Pemphigus is a chronic dermatological disorder caused by an autoimmune response and is associated with a high proportion of comorbidities and fatalities. The aim of this study was to investigate the risk of depression in patients with pemphigus. Data were derived from the National Health Insurance Research Database recorded during the period 2000–2010 in Taiwan. Multivariate Cox proportional hazards regression models were used to analyze the data and assess the effects of pemphigus on the risk of depression after adjusting for demographic characteristics and comorbidities. Patients with pemphigus were 1.98 times more likely to suffer from depression than the control group (pemphigus, adjusted HR: 1.99, 95% CI = 1.37–2.86). People aged ≥65 years were 1.69 times more likely to suffer from depression than those aged 20–49 years (≥65 years, adjusted HR: 1.42, 95% CI = 0.92–2.21). Female and male patients with pemphigus were respectively 2.02 and 1.91 times more likely to suffer from depression than the control group (female, adjusted HR: 2.09, 95% CI = 1.24–3.54; male, adjusted HR: 1.87, 95% CI = 0.97–3.60). People with HTN, hyperlipidemia, asthma/COPD, and chronic liver disease were respectively 1.73, 2.3, 2.2, and 1.69 times more likely to suffer from depression than those without these comorbidities (HTN, adjusted HR: 0.75, 95% CI = 0.41–1.42; hyperlipidemia, adjusted HR: 1.48, 95% CI = 0.78–2.82; asthma/COPD, adjusted HR: 1.4, 95% CI = 0.72–2.69; and chronic liver disease, adjusted HR: 1.61, 95% CI = 1.07–2.43). There was a significant association between pemphigus and increased risk of depression. Female patients had a higher incidence of depression.

With the increasing number of people with disabilities caused by an aging global population, the need for long-term care is gradually increasing. Nursing assistants (NAs) are the primary providers of direct care services to older adults with disabilities, whose knowledge, skills, and beliefs affect the quality of care provided. This study aimed to investigate the influential factors affecting NAs’ current competences. A total of 255 NAs’ valid questionnaires were collected from 20 long-term care institutions in Taiwan through convenience sampling. The questionnaire comprised dimensions of demographics and care competence. The study results indicated that NAs had the greatest care competence in the domain of recognition of patient rights (4.64 ± 0.54 points). The multiple regression indicated that age, religion, job category, disability care experience, the receiving of performance bonuses, and the receiving of year-end bonuses significantly affected the level of care competence (p < 0.05). With the aforementioned findings, the results of this study serve as references for the government in employing long-term care NAs and developing management policies. Training programs for NAs should be developed to improve the quality of care provided to older adults with disabilities.

Background: Taiwan has insufficient nursing resources due to the high turnover rate of health care providers. Therefore, reducing the heavy workload of these employees is essential. Herein, speech transcription, which has various potential clinical applications, was employed for the documentation of nursing records. The requirement of including only one speaker per transcription facilitated data collection and system development. Moreover, authorization from patients was unnecessary. Objective: The aim of this study was to construct a speech recognition system for nursing records such that health care providers can complete nursing records without typing or with only a few edits. Methods: Nursing records in Taiwan are mainly written in Mandarin, with technical terms and abbreviations presented in both Mandarin and English. Therefore, the training set consisted of English code-switching information. Next, transfer learning (TL) and meta-TL (MTL) methods, which perform favorably in code-switching scenarios, were applied. Results: As of September 2021, the China Medical University Hospital Artificial Intelligence Speech (CMaiSpeech) data set was established by manually annotating approximately 100 hours of recordings from 525 speakers. The word error rate (WER) of the benchmark model of syllable-based TL was 29.54% in code-switching. The WER of the proposed model of syllable-based MTL was 22.20% in code-switching. The test set comprised 17,247 words. Moreover, in a clinical case, the proposed model of syllable-based MTL yielded a WER of 31.06% in code-switching. The clinical test set contained 1159 words. Conclusions: This paper has two main contributions. First, the CMaiSpeech data set—a Mandarin-English corpus—has been established. Health care providers in Taiwan are often compelled to use a mixture of Mandarin and English in nursing records. Second, an automatic speech recognition system for nursing record document conversion was proposed. The proposed system can shorten the work handover time and further reduce the workload of health care providers.

Because nurse aides are one of the first-line care providers in hospitals, they should possess better knowledge, attitude, and behavioral intention toward COVID-19 during the pandemic. This study aimed to compare the improvements of COVID-19-related education on learning outcomes between multimedia-based and traditional face-to-face learning models for nurse aides. The parallel-group randomized controlled trial recruited 74 participants in both the experimental and control groups. Two 90 min interventions with the same contents, but in different ways, were delivered. A structured questionnaire was used to collect data of demographic information, knowledge, attitude, and behavioral intention toward COVID-19 before and after the interventions. Results from generalized estimation equations analysis indicated that the nurse aides in the multimedia-based learning group had greater improvement in the scores of knowledge (difference in change: 3.2, standard error: 0.97, p < 0.001), attitude (difference in change: 10.2, standard error: 2.97, p < 0.001), and behavioral intention (difference in change: 0.5, standard error: 0.04, p < 0.001) than those in the face-to-face learning group. During the outbreak of COVID-19, multimedia-based learning as an effective learning method could improve the learning outcomes related to COVID-19 and achieve learning goals without close contact.

Objectives: During the coronavirus disease 2019 (COVID-19) pandemic, nursing aides (NAs) experienced greater work stress than they do typically because they worked in highly contagious environments. This may have influenced their work morale and willingness to work, which can reduce patient satisfaction, influence their physical and mental health, and even endanger patient safety or cause medical system collapse. Design: A cross-sectional survey with a structured self-report questionnaire was conducted. Setting and Participants: 144 NAs from a medical center in Central Taiwan participated. Methods: We recruited NAs through convenience sampling to discuss their work stress, willingness to work, and patients’ satisfaction with them during the COVID-19 pandemic. Result: Of the 144 recruited NAs, 115 (79.9%) were women and 29 (20.1%) were men, and 89 (61.8%) had completed COVID-19 training courses. NAs with different work tenure lengths exhibited significant differences in work stress (p = 0.022), willingness to work (p = 0.029), and patient satisfaction (p = 0.029) scores during the pandemic. Conclusion: The study findings provide crucial data for the management of NAs during pandemics to prevent them from neglecting patients due to excessive work stress or losing their willingness to work, which may cause the medical system to collapse.

Background: For clinical nurses, manually entering information into hospital information systems (HISs) remains time-consuming and prone to omissions. Although speech recognition can reduce the need for manual entry, its use in clinical settings has historically been limited by code-switching, medical terminology, and noisy ward environments. Recent advances in customized automatic speech recognition (ASR) and large language models (LLMs) now make speech-based, structured documentation aligned with nursing frameworks such as DART (data, action, response, and teaching) increasingly feasible. Objective: This study developed and evaluated an integrated ASR and LLM system that transforms spoken nursing input into structured DART notes and evaluated its accuracy, usability, and clinical feasibility within HIS workflows. Methods: A code-switching nursing speech corpus from emergency and ward settings was used to fine-tune the Whisper large-v2 model with parameter-efficient adaptation. The LLM generated schema-constrained DART records from ASR transcripts, which were verified by nurses before being uploaded to the corresponding HIS fields. Evaluation included mixed error rate for ASR accuracy, F ₁ -scores, and agreement statistics for DART classification, hallucination assessments based on factual correctness, and analysis of nurse feedback on system use. Results: The fine-tuned ASR model reduced the mixed error rate from 44.79% to 6.67%. DART generation achieved a macroaveraged F ₁ -score of 0.82 (95% CI 0.80‐0.84) and met the noninferiority margin relative to human transcripts (δ=−0.04). The hallucination rate was 2.51%. During deployment, the monthly volume of valid nursing notes generated through voluntary use of the ASR system increased from 32,724 to 65,417, where each note represented a single documentation entry generated per patient care episode. Among 120 participating nurses, 91 (75.8%) reported reduced workload and improved completeness. Conclusions: The integrated ASR and LLM system was feasible and showed strong performance, with good acceptance among clinical nurses. It reduced the manual documentation burden, improved record completeness, and demonstrated the value of an ASR- and LLM-supported workflow for nursing documentation.