{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T20:57:11Z","timestamp":1786481831445,"version":"3.56.0"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:00:00Z","timestamp":1668988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71991471"],"award-info":[{"award-number":["71991471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6217020551"],"award-info":[{"award-number":["6217020551"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["20dz1200600"],"award-info":[{"award-number":["20dz1200600"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["21QA1400600"],"award-info":[{"award-number":["21QA1400600"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Lab","award":["2019KD0AD01"],"award-info":[{"award-number":["2019KD0AD01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Symptom-based automatic diagnostic system queries the patient\u2019s potential symptoms through continuous interaction with the patient and makes predictions about possible diseases. A few studies use reinforcement learning (RL) to learn the optimal policy from the joint action space of symptoms and diseases. However, existing RL (or Non-RL) methods focus on disease diagnosis while ignoring the importance of symptom inquiry. Although these systems have achieved considerable diagnostic accuracy, they are still far below its performance upper bound due to few turns of interaction with patients and insufficient performance of symptom inquiry. To address this problem, we propose a new automatic diagnostic framework called DxFormer, which decouples symptom inquiry and disease diagnosis, so that these two modules can be independently optimized. The transition from symptom inquiry to disease diagnosis is parametrically determined by the stopping criteria. In DxFormer, we treat each symptom as a token, and formalize the symptom inquiry and disease diagnosis to a language generation model and a sequence classification model, respectively. We use the inverted version of Transformer, i.e. the decoder\u2013encoder structure, to learn the representation of symptoms by jointly optimizing the reinforce reward and cross-entropy loss.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We conduct experiments on three real-world medical dialogue datasets, and the experimental results verify the feasibility of increasing diagnostic accuracy by improving symptom recall. Our model overcomes the shortcomings of previous RL-based methods. By decoupling symptom query from the process of diagnosis, DxFormer greatly improves the symptom recall and achieves the state-of-the-art diagnostic accuracy.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Both code and data are available at https:\/\/github.com\/lemuria-wchen\/DxFormer.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac744","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T13:30:33Z","timestamp":1669037433000},"source":"Crossref","is-referenced-by-count":16,"title":["DxFormer: a decoupled automatic diagnostic system based on decoder\u2013encoder transformer with dense symptom representations"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9431-9247","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"first","affiliation":[{"name":"School of Data Science, Fudan University , Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University , Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajie","family":"Peng","sequence":"additional","affiliation":[{"name":"Research Institute of Automatic and Complex Systems, Fudan University , Shanghai 200433, China"},{"name":"School of Computer Science, Northwestern Polytechnical University , Xi\u2019an 710000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyu","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University , Shanghai 200433, China"},{"name":"Research Institute of Automatic and Complex Systems, Fudan University , Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,11,21]]},"reference":[{"key":"2023010805380062200_btac744-B1","doi-asserted-by":"crossref","first-page":"679","DOI":"10.28991\/ESJ-2022-06-04-02","article-title":"Associated patterns and predicting model of life trauma, depression, and suicide using ensemble machine learning","volume":"6","author":"Aekwarangkoon","year":"2022","journal-title":"Emerg. Sci. J"},{"key":"2023010805380062200_btac744-B2","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"Bengio","year":"2003","journal-title":"J. Mach. Learn. Res"},{"key":"2023010805380062200_btac744-B3","first-page":"4432","author":"Chen","year":"2022"},{"key":"2023010805380062200_btac744-B5","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support vector machine","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn"},{"key":"2023010805380062200_btac744-B6","author":"Devlin","year":"2019"},{"key":"2023010805380062200_btac744-B7","first-page":"2511","author":"He","year":"2022"},{"key":"2023010805380062200_btac744-B8","doi-asserted-by":"crossref","first-page":"1587","DOI":"10.1007\/s10994-020-05874-8","article-title":"Classification with costly features as a sequential decision-making problem","volume":"109","author":"Janisch","year":"2020","journal-title":"Mach. Learn"},{"key":"2023010805380062200_btac744-B9","first-page":"2305","author":"Kao","year":"2018"},{"key":"2023010805380062200_btac744-B10","first-page":"153","article-title":"Prediction of covid-19 confirmed cases after vaccination: based on statistical and deep learning models","volume":"3","author":"Kim","year":"2021","journal-title":"Sci. Med. J"},{"key":"2023010805380062200_btac744-B11","author":"Kingma","year":"2015"},{"key":"2023010805380062200_btac744-B12","author":"Li","year":"2016"},{"key":"2023010805380062200_btac744-B14","first-page":"5033","author":"Lin","year":"2019"},{"key":"2023010805380062200_btac744-B15","doi-asserted-by":"crossref","first-page":"105290","DOI":"10.1016\/j.knosys.2019.105290","article-title":"Adaptive early classification of temporal sequences using deep reinforcement learning","volume":"190","author":"Martinez","year":"2020","journal-title":"Knowl. Based Syst"},{"key":"2023010805380062200_btac744-B16","author":"Mnih","year":"2015"},{"key":"2023010805380062200_btac744-B17","first-page":"7322","article-title":"Refuel: exploring sparse features in deep reinforcement learning for fast disease diagnosis","volume":"31","author":"Peng","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2023010805380062200_btac744-B18","author":"Radford","year":"2018"},{"key":"2023010805380062200_btac744-B19","author":"Ranzato","year":"2016"},{"key":"2023010805380062200_btac744-B20","first-page":"7008","author":"Rennie","year":"2017"},{"key":"2023010805380062200_btac744-B21","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"2023010805380062200_btac744-B22","author":"Tang","year":"2016"},{"key":"2023010805380062200_btac744-B23","first-page":"201","author":"Wei","year":"2018"},{"key":"2023010805380062200_btac744-B24","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn"},{"key":"2023010805380062200_btac744-B25","first-page":"1062","author":"Xia","year":"2020"},{"key":"2023010805380062200_btac744-B26","first-page":"7346","author":"Xu","year":"2019"},{"key":"2023010805380062200_btac744-B28","first-page":"9241","author":"Zeng","year":"2020"},{"key":"2023010805380062200_btac744-B29","doi-asserted-by":"crossref","first-page":"3995","DOI":"10.1093\/bioinformatics\/btac408","article-title":"Hierarchical reinforcement learning for automatic disease diagnosis","volume":"38","author":"Zhong","year":"2022","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac744\/47804760\/btac744.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac744\/48520906\/btac744.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac744\/48520906\/btac744.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T05:38:21Z","timestamp":1673156301000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac744\/6835407"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,11,21]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac744","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,11,21]]},"article-number":"btac744"}}