On the Generation of Medical Dialogues for COVID-19

  1. Wenmian Yang
  2. Guangtao Zeng
  3. Bowen Tan
  4. Zeqian Ju
  5. Subrato Chakravorty
  6. Xuehai He
  7. Shu Chen
  8. Xingyi Yang
  9. Qingyang Wu
  10. Zhou Yu
  11. Eric Xing
  12. Pengtao Xie

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure, a lot of consulting services have been moved online. Because of the shortage of medical professionals, many people cannot receive online consultations timely. To address this problem, we aim to develop a medical dialogue system that can provide COVID19-related consultations. We collected two dialogue datasets – CovidDialog – (in English and Chinese respectively) containing conversations between doctors and patients about COVID-19. On these two datasets, we train several dialogue generation models based on Transformer, GPT, and BERT-GPT. Since the two COVID-19 dialogue datasets are small in size, which bear high risk of overfitting, we leverage transfer learning to mitigate data deficiency. Specifically, we take the pretrained models of Transformer, GPT, and BERT-GPT on dialog datasets and other large-scale texts, then finetune them on our CovidDialog datasets. Experiments demonstrate that these approaches are promising in generating meaningful medical dialogues about COVID-19. But more advanced approaches are needed to build a fully useful dialogue system that can offer accurate COVID-related consultations. The data and code are available at https://github.com/UCSD-AI4H/COVID-Dialogue

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.05.08.20095810: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    To solve this problem, we utilize transfer learning, which pretrains the neural models on large corpus, then finetunes the pretrained models on the CovidDialog datasets. 3.1. Transformer: Generating response t from the conversation history s is a typical sequence-to-sequence (seq2seq) (Sutskever et al., 2014) modeling problem.
    CovidDialog
    suggested: None
    Auto-Regressive Transformers (BART) (Lewis et al., 2019) has a similar architecture as BERT-GPT, but trains the BERT encoder and GPT decoder jointly.
    BERT
    suggested: (BERT, RRID:SCR_018008)

    Results from OddPub: Thank you for sharing your code and data.

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  2. Version published to 10.1101/2020.05.08.20095810v1 on medRxiv