Preferences for Artificial Intelligence Clinicians Before and During the COVID-19 Pandemic: Discrete Choice Experiment and Propensity Score Matching Study.

BACKGROUND: Artificial intelligence (AI) methods can potentially be used to relieve the pressure that the COVID-19 pandemic has exerted on public health. In cases of medical resource shortages caused by the pandemic, changes in people's preferences for AI clinicians and traditional clinicians are worth exploring. OBJECTIVE: We aimed to quantify and compare people's preferences for AI clinicians and traditional clinicians before and during the COVID-19 pandemic, and to assess whether people's preferences were affected by the pressure of pandemic. METHODS: We used the propensity score matching method to match two different groups of respondents with similar demographic characteristics. Respondents were recruited in 2017 and 2020. A total of 2048 respondents (2017: n=1520; 2020: n=528) completed the questionnaire and were included in the analysis. Multinomial logit models and latent class models were used to assess people's preferences for different diagnosis methods. RESULTS: In total, 84.7% (1115/1317) of respondents in the 2017 group and 91.3% (482/528) of respondents in the 2020 group were confident that AI diagnosis methods would outperform human clinician diagnosis methods in the future. Both groups of matched respondents believed that the most important attribute of diagnosis was accuracy, and they preferred to receive combined diagnoses from both AI and human clinicians (2017: odds ratio [OR] 1.645, 95% CI 1.535-1.763; P<.001; 2020: OR 1.513, 95% CI 1.413-1.621; P<.001; reference: clinician diagnoses). The latent class model identified three classes with different attribute priorities. In class 1, preferences for combined diagnoses and accuracy remained constant in 2017 and 2020, and high accuracy (eg, 100% accuracy in 2017: OR 1.357, 95% CI 1.164-1.581) was preferred. In class 2, the matched data from 2017 were similar to those from 2020; combined diagnoses from both AI and human clinicians (2017: OR 1.204, 95% CI 1.039-1.394; P=.011; 2020: OR 2.009, 95% CI 1.826-2.211; P<.001; reference: clinician diagnoses) and an outpatient waiting time of 20 minutes (2017: OR 1.349, 95% CI 1.065-1.708; P<.001; 2020: OR 1.488, 95% CI 1.287-1.721; P<.001; reference: 0 minutes) were consistently preferred. In class 3, the respondents in the 2017 and 2020 groups preferred different diagnosis methods; respondents in the 2017 group preferred clinician diagnoses, whereas respondents in the 2020 group preferred AI diagnoses. In the latent class, which was stratified according to sex, all male and female respondents in the 2017 and 2020 groups believed that accuracy was the most important attribute of diagnosis. CONCLUSIONS: Individuals' preferences for receiving clinical diagnoses from AI and human clinicians were generally unaffected by the pandemic. Respondents believed that accuracy and expense were the most important attributes of diagnosis. These findings can be used to guide policies that are relevant to the development of AI-based health care.

Health Communication Through News Media During the Early Stage of the COVID-19 Outbreak in China: Digital Topic Modeling Approach.

BACKGROUND: In December 2019, a few coronavirus disease (COVID-19) cases were first reported in Wuhan, Hubei, China. Soon after, increasing numbers of cases were detected in other parts of China, eventually leading to a disease outbreak in China. As this dreadful disease spreads rapidly, the mass media has been active in community education on COVID-19 by delivering health information about this novel coronavirus, such as its pathogenesis, spread, prevention, and containment. OBJECTIVE: The aim of this study was to collect media reports on COVID-19 and investigate the patterns of media-directed health communications as well as the role of the media in this ongoing COVID-19 crisis in China. METHODS: We adopted the WiseSearch database to extract related news articles about the coronavirus from major press media between January 1, 2020, and February 20, 2020. We then sorted and analyzed the data using Python software and Python package Jieba. We sought a suitable topic number with evidence of the coherence number. We operated latent Dirichlet allocation topic modeling with a suitable topic number and generated corresponding keywords and topic names. We then divided these topics into different themes by plotting them into a 2D plane via multidimensional scaling. RESULTS: After removing duplications and irrelevant reports, our search identified 7791 relevant news reports. We listed the number of articles published per day. According to the coherence value, we chose 20 as the number of topics and generated the topics' themes and keywords. These topics were categorized into nine main primary themes based on the topic visualization figure. The top three most popular themes were prevention and control procedures, medical treatment and research, and global or local social and economic influences, accounting for 32.57% (n=2538), 16.08% (n=1258), and 11.79% (n=919) of the collected reports, respectively. CONCLUSIONS: Topic modeling of news articles can produce useful information about the significance of mass media for early health communication. Comparing the number of articles for each day and the outbreak development, we noted that mass media news reports in China lagged behind the development of COVID-19. The major themes accounted for around half the content and tended to focus on the larger society rather than on individuals. The COVID-19 crisis has become a worldwide issue, and society has become concerned about donations and support as well as mental health among others. We recommend that future work addresses the mass media's actual impact on readers during the COVID-19 crisis through sentiment analysis of news data.