queue for minutes to consult. Recently, there have already been some eff...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-12-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2024.1468519/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850251008480903168 |
|---|---|
| author | Xiao Xiao Shuqin Wang Feng Jiang Tingyue Qi Wei Wang |
| author_facet | Xiao Xiao Shuqin Wang Feng Jiang Tingyue Qi Wei Wang |
| author_sort | Xiao Xiao |
| collection | DOAJ |
| description | It is a universal phenomenon for patients who do not know which clinical department to register in large general hospitals. Although triage nurses can help patients, due to the larger number of patients, they have to stand in a queue for minutes to consult. Recently, there have already been some efforts to devote deep-learning techniques or pre-trained language models (PLMs) to triage recommendations. However, these methods may suffer two main limitations: (1) These methods typically require a certain amount of labeled or unlabeled data for model training, which are not always accessible and costly to acquire. (2) These methods have not taken into account the distortion of semantic feature structure and the loss of category discriminability in the model training. To overcome these limitations, in this study, we propose a cross-domain text classification method based on prompt-tuning, which can classify patients' questions or texts about their symptoms into several given categories to give suggestions on which kind of consulting room patients could choose. Specifically, first, different prompt templates are manually crafted based on various data contents, embedding source domain information into the prompt templates to generate another text with similar semantic feature structures for performing classification tasks. Then, five different strategies are employed to expand the label word space for modifying prompts, and the integration of these strategies is used as the final verbalizer. The extensive experiments on Chinese Triage datasets demonstrate that our method achieved state-of-the-art performance. |
| format | Article |
| id | doaj-art-0e8618ae194e4917b1cddca21ee60faa |
| institution | OA Journals |
| issn | 1662-5188 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj-art-0e8618ae194e4917b1cddca21ee60faa2025-08-20T01:58:00ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882024-12-011810.3389/fncom.2024.14685191468519Alleviating the medical strain: a triage method via cross-domain text classificationXiao Xiao0Shuqin Wang1Feng Jiang2Tingyue Qi3Wei Wang4Department of Ultrasound, The Affiliated Hospital of Yangzhou University, Yangzhou University, Yangzhou, Jiangsu, ChinaDepartment of Information Engineering, Yangzhou University, Yangzhou, Jiangsu, ChinaDepartment of Ultrasound, The First Affiliated Hospital of Wannan Medical College, Wuhu, Anhui, ChinaDepartment of Ultrasound, The Affiliated Hospital of Yangzhou University, Yangzhou University, Yangzhou, Jiangsu, ChinaDepartment of Radiology, The Affiliated Hospital of Yangzhou University, Yangzhou University, Yangzhou, Jiangsu, ChinaIt is a universal phenomenon for patients who do not know which clinical department to register in large general hospitals. Although triage nurses can help patients, due to the larger number of patients, they have to stand in a queue for minutes to consult. Recently, there have already been some efforts to devote deep-learning techniques or pre-trained language models (PLMs) to triage recommendations. However, these methods may suffer two main limitations: (1) These methods typically require a certain amount of labeled or unlabeled data for model training, which are not always accessible and costly to acquire. (2) These methods have not taken into account the distortion of semantic feature structure and the loss of category discriminability in the model training. To overcome these limitations, in this study, we propose a cross-domain text classification method based on prompt-tuning, which can classify patients' questions or texts about their symptoms into several given categories to give suggestions on which kind of consulting room patients could choose. Specifically, first, different prompt templates are manually crafted based on various data contents, embedding source domain information into the prompt templates to generate another text with similar semantic feature structures for performing classification tasks. Then, five different strategies are employed to expand the label word space for modifying prompts, and the integration of these strategies is used as the final verbalizer. The extensive experiments on Chinese Triage datasets demonstrate that our method achieved state-of-the-art performance.https://www.frontiersin.org/articles/10.3389/fncom.2024.1468519/fullmedical triagecross-domain text classificationprompt-tuningfew-shotdomain adaptation |
| spellingShingle | Xiao Xiao Shuqin Wang Feng Jiang Tingyue Qi Wei Wang Alleviating the medical strain: a triage method via cross-domain text classification Frontiers in Computational Neuroscience medical triage cross-domain text classification prompt-tuning few-shot domain adaptation |
| title | Alleviating the medical strain: a triage method via cross-domain text classification |
| title_full | Alleviating the medical strain: a triage method via cross-domain text classification |
| title_fullStr | Alleviating the medical strain: a triage method via cross-domain text classification |
| title_full_unstemmed | Alleviating the medical strain: a triage method via cross-domain text classification |
| title_short | Alleviating the medical strain: a triage method via cross-domain text classification |
| title_sort | alleviating the medical strain a triage method via cross domain text classification |
| topic | medical triage cross-domain text classification prompt-tuning few-shot domain adaptation |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2024.1468519/full |
| work_keys_str_mv | AT xiaoxiao alleviatingthemedicalstrainatriagemethodviacrossdomaintextclassification AT shuqinwang alleviatingthemedicalstrainatriagemethodviacrossdomaintextclassification AT fengjiang alleviatingthemedicalstrainatriagemethodviacrossdomaintextclassification AT tingyueqi alleviatingthemedicalstrainatriagemethodviacrossdomaintextclassification AT weiwang alleviatingthemedicalstrainatriagemethodviacrossdomaintextclassification |