Background: The application of large language models in clinical decision support (CDS) is an area that warrants further investigation. ChatGPT, a prominent large language models developed by OpenAI, has shown promising performance across various domains. However, there is limited research evaluating its use specifically in pediatric clinical decision-making. This study aimed to assess ChatGPT’s potential as a CDS tool in pediatrics by evCDSaluating its performance on 8 common clinical symptom prompts. Study objectives were to answer the 2 research questions: the ChatGPT’s overall grade in a range from A (high) to E (low) compared to a normal sample and the difference in assessment of ChatGPT between 2 pediatricians. Methods: We compared ChatGPT’s responses to 8 items related to clinical symptoms commonly encountered by pediatricians. Two pediatricians independently assessed the answers provided by ChatGPT in an open-ended format. The scoring system ranged from 0 to 100, which was then transformed into 5 ordinal categories. We simulated 300 virtual students with a normal distribution to provide scores on items based on Rasch rating scale model and their difficulties in a range between −2 to 2.5 logits. Two visual presentations (Wright map and KIDMAP) were generated to answer the 2 research questions outlined in the objectives of the study. Results: The 2 pediatricians’ assessments indicated that ChatGPT’s overall performance corresponded to a grade of C in a range from A to E, with average scores of −0.89 logits and 0.90 logits (=log odds), respectively. The assessments revealed a significant difference in performance between the 2 pediatricians (P < .05), with scores of −0.89 (SE = 0.37) and 0.90 (SE = 0.41) in log odds units (logits in Rasch analysis). Conclusion: This study demonstrates the feasibility of utilizing ChatGPT as a CDS tool for patients presenting with common pediatric symptoms. The findings suggest that ChatGPT has the potential to enhance clinical workflow and aid in responsible clinical decision-making. Further exploration and refinement of ChatGPT’s capabilities in pediatric care can potentially contribute to improved healthcare outcomes and patient management.

Background: Many previous papers have investigated most-cited articles or most productive authors in academics, but few have studied most-cited authors. Two challenges are faced in doing so, one of which is that some different authors will have the same name in the bibliometric data, and the second is that coauthors’ contributions are different in the article byline. No study has dealt with the matter of duplicate names in bibliometric data. Although betweenness centrality (BC) is one of the most popular degrees of density in social network analysis (SNA), few have applied the BC algorithm to interpret a network’s characteristics. A quantitative scheme must be used for calculating weighted author credits and then applying the metrics in comparison. Objective: This study aimed to apply the BC algorithm to examine possible identical names in a network and report the most-cited authors for a journal related to international mobile health (mHealth) research. Methods: We obtained 676 abstracts from Medline based on the keywords “JMIR mHealth and uHealth” (Journal) on June 30, 2018. The author names, countries/areas, and author-defined keywords were recorded. The BCs were then calculated for the following: (1) the most-cited authors displayed on Google Maps; (2) the geographical distribution of countries/areas for the first author; and (3) the keywords dispersed by BC and related to article topics in comparison on citation indices. Pajek software was used to yield the BC for each entity (or node). Bibliometric indices, including h-, g-, and x-indexes, the mean of core articles on g(Ag)=sum (citations on g-core/publications on g-core), and author impact factor (AIF), were applied. Results: We found that the most-cited author was Sherif M Badawy (from the United States), who had published six articles on JMIR mHealth and uHealth with high bibliometric indices (h=3; AIF=8.47; x=4.68; Ag=5.26). We also found that the two countries with the highest BC were the United States and the United Kingdom and that the two keyword clusters of mHealth and telemedicine earned the highest indices in comparison to other counterparts. All visual representations were successfully displayed on Google Maps. Conclusions: The most cited authors were selected using the authorship-weighted scheme (AWS), and the keywords of mHealth and telemedicine were more highly cited than other counterparts. The results on Google Maps are novel and unique as knowledge concept maps for understanding the feature of a journal. The research approaches used in this study (ie, BC and AWS) can be applied to other bibliometric analyses in the future.

The COVID-19 pandemic has spread widely around the world. Many mathematical models have been proposed to investigate the inflection point (IP) and the spread pattern of COVID-19. However, no researchers have applied social network analysis (SNA) to cluster their characteristics. We aimed to illustrate the use of SNA to identify the spread clusters of COVID-19. Cumulative numbers of infected cases (CNICs) in countries/regions were downloaded from GitHub. The CNIC patterns were extracted from SNA based on CNICs between countries/regions. The item response model (IRT) was applied to create a general predictive model for each country/region. The IP days were obtained from the IRT model. The location parameters in continents, China, and the United States were compared. The results showed that (1) three clusters (255, n = 51, 130, and 74 in patterns from Eastern Asia and Europe to America) were separated using SNA, (2) China had a shorter mean IP and smaller mean location parameter than other counterparts, and (3) an online dashboard was used to display the clusters along with IP days for each country/region. Spatiotemporal spread patterns can be clustered using SNA and correlation coefficients (CCs). A dashboard with spread clusters and IP days is recommended to epidemiologists and researchers and is not limited to the COVID-19 pandemic.

Background: Burnout (BO), a critical syndrome particularly for nurses in health care settings, substantially affects their physical and psychological status, the institute’s well-being, and indirectly, patient outcomes. However, objectively classifying BO levels has not been defined and noticed in the literature. Objective: The aim of this study is to build a model using the convolutional neural network (CNN) to develop an app for automatic detection and classification of nurse BO using the Maslach Burnout Inventory–Human Services Survey (MBI-HSS) to help assess nurse BO at an earlier stage. Methods: We recruited 1002 nurses working in a medical center in Taiwan to complete the Chinese version of the 20-item MBI-HSS in August 2016. The k-mean and CNN were used as unsupervised and supervised learnings for dividing nurses into two classes (n=531 and n=471 of suspicious BO+ and BO−, respectively) and building a BO predictive model to estimate 38 parameters. Data were separated into training and testing sets in a proportion 70%:30%, and the former was used to predict the latter. We calculated the sensitivity, specificity, and receiver operating characteristic curve (area under the curve) across studies for comparison. An app predicting respondent BO was developed involving the model’s 38 estimated parameters for a website assessment. Results: We observed that (1) the 20-item model yields a higher accuracy rate (0.95) with an area under the curve of 0.97 (95% CI 0.94-0.95) based on the 1002 cases, (2) the scheme named matching personal response to adapt for the correct classification in model drives the prior model’s predictive accuracy at 100%, (3) the 700-case training set with 0.96 accuracy predicts the 302-case testing set reaching an accuracy of 0.91, and (4) an available MBI-HSS app for nurses predicting BO was successfully developed and demonstrated in this study. Conclusions: The 20-item model with the 38 parameters estimated by using CNN for improving the accuracy of nurse BO has been particularly demonstrated in Excel (Microsoft Corp). An app developed for helping nurses to self-assess job BO at an early stage is required for application in the future.

The COronaVIrus Disease 2019 (COVID-19), which developed into a pandemic in 2020, has become a major healthcare challenge for governments and healthcare workers worldwide. Despite several medical treatment protocols having been established, a comprehensive rehabilitation program that can promote functional recovery is still frequently ignored. An online consensus meeting of an expert panel comprising members of the Taiwan Academy of Cardiovascular and Pulmonary Rehabilitation was held to provide recommendations for rehabilitation protocols in each of the five COVID-19 stages, namely (1) outpatients with mild disease and no risk factors, (2) outpatients with mild disease and epidemiological risk factors, (3) hospitalized patients with moderate to severe disease, (4) ventilator-supported patients with clear cognitive function, and (5) ventilator-supported patients with impaired cognitive function. Apart from medications and life support care, a proper rehabilitation protocol that facilitates recovery from COVID-19 needs to be established and emphasized in clinical practice.

Severe dengue outbreaks (DOs) affect the majority of Asian and Latin American countries. Whether all DOs always occurred in sub-tropical and tropical areas (STTA) has not been verified. We downloaded abstracts by searching keywords “dengue (MeSH Major Topic)” from Pubmed Central since 1950, including three collections: country names in abstracts (CNA), no abstracts (WA), and no country names in abstracts (Non-CNA). Visualizations were created to present the DOs across countries/areas in STTA. The percentages of mentioned country names and authors’ countries in STTA were computed on the CNA and Non-CNA bases. The social network analysis was applied to highlight the most cited articles and countries. We found that (1) three collections are 3427 (25.48%), 3137 (23.33%), and 6884 (51.19%) in CNA, WA, and Non-CNA, respectively; (2) the percentages of 94.3% and 79.9% were found in the CNA and Non-CNA groups; (3) the most mentioned country in abstracts were India, Thailand, and Brazil; (4) most authors in the Non-CNA collections were from the United States, Brazil, and China; (5) the most cited article (PMID = 23563266) authored by Bhatt et al. had 2604 citations since 2013. Our findings provide in-depth insights into the DO knowledge. The research approaches are recommended for authors in research on other infectious diseases in the future, not just limited to the DO topic.