Background: The integration of artificial intelligence (AI), notably ChatGPT, into medical education, has shown promising results in various medical fields. Nevertheless, its efficacy in traditional Chinese medicine (TCM) examinations remains understudied. Objective: This study aims to (1) assess the performance of ChatGPT on the TCM licensing examination in Taiwan and (2) evaluate the model’s explainability in answering TCM-related questions to determine its suitability as a TCM learning tool. Methods: We used the GPT-4 model to respond to 480 questions from the 2022 TCM licensing examination. This study compared the performance of the model against that of licensed TCM doctors using 2 approaches, namely direct answer selection and provision of explanations before answer selection. The accuracy and consistency of AI-generated responses were analyzed. Moreover, a breakdown of question characteristics was performed based on the cognitive level, depth of knowledge, types of questions, vignette style, and polarity of questions. Results: ChatGPT achieved an overall accuracy of 43.9%, which was lower than that of 2 human participants (70% and 78.4%). The analysis did not reveal a significant correlation between the accuracy of the model and the characteristics of the questions. An in-depth examination indicated that errors predominantly resulted from a misunderstanding of TCM concepts (55.3%), emphasizing the limitations of the model with regard to its TCM knowledge base and reasoning capability. Conclusions: Although ChatGPT shows promise as an educational tool, its current performance on TCM licensing examinations is lacking. This highlights the need for enhancing AI models with specialized TCM training and suggests a cautious approach to utilizing AI for TCM education. Future research should focus on model improvement and the development of tailored educational applications to support TCM learning.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) caused a global pandemic in 2019—coronavirus disease (COVID-19). More and more Western medicine (WM) and Chinese herbal medicine (CHM) treatments have been used to treat COVID-19 patients, especially among Asian populations. However, the interactions between WM and CHM have not been studied. This study aims at using the network pharmacology approach to explore the potential complementary effects among commonly used CHM and WM in a clinical setting from a biomolecular perspective. Three well-published and widely used CHM formulas (National Research Institute of Chinese Medicine 101 (NRICM101), Qing-Fei-Pai-Du-Tang (QFPDT), Hua-Shi-Bai-Du-Formula (HSBDF)) and six categories of WM (Dexamethasone, Janus kinase inhibitors (JAKi), Anti-Interleukin-6 (Anti-IL6), anticoagulants, non-vitamin K antagonist oral anticoagulants (NOAC), and Aspirin) were included in the network pharmacology analysis. The target proteins on which these CHM and WM had direct effects were acquired from the STITCH database, and the potential molecular pathways were found in the REACTOME database. The COVID-19-related target proteins were obtained from the TTD database. For the three CHM formulas, QFPDT covered the most proteins (714), and 27 of them were COVID-19-related, while HSBDF and NRICM101 covered 624 (24 COVID-19-related) and 568 (25 COVID-19-related) proteins, respectively. On the other hand, WM covered COVID-19-related proteins more precisely and seemed different from CHM. The network pharmacology showed CHM formulas affected several inflammation-related proteins for COVID-19, including IL-10, TNF-α, IL-6, TLR3, and IL-8, in which Dexamethasone and Aspirin covered only IL-10 and TNF-α. JAK and IL-6 receptors were only inhibited by WM. The molecular pathways covered by CHM and WM also seemed mutually exclusive. WM had advantages in cytokine signaling, while CHM had an add-on effect on innate and adaptive immunity, including neutrophil regulation. WM and CHM could be used together to strengthen the anti-inflammation effects for COVID-19 from different pathways, and the combination of WM and CHM may achieve more promising results. These findings warrant further clinical studies about CHM and WM use for COVID-19 and other diseases.

The targeted agents capmatinib and tepotinib provide a new treatment for patients with non-small cell lung cancer (NSCLC) with MET exon 14 skipping mutation (METex14). However, drug-induced pneumonitis is an uncommon but threatening adverse effect found in patients treated with both capmatinib and tepotinib. The safety of treating a patient with a MET inhibitor after drug-induced pneumonitis by another MET inhibitor remains unclear. Here, we present a case of a patient with NSCLC harboring a METex14 who was treated with a standard dose of tepotinib after advanced capmatinib-induced pneumonitis and did not present pneumonitis relapse. Tepotinib may be a safe option when medical professionals consider switching MET inhibitors after patients experience pneumonitis.

Enterovirus infection and enterovirus infection with severe complications (EVSC) are critical issues in several aspects. However, there is no suitable predictive tool for these infections. A climate factor complex (CFC) containing several climate factors could provide more effective predictions. The ping-year factor (PYF) and El Niño-Southern Oscillation (ENSO) are possible CFCs. This study aimed to determine the relationship between these two CFCs and the incidence of enterovirus infection. Children aged 15 years and younger with enterovirus infection and/or EVSC were enrolled between 2007 and 2022. Each year was categorized into a ping-year or non-ping-year according to the PYF. Poisson regression was used to evaluate the associations between the PYF, ENSO, and the incidence of enterovirus infection. Compared to the ping-year group, the incidence rate of enterovirus infection, the incidence rate of EVSC, and the ratio of EVSC in the non-ping-year group were 1.24, 3.38, and 2.73 times higher, respectively (p < 0.001). For every one-unit increase in La Niña, the incidence rate of enterovirus infection decreased to 0.96 times (p < 0.001). Our study indicated that CFCs could be potential predictors for enterovirus infection, and the PYF was more suitable than ENSO. Further research is needed to improve the predictive model.

Introduction: Traditional Chinese Medicine (TCM) education in Taiwan is transitioning from an apprenticeship model to a standardized residency program. This unique training cohort of TCM residents integrates the knowledge systems of TCM and Western Medicine (WM). To understand this population, we aim to translate, validate, and use the Traditional Chinese version of the Index of Learning Styles (TC-ILS) to profile the learning style distribution of Taiwanese TCM residents. Methods: A cross-sectional survey recruited 217 TCM residents from the Chang Gung Memorial Hospital system. Psychometric properties were assessed via Confirmatory Factor Analysis (CFA) and Composite Reliability (CR). Learning style profiles and subgroup differences were also analyzed. Results: Psychometric evaluation of the TC-ILS yielded mixed fit findings: while RMSEA (0.035) suggested small average residuals, CFI (0.730), TLI (0.714), and SRMR (0.136) indicated substantial misfit. Accordingly, the CFA provides only partial support for the hypothesized four-factor structure, consistent with prior ILS reports involving dichotomous items and highly correlated dimensions. Regarding internal consistency, the CR was acceptable for Sensing/Intuitive (0.639) and Visual/Verbal (0.625), but below the 0.6 standard for Active/Reflective (0.461) and Sequential/Global (0.485). The cohort exhibited strong preferences for Sensing (77.42%), Visual (87.56%), Reflective (62.21%), and Global (59.45%) styles. Discussion: This study translated, adapted, and assessed the TC-ILS for use in this specific TCM resident cohort. The profile demonstrated a distinct tendency toward Visual, Sensing, Reflective, and Global styles. The Global preference differs from the Sequential style typically observed in WM participants and may reflect features of this specific professional training context.