File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Identification of pediatric respiratory diseases using a fine-grained diagnosis system

TitleIdentification of pediatric respiratory diseases using a fine-grained diagnosis system
Authors
KeywordsRespiratory diseases
Fine-grained diagnosis
Pediatric diagnosis
Clinical notes
Multi-modal
Issue Date2021
PublisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/yjbin
Citation
Journal of Biomedical Informatics, 2021, v. 117, p. article no. 103754 How to Cite?
AbstractRespiratory diseases, including asthma, bronchitis, pneumonia, and upper respiratory tract infection (RTI), are among the most common diseases in clinics. The similarities among the symptoms of these diseases precludes prompt diagnosis upon the patients’ arrival. In pediatrics, the patients’ limited ability in expressing their situation makes precise diagnosis even harder. This becomes worse in primary hospitals, where the lack of medical imaging devices and the doctors’ limited experience further increase the difficulty of distinguishing among similar diseases. In this paper, a pediatric fine-grained diagnosis-assistant system is proposed to provide prompt and precise diagnosis using solely clinical notes upon admission, which would assist clinicians without changing the diagnostic process. The proposed system consists of two stages: a test result structuralization stage and a disease identification stage. The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage. A novel deep learning algorithm was developed for the disease identification stage, where techniques including adaptive feature infusion and multi-modal attentive fusion were introduced to fuse structured and text data together. Clinical notes from over 12000 patients with respiratory diseases were used to train a deep learning model, and clinical notes from a non-overlapping set of about 1800 patients were used to evaluate the performance of the trained model. The average precisions (AP) for pneumonia, RTI, bronchitis and asthma are 0.878, 0.857, 0.714, and 0.825, respectively, achieving a mean AP (mAP) of 0.819. These results demonstrate that our proposed fine-grained diagnosis-assistant system provides precise identification of the diseases.
Persistent Identifierhttp://hdl.handle.net/10722/301456
ISSN
2023 Impact Factor: 4.0
2023 SCImago Journal Rankings: 1.160
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYu, G-
dc.contributor.authorYu, Z-
dc.contributor.authorShi, Y-
dc.contributor.authorWang, Y-
dc.contributor.authorLiu, X-
dc.contributor.authorLi, Z-
dc.contributor.authorZhao, Y-
dc.contributor.authorSun, F-
dc.contributor.authorYu, Y-
dc.contributor.authorShu, Q-
dc.date.accessioned2021-07-27T08:11:21Z-
dc.date.available2021-07-27T08:11:21Z-
dc.date.issued2021-
dc.identifier.citationJournal of Biomedical Informatics, 2021, v. 117, p. article no. 103754-
dc.identifier.issn1532-0464-
dc.identifier.urihttp://hdl.handle.net/10722/301456-
dc.description.abstractRespiratory diseases, including asthma, bronchitis, pneumonia, and upper respiratory tract infection (RTI), are among the most common diseases in clinics. The similarities among the symptoms of these diseases precludes prompt diagnosis upon the patients’ arrival. In pediatrics, the patients’ limited ability in expressing their situation makes precise diagnosis even harder. This becomes worse in primary hospitals, where the lack of medical imaging devices and the doctors’ limited experience further increase the difficulty of distinguishing among similar diseases. In this paper, a pediatric fine-grained diagnosis-assistant system is proposed to provide prompt and precise diagnosis using solely clinical notes upon admission, which would assist clinicians without changing the diagnostic process. The proposed system consists of two stages: a test result structuralization stage and a disease identification stage. The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage. A novel deep learning algorithm was developed for the disease identification stage, where techniques including adaptive feature infusion and multi-modal attentive fusion were introduced to fuse structured and text data together. Clinical notes from over 12000 patients with respiratory diseases were used to train a deep learning model, and clinical notes from a non-overlapping set of about 1800 patients were used to evaluate the performance of the trained model. The average precisions (AP) for pneumonia, RTI, bronchitis and asthma are 0.878, 0.857, 0.714, and 0.825, respectively, achieving a mean AP (mAP) of 0.819. These results demonstrate that our proposed fine-grained diagnosis-assistant system provides precise identification of the diseases.-
dc.languageeng-
dc.publisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/yjbin-
dc.relation.ispartofJournal of Biomedical Informatics-
dc.subjectRespiratory diseases-
dc.subjectFine-grained diagnosis-
dc.subjectPediatric diagnosis-
dc.subjectClinical notes-
dc.subjectMulti-modal-
dc.titleIdentification of pediatric respiratory diseases using a fine-grained diagnosis system-
dc.typeArticle-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.jbi.2021.103754-
dc.identifier.pmid33831537-
dc.identifier.scopuseid_2-s2.0-85104293731-
dc.identifier.hkuros323534-
dc.identifier.volume117-
dc.identifier.spagearticle no. 103754-
dc.identifier.epagearticle no. 103754-
dc.identifier.isiWOS:000663076900008-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats