Unplanned patient readmission (UPRA) is frequent and costly in healthcare settings. No indicators during hospitalization have been suggested to clinicians as useful for identifying patients at high risk of UPRA. This study aimed to create a prediction model for the early detection of 14-day UPRA of patients with pneumonia. We downloaded the data of patients with pneumonia as the primary disease (e.g., ICD-10:J12*-J18*) at three hospitals in Taiwan from 2016 to 2018. A total of 21,892 cases (1208 (6%) for UPRA) were collected. Two models, namely, artificial neural network (ANN) and convolutional neural network (CNN), were compared using the training (n = 15,324; ≅70%) and test (n = 6568; ≅30%) sets to verify the model accuracy. An app was developed for the prediction and classification of UPRA. We observed that (i) the 17 feature variables extracted in this study yielded a high area under the receiver operating characteristic curve of 0.75 using the ANN model and that (ii) the ANN exhibited better AUC (0.73) than the CNN (0.50), and (iii) a ready and available app for predicting UHA was developed. The app could help clinicians predict UPRA of patients with pneumonia at an early stage and enable them to formulate preparedness plans near or after patient discharge from hospitalization.

Although previous studies demonstrated the risk of ischemic stroke (IS) in patients with head and neck cancer (HNC), the impact of oral antithrombotic therapy (OAT) on this risk has not yet been assessed. We aimed to evaluate the effectiveness and safety of OAT in patients with HNC treated with RT. This retrospective cohort study was performed using the National Health Insurance Research Database of Taiwan. A total of 37,638 patients diagnosed with HNC included in the study were classified as users and nonusers of OAT. Primary outcome was IS or transient ischemic attack (TIA), and secondary outcomes were death and major bleeding. The Cox proportional hazards model was used to calculate hazard ratios (HRs) and 95% confidence intervals (CIs). There was no significant difference in the risk of IS or TIA between patients on continuous OAT and nonusers (adjusted HR, 0.812; 95% CI, 0.199–3.309). The risk of major bleeding was not significantly different between the groups. From a national population database, we did not find an association between OAT and decreasing risk of ischemic stroke/TIA or increasing hazard of major bleeding.

The efficacy of inhaled corticosteroid (ICS) in the treatment of patients with COVID-19 has been evaluated in randomized controlled trials (RCTs), however, their findings are not consistent. PubMed, Embase, Cochrane Library, ClinicalTrials.gov, Scopus, Web of Science and Google Scholar were searched to June 10, 2023. Only RCTs that investigated the clinical efficacy and safety of ICS for patients with COVID-19 were included. Eleven RCTs were included. ICS users had significantly higher rate of symptom alleviation at day 14 than the control group (risk ratio [RR], 1.13; 95% CI, 1.04-1.23; I² = 42%). Additionally, no significant difference between the ICS users and the control group was observed in the composite outcome of urgent care, emergency department (ED) visit or hospitalization (RR, 0.43; 95% CI, 0.08-2.48; I² = 85%) and hospitalization or death (RR, 0.85; 95% CI, 0.64-1.12; I² = 0%). Finally, ICS user had a non-significantly lower risk of death at day 28 than the control group (0.63% vs 0.99%; RR, 0.82; 95% CI, 0.43-1.56; I² = 0%). Additional ICS use, particularly inhaled budesonide may help symptom relief in patients with COVID-19. However, ICS use did not help reduce the risk of urgent care, ED visit, hospitalization, or death.

The introductory pharmacy practice experiences (IPPE) in Taiwan, which are traditionally conducted in physical hospital settings, incorporated up to 30% distance learning from May 2021 due to Coronavirus Disease 2019 (COVID-19). A web-based cross-sectional survey was adopted to investigate pharmacy students’ experiences and perceptions of transitioning from in-hospital internships to distance learning due to COVID-19 in the pharmacy department of a university in Southern Taiwan. We analyzed the results to discover factors that significantly affected students’ perceptions of transitioning from in-hospital internships to distance learning. In total, 81 interns from the university’s pharmacy department responded to the questionnaire. Approximately half of the participants felt happy when they learned, before the internship began, that the internship would be partially replaced with distance learning. The overall satisfaction rate was 67.9%, and no significant differences was observed in students’ satisfaction between hospital size or distance-learning time. However, more students in the medical center felt they had insufficient time to finish assignments compared to those in the regional hospitals, and the students who had 11–15 days of distance learning felt that they interacted more smoothly with their peers compared to those who had other durations. Program designers should make distance internship courses more student-centered, with a focus on increasing interactions between students, teachers, and peers to compensate for the lack of physical presence.