21
views
0
recommends
+1 Recommend
1 collections
    0
    shares

      Submit your digital health research with an established publisher
      - celebrating 25 years of open access

      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      End-to-End Models to Imitate Traditional Chinese Medicine Syndrome Differentiation in Lung Cancer Diagnosis: Model Development and Validation

      research-article

      Read this article at

      ScienceOpenPublisherPMC
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Traditional Chinese medicine (TCM) has been shown to be an efficient mode to manage advanced lung cancer, and accurate syndrome differentiation is crucial to treatment. Documented evidence of TCM treatment cases and the progress of artificial intelligence technology are enabling the development of intelligent TCM syndrome differentiation models. This is expected to expand the benefits of TCM to lung cancer patients.

          Objective

          The objective of this work was to establish end-to-end TCM diagnostic models to imitate lung cancer syndrome differentiation. The proposed models used unstructured medical records as inputs to capitalize on data collected for practical TCM treatment cases by lung cancer experts. The resulting models were expected to be more efficient than approaches that leverage structured TCM datasets.

          Methods

          We approached lung cancer TCM syndrome differentiation as a multilabel text classification problem. First, entity representation was conducted with Bidirectional Encoder Representations from Transformers and conditional random fields models. Then, five deep learning–based text classification models were applied to the construction of a medical record multilabel classifier, during which two data augmentation strategies were adopted to address overfitting issues. Finally, a fusion model approach was used to elevate the performance of the models.

          Results

          The F1 score of the recurrent convolutional neural network (RCNN) model with augmentation was 0.8650, a 2.41% improvement over the unaugmented model. The Hamming loss for RCNN with augmentation was 0.0987, which is 1.8% lower than that of the same model without augmentation. Among the models, the text-hierarchical attention network (Text-HAN) model achieved the highest F1 scores of 0.8676 and 0.8751. The mean average precision for the word encoding–based RCNN was 10% higher than that of the character encoding–based representation. A fusion model of the text-convolutional neural network, text-recurrent neural network, and Text-HAN models achieved an F1 score of 0.8884, which showed the best performance among the models.

          Conclusions

          Medical records could be used more productively by constructing end-to-end models to facilitate TCM diagnosis. With the aid of entity-level representation, data augmentation, and model fusion, deep learning–based multilabel classification approaches can better imitate TCM syndrome differentiation in complex cases such as advanced lung cancer.

          Related collections

          Most cited references24

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Bag of Tricks for Efficient Text Classification

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found
            Is Open Access

            Syndrome differentiation in modern research of traditional Chinese medicine.

            Syndrome differentiation (Bian Zheng) in traditional Chinese medicine (TCM) is the comprehensive analysis of clinical information gained by the four main diagnostic TCM procedures: observation, listening, questioning, and pulse analysis, and it is used to guide the choice of treatment either by acupuncture and/or TCM herbal formulae, that is, Fufang. TCM syndrome differentiation can be used for further stratification of the patients' conditions with certain disease, identified by orthodox medical diagnosis, which could help the improvement of efficacy of the selected intervention. In modern TCM research it is possible to integrate syndrome differentiation with orthodox medical diagnosis leading to new scientific findings in overall medical diagnosis and treatment. In this review, the focus is to screen published evidence on the role of syndrome differentiation in modern TCM research with particular emphasis on basic and clinical research as well as, pharmacological evaluation of TCM herbal formulary for drug discovery. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Traditional Chinese medicine and cancer: History, present situation, and development

              Cancer treatment with traditional Chinese medicine (TCM) has a long history. Heritage provides general conditions for the innovation and development of TCM in oncology. This article reviews the development of TCM in oncology, interprets the position and function of TCM for cancer prevention and treatment, summarizes the innovations of TCM in oncology over nearly fifty years, and suggests the development direction.
                Bookmark

                Author and article information

                Contributors
                Journal
                JMIR Med Inform
                JMIR Med Inform
                JMI
                JMIR Medical Informatics
                JMIR Publications (Toronto, Canada )
                2291-9694
                June 2020
                16 June 2020
                : 8
                : 6
                : e17821
                Affiliations
                [1 ] Second School of Clinic Medicine Guangzhou University of Chinese Medicine Guangzhou China
                [2 ] School of Artifical Intelligence and Information Techology Nanjing University of Chinese Medicine Nanjing China
                [3 ] Shanghai Bright AI Co, Ltd Shanghai China
                [4 ] Shanghai Literature Institute of Traditional Chinese Medicine Shanghai China
                Author notes
                Corresponding Author: Tao Yang taoyang1111@ 123456126.com
                Author information
                https://orcid.org/0000-0002-4964-7177
                https://orcid.org/0000-0001-6422-0692
                https://orcid.org/0000-0002-3399-1942
                https://orcid.org/0000-0003-2674-5476
                https://orcid.org/0000-0002-9537-0500
                https://orcid.org/0000-0001-5568-0347
                Article
                v8i6e17821
                10.2196/17821
                7327597
                32543445
                e4b0b292-e027-4591-96b0-e7d2b1aa0d33
                ©Ziqing Liu, Haiyang He, Shixing Yan, Yong Wang, Tao Yang, Guo-Zheng Li. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 16.06.2020.

                This is an open-access article distributed under the terms of the Creative Commons Attribution License ( https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on http://medinform.jmir.org/, as well as this copyright and license information must be included.

                History
                : 15 January 2020
                : 25 February 2020
                : 30 March 2020
                : 11 April 2020
                Categories
                Original Paper
                Original Paper

                traditional chinese medicine,syndrome differentiation,lung cancer,medical record,deep learning,model fusion

                Comments

                Comment on this article