Need assessment for history-taking instruction program using chatbot for nursing students: A qualitative study using focus group interviews.

Purpose: A comprehensive health history contributes to identifying the most appropriate interventions and care priorities. However, history-taking is challenging to learn and develop for most nursing students. Chatbot was suggested by students to be used in history-taking training. Still, there is a lack of clarity regarding the needs of nursing students in these programs. This study aimed to explore nursing students' needs and essential components of chatbot-based history-taking instruction program. Methods: This was a qualitative study. Four focus groups, with a total of 22 nursing students, were recruited. Colaizzi's phenomenological methodology was used to analyze the qualitative data generated from the focus group discussions. Results: Three main themes and 12 subthemes emerged. The main themes included limitations of clinical practice for history-taking, perceptions of chatbot used in history-taking instruction programs, and the need for history-taking instruction programs using chatbot. Students had limitations in clinical practice for history-taking. When developing chatbot-based history-taking instruction programs, the development should reflect students' needs, including feedback from the chatbot system, diverse clinical situations, chances to practice nontechnical skills, a form of chatbot (i.e., humanoid robots or cyborgs), the role of teachers (i.e., sharing experience and providing advice) and training before the clinical practice. Conclusion: Nursing students had limitations in clinical practice for history-taking and high expectations for chatbot-based history-taking instruction programs.

A real-world data validation of the value of early-stage SIR modelling to public health.

Performance of Susceptible-Infected-Recovered (SIR) model in the early stage of a novel epidemic may be hindered by data availability. Additionally, the traditional SIR model may oversimplify the disease progress, and knowledge about the virus and transmission is limited early in the epidemic, resulting in a greater uncertainty of such modelling. We aimed to investigate the impact of model inputs on the early-stage SIR projection using COVID-19 as an illustration to evaluate the application of early infection models. We constructed a modified SIR model using discrete-time Markov chain to simulate daily epidemic dynamics and estimate the number of beds needed in Wuhan in the early stage of COVID-19 epidemic. We compared eight scenarios of SIR projection to the real-world data (RWD) and used root mean square error (RMSE) to assess model performance. According to the National Health Commission, the number of beds occupied in isolation wards and ICUs due to COVID-19 in Wuhan peaked at 37,746. In our model, as the epidemic developed, we observed an increasing daily new case rate, and decreasing daily removal rate and ICU rate. This change in rates contributed to the growth in the needs of bed in both isolation wards and ICUs. Assuming a 50% diagnosis rate and 70% public health efficacy, the model based on parameters estimated using data from the day reaching 3200 to the day reaching 6400 cases returned a lowest RMSE. This model predicted 22,613 beds needed in isolation ward and ICU as on the day of RWD peak. Very early SIR model predictions based on early cumulative case data initially underestimated the number of beds needed, but the RMSEs tended to decline as more updated data were used. Very-early-stage SIR model, although simple but convenient and relatively accurate, is a useful tool to provide decisive information for the public health system and predict the trend of an epidemic of novel infectious disease in the very early stage, thus, avoiding the issue of delay-decision and extra deaths.

Patients' Preferences for Artificial Intelligence Applications Versus Clinicians in Disease Diagnosis During the SARS-CoV-2 Pandemic in China: Discrete Choice Experiment.

BACKGROUND: Misdiagnosis, arbitrary charges, annoying queues, and clinic waiting times among others are long-standing phenomena in the medical industry across the world. These factors can contribute to patient anxiety about misdiagnosis by clinicians. However, with the increasing growth in use of big data in biomedical and health care communities, the performance of artificial intelligence (Al) techniques of diagnosis is improving and can help avoid medical practice errors, including under the current circumstance of COVID-19. OBJECTIVE: This study aims to visualize and measure patients' heterogeneous preferences from various angles of AI diagnosis versus clinicians in the context of the COVID-19 epidemic in China. We also aim to illustrate the different decision-making factors of the latent class of a discrete choice experiment (DCE) and prospects for the application of AI techniques in judgment and management during the pandemic of SARS-CoV-2 and in the future. METHODS: A DCE approach was the main analysis method applied in this paper. Attributes from different dimensions were hypothesized: diagnostic method, outpatient waiting time, diagnosis time, accuracy, follow-up after diagnosis, and diagnostic expense. After that, a questionnaire is formed. With collected data from the DCE questionnaire, we apply Sawtooth software to construct a generalized multinomial logit (GMNL) model, mixed logit model, and latent class model with the data sets. Moreover, we calculate the variables' coefficients, standard error, P value, and odds ratio (OR) and form a utility report to present the importance and weighted percentage of attributes. RESULTS: A total of 55.8% of the respondents (428 out of 767) opted for AI diagnosis regardless of the description of the clinicians. In the GMNL model, we found that people prefer the 100% accuracy level the most (OR 4.548, 95% CI 4.048-5.110, P<.001). For the latent class model, the most acceptable model consists of 3 latent classes of respondents. The attributes with the most substantial effects and highest percentage weights are the accuracy (39.29% in general) and expense of diagnosis (21.69% in general), especially the preferences for the diagnosis "accuracy" attribute, which is constant across classes. For class 1 and class 3, people prefer the AI + clinicians method (class 1: OR 1.247, 95% CI 1.036-1.463, P<.001; class 3: OR 1.958, 95% CI 1.769-2.167, P<.001). For class 2, people prefer the AI method (OR 1.546, 95% CI 0.883-2.707, P=.37). The OR of levels of attributes increases with the increase of accuracy across all classes. CONCLUSIONS: Latent class analysis was prominent and useful in quantifying preferences for attributes of diagnosis choice. People's preferences for the "accuracy" and "diagnostic expenses" attributes are palpable. AI will have a potential market. However, accuracy and diagnosis expenses need to be taken into consideration.