Empirical Study on the Usage of Telemedicine by Rural and Urban Health Care Consumers in Taiwan: Integrating the Perspectives of Technology Acceptance Model and Theory of Planned Behavior.

Introduction: The outbreak of the novel coronavirus disease-19 posed significant challenges globally, impacting various sectors and health care systems profoundly. In response, telemedicine has emerged as a vital solution to address health care demands and resource shortages. However, there is a lack of comprehensive research on telemedicine usage among health care consumers in urban and rural areas of Taiwan. Methods: This study aimed to investigate the usage, attitudes, and intentions of telemedicine utilization among health care consumers in Taiwan, integrating the Technology Acceptance Model and Theory of Planned Behavior. A cross-sectional study was conducted from April 2023 to May 2024, involving 1,053 participants who utilized telemedicine services. Structured questionnaires were used for data collection, and statistical analyses were performed using SPSS 21.0 software. Results: The results revealed significant disparities in telemedicine utilization between urban and rural areas, with urban residents exhibiting higher levels of perceived ease of use, perceived usefulness, attitude toward use, trust, and intention to use telemedicine. Regression analysis indicated a significant association between urban residence and male gender with telemedicine utilization, contrary to previous research findings. These disparities may stem from differences in health care accessibility and cultural norms prevalent in urban and rural areas. Conclusions: Further investigation into gender differences and interventions to promote telemedicine usage among females, particularly in urban areas, are recommended. This study provides valuable insights for future research and health care policy formulation.

The LACE index and risk factors of 14-day versus 30-day readmissions in children.

Risk factors for readmissions in children differ from those in adults, yet little is known about whether the LACE index (Length of stay, Acute admission, Charlson comorbidity index, Emergency department visits in the previous 6 months) developed for adults retains its validity when applied to the prediction of readmissions in children or within shorter intervals of time after discharge. In this retrospective cohort analysis of 4256 patients aged ≤18 years hospitalized at one academic medical center in Taiwan in 2019, we first evaluated the performance of a LACE index model and the three other multivariate logistic regression models in their predictions of hospital readmissions in children using the same time interval of 30 days. We then used multinomial logistic regression to analyze the characteristics and risk factors for readmissions that occur in the first 14 days with those that occur between 15 and 30 days after discharge. The optimal cut-off of the LACE index score for children in the current study was 7, which is less than the optimal score of 10 in the original derivation for adults. The predictive model with the least discriminatory power was based on the LACE score alone, whereas our model that included only two variables (length of stay and the number of admissions in the past 1 year) was found to outperform the LACE index. Multinomial logistic regression results revealed that children who had supplemental private health insurance had lower readmission rates than those insured by the National Health Insurance program only, suggesting a disparity by insurance status. Some risk factors of readmission within 14 days such as acute admissions and supplemental private health insurance were not found to be relevant for longer-term predictions, while age, which was a valid predictor of readmission within 15-30 days, did not affect the prediction of shorter-term readmissions. Prior health care utilization and a higher illness burden were found to be greater contributors to readmissions beyond 14 days. Our simpler model outperformed the more complex LACE tool in identifying children at risk of readmission. Shorter-term readmissions can be attributed to different causes than 30-day readmissions, suggesting a need for different screening tools, interventions, and care support. There remains some socioeconomic disparity associated with readmission rates in the current health care system.

Effect of China's long-term care insurance on health outcomes of older disabled people: role of institutional care.

Since the public long-term care insurance (LTCI) system was piloted in Chengdu, China, in October 2017, there has been considerable growth of LTC institutions in China. This study aimed to evaluate the health value effect of LTCI in older patients with severe disabilities in an LTC institution. This prospective study was based on data from 985 severe disability patients with or without LTCI from October 2017 to May 2021 in the Eighth People's Hospital, Chengdu, China. The Cox proportional hazard model estimated LTCI's health value, including survival probability and risk of pneumonia/pressure ulcers. Subgroup analysis was performed for sex, age, Charlson Comorbidity Index (CCI), and the number of drugs. In the analysis, 519 and 466 patients in LTCI and non-LTCI groups were included, respectively. In adjusted Cox analyses, the LTCI group had a significantly elevated survival rate compared with the non-LTCI groups at 12 months (P < .001, hazard ratio (HR) = 1.758, 95% confidence interval (CI) 1.300-2.376). At 40 months, the adjusted survival rate was 62.6% in the LTCI group, which was significantly higher (53.7%; P = .003, HR = 1.438, 95% CI 1.131-1.831). The subgroups of patients aged 60 to 79 years (interaction P = .007) and with CCI ≥ 3 (interaction P = .026) were more significantly associated with survival improvement than those aged >80 years and with CCI< 3. The LTCI group was also at lower risk for hospital-acquired pneumonia (P = .016, HR 0.622, 95% CI 0.422-0.917) and pressure ulcers (P = .008, HR 0.695, 95% CI 0.376-0.862). The improved survival of LTCI remained stable in sensitivity analyses. For older patients with severe disabilities, in a LTC institution, LTCI significantly improved their health profile and longevity after a year, suggesting the large role and development potentiality of institution care in the LTCI system of China.

Patient-centred e-health supports value cocreation and quality of medical care in Taiwan.

BACKGROUND: Patient-centred e-health (PCEH) focusses on the interaction between patients and physicians. However, only a limited number of studies have focussed on the design of physician-patient value cocreation mechanisms in the PCEH context. Thus, we extend Grönroos' concept of value cocreation to understand how PCEH might improve the quality of care. OBJECTIVES: This study proposes a theoretical framework to embody PCEH-supported value cocreation and presents some empirical validation. We expect that PCEH-supported value cocreation should comprise capabilities for patient empowerment, intention for information sharing, complementation for checking and verifying information, and interaction for shared understanding. METHODS: This study surveyed a small group of patients that have used PCEH, 'My Health Bank' in Taiwan. The questionnaires were delivered to patients in hospitals (n = 167 questionnaires, 98% response rate). RESULTS: Results indicate that certain PCEH-supported value cocreation mechanisms-capabilities for patient empowerment and interaction for shared understanding-affect the perceived quality of medical care. LIMITATIONS: The survey only considered patient perceptions of value cocreation. CONCLUSION: This study shows the patient perception of value cocreation in patient-centred e-Health. Further research needs to validate the framework for health professionals and in other e-Health record information sharing settings.

Predicting the number of article citations in the field of attention-deficit/hyperactivity disorder (ADHD) with the 100 top-cited articles since 2014: a bibliometric analysis.

BACKGROUND: Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children or early adolescents with an estimated worldwide prevalence of 7.2%. Numerous articles related to ADHD have been published in the literature. However, which articles had ultimate influence is still unknown, and what factors affect the number of article citations remains unclear as well. This bibliometric analysis (1) visualizes the prominent entities with 1 picture using the top 100 most-cited articles, and (2) investigates whether medical subject headings (i.e., MeSH terms) can be used in predicting article citations. METHODS: By searching the PubMed Central® (PMC) database, the top 100 most-cited abstracts relevant to ADHD since 2014 were downloaded. Citation rank analysis was performed to compare the dominant roles of article types and topic categories using the pyramid plot. Social network analysis (SNA) was performed to highlight prominent entities for providing a quick look at the study result. The authors examined the MeSH prediction effect on article citations using its correlation coefficients (CC). RESULTS: The most frequent article types and topic categories were research support by institutes (56%) and epidemiology (28%). The most productive countries were the United States (42%), followed by the United Kingdom (13%), Germany (9%), and the Netherlands (9%). Most articles were published in the Journal of the American Academy of Child and Adolescent Psychiatry (15%) and JAMA Psychiatry (9%). MeSH terms were evident in prediction power on the number of article citations (correlation coefficient = 0.39; t = 4.1; n = 94; 6 articles were excluded because they do not have MeSH terms). CONCLUSIONS: The breakthrough was made by developing 1 dashboard to display 100 top-cited articles on ADHD. MeSH terms can be used in predicting article citations on ADHD. These visualizations of the top 100 most-cited articles could be applied to future academic pursuits and other academic disciplines.

A preliminary study on applying holistic health care model on medical education behavioral intention: a theoretical perspective of planned behavior.

BACKGROUND: This study aimed to apply the theory of planned behavior to identify the medical education behavioral intention of holistic healthcare on teachers and students who influence the medical and healthcare profession, as a revised future direction for hospitals to continue to implement holistic healthcare. METHODS: This cross-sectional study was performed from April to May 2020. A questionnaire survey was conducted with the clinical teachers and students of the medical and healthcare profession in an individual Taiwan hospital as study subjects, based on judgmental sampling, and the study tool was a structured questionnaire. RESULTS: A total of 360 valid samples were collected, 105 clinical teachers (29.2%) and 255 students (70.8%). Demographic variables were significantly different between clinical teachers (mean = 3.91) and students (mean = 3.73) (p = 0.023). Post hoc analysis regarding work experience found that those with work experience < 2 years (mean = 3.94) had higher results than those with 6-10 years (mean = 3.61) (p = 0.019). The results of multiple regression analysis indicate that the factors affecting medical education behavioral intention are subjective norm (t = 3.571, p < 0.001) and perceived behavioral control (t = 11.870, p < 0.001). CONCLUSIONS: With respect to medical education behavioral intention, clinical teachers and students are affected by the subjective norm and perceived behavioral control. It is recommended that, in the curriculum of holistic medical education, designing holistic medical education teaching templates and check forms can encourage clinical teachers to re-examine their beliefs in teaching, learning, and knowledge. The results of this study allow the advocator to consider from a broader view making policies of and promoting the platform of holistic healthcare on medical education. It is recommended that future researchers conduct research, investigation, and analysis on other stakeholders.

Analysis of outpatient medical services for correctional institution's inmates entitled to national health insurance: A prison in Taiwan.

BACKGROUND: To formulate better future policies, this study aims to understand the outpatient services provided in a prison in Southern Taiwan by the contracted hospital in two phases. METHODS: Data were analyzed through the outpatient medical services performed by the contracted hospitals in prison in two phases (2013-2015 and 2016-2018). SPSS 20.0 software was used to analyze data such as age, medical fees, department, outpatient visits, average number of visits per patient, and common diseases. RESULTS: The average age of the treated inmates was 49.34 and 47.04 years in the first and second phases, respectively. Most patients belong in the age group of 41-50 years. The number of medical visits per person increased from 15.6 to 20.6 visits. The average medical fee per visit increased from NTD 748 to NTD 775, and the average days of medication per visit decreased from 14 to 13 days. Commonly visited were family medicine, general medicine, orthopedics, and psychiatry departments. Disease of the skin and subcutaneous tissue was the first common disease in both phases, and hypertension was the most common disease. CONCLUSION: The number of medical visits and the average medical fee increased. The medical cost of inmates is higher than the generally insured individuals. If environmental conditions in the correctional facility are improved, the consumption of medical resources will be reduced. There should be a complete therapy and medical treatment plan for mentally ill inmates for a successful return to the society after serving time.

The association of hospital governance with innovation in Taiwan.

Hospitals in Taiwan are facing major changes and innovation is increasingly becoming a critical factor for remaining competitive. One determinant that can have a significant impact on innovation is hospital governance. However, there is limited prior research on the relationship between hospital governance and innovation. The purpose of this study is to propose a conceptual framework to hypothesize the relationship between governance mechanisms and innovation and to empirically test the hypotheses in hospital organizations. We examine the relationship between governance mechanisms and innovation using data on 102 hospitals in Taiwan from the Taiwan Joint Commission on Hospital Accreditation and Quality Improvement. We model governance mechanisms using board structure, information transparency and strategic decision-making processes. For our modeling and data analysis we use measurement and structural models. We find that in hospital governance, information transparency and strategic decision making did impact innovation. However, governance structure did not. To facilitate innovation, hospital boards can increase information transparency and improve the decision-making process when considering strategic investments in innovative initiatives. To remain competitive, hospital boards need to develop and monitor indices that measure hospital innovation to ensure ongoing progress.

The exploration of medical resources utilization among inguinal hernia repair in Taiwan diagnosis-related groups.

BACKGROUND: This study centered on differences in medical costs, using the Taiwan diagnosis-related groups (Tw-DRGs) on medical resource utilization in inguinal hernia repair (IHR) in hospitals with different ownership to provide suitable reference information for hospital administrators. METHODS: The 2010-2011 data for three hospitals under different ownership were extracted from the Taiwan National Health Insurance claims database. A retrospective method was applied to analyze the age, sex, length of stay, diagnosis and surgical procedure code, and the change in financial risk of medical costs in IHR cases after introduction of Tw-DRGs. The study calculated the cost using Tw-DRG payment principles, and compared it with estimated inpatient medical costs calculated using the fee-for-service policy. RESULTS: There were 723 IHR cases satisfying the Tw-DRGs criteria. Cost control in the medical care corporation hospital (US$764.2/case) was more efficient than that in the public hospital (US$902.7/case) or nonprofit proprietary hospital (US$817.1/case) surveyed in this study. For IHR, anesthesiologists in the public hospital preferred to use general anesthesia (86%), while those in the two other hospitals tended to administer spinal anesthesia. We also discovered the difference in anesthesia cost was high, at US$80.2/case on average. CONCLUSIONS: Because the Tw-DRG-based reimbursement system produces varying hospital costs, hospital administrators should establish a financial risk assessment system as early as possible to improve healthcare quality and financial management efficiency. This would then benefit the hospital, patient, and Bureau of National Health Insurance.

Empirical Study on Hospitalist System: A Value Creation Perspective.

This study investigates the impact of hospitalist system awareness, motivation, and behavior on value creation within the healthcare context of Taiwan. As population aging and the prevalence of chronic diseases continue to rise, accompanied by increased medical resource consumption, the Taiwan Ministry of Health and Welfare introduced the hospitalist system. Despite its implementation, the number of participating hospitals remains low. Using a questionnaire survey conducted from October 2021 to March 2022, data were collected from medical teams involved in the hospitalist system. A total of 324 valid questionnaires were analyzed. The results reveal that hospitalist awareness positively influences participation motivation (ß = 0.846, p < 0.001), which subsequently impacts participation behavior positively (ß = 0.888, p < 0.001). Moreover, participation behavior significantly contributes to value creation (ß = 0.869, p < 0.001), along with the direct effect of awareness (ß = 0.782, p < 0.001) on value creation. In conclusion, the successful promotion and implementation of the hospitalist system rely heavily on the support and active participation of medical staff. Effective interactions and comprehensive information dissemination are essential for maximizing healthcare value creation.

Exploring Telemedicine Usage Intention Using Technology Acceptance Model and Social Capital Theory.

Telemedicine technology has emerged as a pivotal solution to enhance the accessibility and efficiency of healthcare services. This study investigates the factors influencing the acceptance of telemedicine technology among healthcare professionals in Taiwan. Employing a quantitative research approach, we utilized a survey instrument adapted from the Unified Theory of Acceptance and Use of Technology (UTAUT) model. Data were collected from 325 healthcare professionals across diverse medical fields. The results indicate that perceived usefulness, ease of use, social influence, and convenience significantly influence intention to use telemedicine. Moreover, age moderates the relationship between perceived usefulness and usage intention. These findings underscore the importance of addressing both technological and social factors in promoting the adoption of telemedicine among healthcare professionals. Policy implications and recommendations for enhancing telemedicine implementation are discussed based on the study findings. Specifically, our findings highlight that perceived usefulness, ease of use, social influence, and convenience significantly impact the intention to use telemedicine technology. Age significantly moderates the relationship between perceived usefulness and usage intention. These results not only theoretically support the UTAUT model but also provide practical strategies to advance the application of telemedicine technology.

A Cross-Sectional Study on the Assessment of Service Quality and User Satisfaction of a Community Support Program in a Region of Taiwan.

This study aims to assess the service quality and user satisfaction of a community support program (CSP) in a specific administrative region of Taiwan. Employing a cross-sectional design, data were collected from 450 CSP users in the region via a questionnaire. Statistical analyses, including descriptive analysis, ANOVA, and Scheffe's Test, were conducted using SPSS 22.0. The findings reveal that users aged 70-79 years with primary education, as well as those with demand or unknown demand for long-term care, reported the highest level of satisfaction with CSP services (mean = 4.5, SD = 0.7, p < 0.05). The study underscores the influence of user characteristics and their understanding of the services on satisfaction levels. These insights provide clear direction for policymakers in shaping the future of CSPs, emphasizing the importance of addressing user needs and enhancing awareness and the utilization of available services.

Empirical study on the factors influencing the successful aging of the middle-aged and older adult community volunteers.

Background: The pursuit of successful aging is currently the most important research and policy issue in an aging society. Participating in voluntary services can help middle-aged and older adults recognize the positive value and benefits of social participation, feel a sense of happiness and accomplishment, and improve their overall life satisfaction, which can also contribute to successful aging. This study wants to understand whether the participation motivation and expectation confirmation of middle-aged and older adult volunteering will affect their continuous participation behavior and successful aging because of the satisfaction of actual participation? Objective: This study explores the factors related to middle-aged and older adult volunteering participation and their impact on successful aging. Methods: Middle-aged and older adult volunteering from the East Taiwan Community Development Association and community care centers were taken as the research objects. Convenience sampling was used to select volunteers who were over 45 years old (inclusive) and have participated in voluntary services over five (inclusive) times in the last 6 months. Respondents completed the questionnaire through self-completion or face-to-face interviews with the interviewer. The measurement tools include engagement motivation, expectation validation, satisfaction, ongoing engagement, and successful aging. Results: A total of 536 questionnaires were distributed of which 498 were valid and 38 invalid. The questionnaire recovery rate was 92.91%. Statistical findings include: (1) Those who perceived that their health was good had a better successful aging status than those who perceived that their health was normal. (2) The volunteering participation motivation and expectation confirmation of middle-aged and older adults significantly affected their volunteer participation satisfaction. (3) Participation motivation and expectation confirmation predicted 50.8% of satisfaction. (4) Satisfaction predicted 47.1% of continuous participation. (5) Continuous participation and satisfaction had a predictive power of 65.1% for successful aging. Conclusion: This study confirms that the motivation and expectation of middle-aged and older adult to participate in volunteering will affect their continuous participation behavior and successful aging status through satisfaction. The research results can be used as a reference for the practical work plan of volunteering.

Assessing the impact of COVID-19 on outpatient and inpatient revenues: A comparative analysis of large and small hospitals in Taiwan.

BACKGROUND: The COVID-19 pandemic has had profound effects on healthcare systems worldwide, not only by straining medical resources but also by significantly impacting hospital revenues. These economic repercussions have varied across different hospital departments and facility sizes. This study posits that outpatient (OPD) revenues experienced greater reductions than inpatient (IPD) revenues and that the financial impact was more profound in larger hospitals than in smaller hospitals. METHODS: We collected data on patient case numbers and associated revenues for 468 hospitals from the Taiwan government-run National Health Insurance Administration website. We then employed Microsoft Excel to construct scatter plots using the trigonometric function (=DEGREES (Atan (growth rate))) for each hospital. Our analysis scrutinized 4 areas: the case numbers and the revenues (represented by medical fees) submitted to the Taiwan government-run National Health Insurance Administration in both March and April of 2019 and 2020 for OPD and IPD departments. The validity of our hypotheses was established through correlation coefficients (CCs) and chi-square tests. Moreover, to visualize and substantiate the hypothesis under study, we utilized the Kano diagram. A higher CC indicates consistent counts and revenues between 2019 and 2020. RESULTS: Our findings indicated a higher impact on OPDs, with CCs of 0.79 and 0.83, than on IPDs, which had CCs of 0.40 and 0.18. Across all hospital types, there was a consistent impact on OPDs (P = .14 and 0.46). However, a significant variance was observed in the impact on IPDs (P < .001), demonstrating that larger hospitals faced greater revenue losses than smaller facilities, especially in their inpatient departments. CONCLUSION: The two hypotheses confirmed that the COVID-19 pandemic impacted outpatient departments more than inpatient departments. Larger hospitals in Taiwan faced greater financial challenges, especially in inpatient sectors, underscoring the pandemic's varied economic effects. The COVID-19 pandemic disproportionately affected outpatient departments and larger hospitals in Taiwan. Policymakers must prioritize support for these areas to ensure healthcare resilience in future epidemics. The research approach used in this study can be utilized as a model for similar research in other countries affected by COVID-19.

Trend and prediction of citations on the topic of neuromuscular junctions in 100 top-cited articles since 2001 using a temporal bar graph: A bibliometric analysis.

BACKGROUND: A neuromuscular junction (NMJ) (or myoneural junction) is a chemical synapse between a motor neuron (MN) and a muscle fiber. Although numerous articles have been published, no such analyses on trend or prediction of citations in NMJ were characterized using the temporal bar graph (TBG). This study is to identify the most dominant entities in the 100 top-cited articles in NMJ (T100MNJ for short) since 2001; to verify the improved TBG that is viable for trend analysis; and to investigate whether medical subject headings (MeSH terms) can be used to predict article citations. METHODS: We downloaded T100MNJ from the PubMed database by searching the string ("NMJ" [MeSH Major Topic] AND ("2001" [Date - Modification]: "2021" [Date - Modification])) and matching citations to each article. Cluster analysis of citations was performed to select the most cited entities (e.g., authors, research institutes, affiliated countries, journals, and MeSH terms) in T100MNJ using social network analysis. The trend analysis was displayed using TBG with two major features of burst spot and trend development. Next, we examined the MeSH prediction effect on article citations using its correlation coefficients (CC) when the mean citations in MeSH terms were collected in 100 top-cited articles related to NMJ (T100NMJs). RESULTS: The most dominant entities (i.e., country, journal, MesH term, and article in T100NMJ) in citations were the US (with impact factor [IF] = 142.2 = 10237/72), neuron (with IF = 151.3 = 3630/24), metabolism (with IF = 133.02), and article authored by Wagh et al from Germany in 2006 (with 342 citing articles). The improved TBG was demonstrated to highlight the citation evolution using burst spots, trend development, and line-chart plots. MeSH terms were evident in the prediction power on the number of article citations (CC = 0.40, t = 4.34). CONCLUSION: Two major breakthroughs were made by developing the improved TBG applied to bibliographical studies and the prediction of article citations using the impact factor of MeSH terms in T100NMJ. These visualizations of improved TBG and scatter plots in trend, and prediction analyses are recommended for future academic pursuits and applications in other disciplines.

The use of forest plot to identify article similarity and differences in characteristics between journals using medical subject headings terms: A protocol for bibliometric study.

BACKGROUND: Comparison of similarity and difference in research types among journals are concerned in literature. However, to date, none display the methodology seen in selecting similar journals related to the target journal, as similar articles did to a given article. Authors need 1 effective method not only to find similar journals for their studies but also to know the difference in methods. This study (1) shows the similar journals for the target journal online displayed, and (2) identifies the effect of similarity odds ratio compared to the counterparts using the forest plots in Meta-analysis and the major medical subject headings (MeSH terms). METHODS: We downloaded 1000 recent top 20 most similar articles related to the Respiratory Care journal from the PubMed library, plotted the clusters of related journals using social network analysis (SNA), and compared the MeSH terms in differences in an odds ratio unit using the forest plot relevant to Respiratory Care and the most similar journals. Q statistic and I-square (I2) index were used to evaluate the difference in the proportion of events. RESULTS: This study found that (1) the journals related to Respiratory Care are easily presented on Google Maps; (2) 10 journal clusters were identified using SNA; (3) the top 3 MeSH terms are methods, therapy, and physiopathology, and (4) the odds ratios of MeSH terms between journals associated with the Respiratory Care showing different from Int J Chron Obstruct Pulmori Dis and similar to Curr Opin Endocrinol Diabetes Obes within heterogeneity with I2 = 70.5% (P < 0.001) and 0% (P = 0.803), respectively. CONCLUSIONS: SNA and forest plots provide deep insight into the relationships between journals in MeSH terms. The results of this research can provide readers with a concept diagram that can be used for future submissions to a given journal.

Emotional Labor Is Associated With the Mental Health of Respiratory Therapists in Hospitals.

BACKGROUND: Respiratory therapists (RTs) play important roles in providing ventilator support to patients in hospitals. They are on the front line in respiratory cases and work with physicians to help patients survive. However, questions remain regarding whether the mental health conditions at work are protected and secured for RTs. This study aimed to explore the risk factors of mental illness for RTs and to design an app to allow individual RTs to seek assistance at an earlier stage. METHODS: A total of 642 RTs from 107 two-tiered hospitals in Taiwan were randomly selected to complete a 44-item, 5-category questionnaire regarding emotional labor and mental health in 2019. Exploratory factor analysis, the Rasch model, descriptive statistics, the nonparametric Mann-Whitney U test, the Kruskal-Wallis test for unpaired t test, and one-way analysis of variance were performed to examine the demographic characteristics and emotional labor and mental health factors that influence RTs' mental health. An app was then designed to evaluate their mental health status. RESULTS: A total of 352 questionnaires were eligible, with a return rate of 54.8% (352 of 642). About 62.8% came from medical centers and 37.2% from regional hospitals. There were 311 (88.4%) women and 41 (11.6%) men, with a mean ± SD age of 37 ± 9.5 y. Six construct factors were extracted from the responses. The overall reliability of the emotional labor and mental health questionnaire for each subscale beyond 0.70 was evident based on internal consistency and stability in the data. Four risk factors (ie, basic emotional expression, superficial emotional control, emotional diversity extent, and weekly work hours) influenced RT mental health. All findings were applied to design an app for RTs to evaluate their mental health at work. CONCLUSIONS: Four risk factors were verified to influence RT mental health. An app was developed to detect their mental health and allow them to seek assistance at an earlier stage.

An application for classifying perceptions on my health bank in Taiwan using convolutional neural networks and web-based computerized adaptive testing: A development and usability study.

BACKGROUND: The classification of a respondent's opinions online into positive and negative classes using a minimal number of questions is gradually changing and helps turn techniques into practices. A survey incorporating convolutional neural networks (CNNs) into web-based computerized adaptive testing (CAT) was used to collect perceptions on My Health Bank (MHB) from users in Taiwan. This study designed an online module to accurately and efficiently turn a respondent's perceptions into positive and negative classes using CNNs and web-based CAT. METHODS: In all, 640 patients, family members, and caregivers with ages ranging from 20 to 70 years who were registered MHB users were invited to complete a 3-domain, 26-item, 5-category questionnaire asking about their perceptions on MHB (PMHB26) in 2019. The CNN algorithm and k-means clustering were used for dividing respondents into 2 classes of unsatisfied and satisfied classes and building a PMHB26 predictive model to estimate parameters. Exploratory factor analysis, the Rasch model, and descriptive statistics were used to examine the demographic characteristics and PMHB26 factors that were suitable for use in CNNs and Rasch multidimensional CAT (MCAT). An application was then designed to classify MHB perceptions. RESULTS: We found that 3 construct factors were extracted from PMHB26. The reliability of PMHB26 for each subscale beyond 0.94 was evident based on internal consistency and stability in the data. We further found the following: the accuracy of PMHB26 with CNN yields a higher accuracy rate (0.98) with an area under the curve of 0.98 (95% confidence interval, 0.97-0.99) based on the 391 returned questionnaires; and for the efficiency, approximately one-third of the items were not necessary to answer in reducing the respondents' burdens using Rasch MCAT. CONCLUSIONS: The PMHB26 CNN model, combined with the Rasch online MCAT, is recommended for improving the accuracy and efficiency of classifying patients' perceptions of MHB utility. An application developed for helping respondents self-assess the MHB cocreation of value can be applied to other surveys in the future.

Comparison of Back-Propagation Neural Network, LACE Index and HOSPITAL Score in Predicting All-Cause Risk of 30-Day Readmission.

BACKGROUND: The main purpose of this study is to predict the all-cause risk of 30-day readmission by employing the back-propagation neural network (BPNN) in comparison with traditional risk assessment tools of LACE index and HOSPITAL scores. METHODS: This was a retrospective cohort study from January 1st, 2018 to December 31st, 2019. A total of 55,688 hospitalizations from a medical center in Taiwan were examined. The LACE index (length of stay, acute admission, Charlson comorbidity index score, emergency department visits in previous 6 months) and HOSPITAL score (hemoglobin level at discharge, discharge from an Oncology service, sodium level at discharge, procedure during hospital stay, Index admission type, number of hospital admissions during the previous year, length of stay) are calculated. We employed variables from LACE index and HOSPITAL score as the input vector of BPNN for comparison purposes. RESULTS: The BPNN constructed in the current study has a considerably better ability with a C statistics achieved 0.74 (95% CI 0.73 to 0.75), which is statistically significant larger than that of the other two models using DeLong's test. Also, it was possible to achieve higher sensitivity (70.32%) without penalizing the specificity (71.76%) and accuracy (71.68%) at its optimal threshold, which is at the 20% of patients with the highest predicted risk. Moreover, it is much more informative than the other two methods because of a considerably higher LR+ and a lower LR-. CONCLUSION: Our findings suggest that more attention should be paid to methods based on non-linear classification systems, as they lead to substantial differences in risk-scores.

An App for Classifying Personal Mental Illness at Workplace Using Fit Statistics and Convolutional Neural Networks: Survey-Based Quantitative Study.

BACKGROUND: Mental illness (MI) is common among those who work in health care settings. Whether MI is related to employees' mental status at work is yet to be determined. An MI app is developed and proposed to help employees assess their mental status in the hope of detecting MI at an earlier stage. OBJECTIVE: This study aims to build a model using convolutional neural networks (CNNs) and fit statistics based on 2 aspects of measures and outfit mean square errors for the automatic detection and classification of personal MI at the workplace using the emotional labor and mental health (ELMH) questionnaire, so as to equip the staff in assessing and understanding their own mental status with an app on their mobile device. METHODS: We recruited 352 respiratory therapists (RTs) working in Taiwan medical centers and regional hospitals to fill out the 44-item ELMH questionnaire in March 2019. The exploratory factor analysis (EFA), Rasch analysis, and CNN were used as unsupervised and supervised learnings for (1) dividing RTs into 4 classes (ie, MI, false MI, health, and false health) and (2) building an ELMH predictive model to estimate 108 parameters of the CNN model. We calculated the prediction accuracy rate and created an app for classifying MI for RTs at the workplace as a web-based assessment. RESULTS: We observed that (1) 8 domains in ELMH were retained by EFA, (2) 4 types of mental health (n=6, 63, 265, and 18 located in 4 quadrants) were classified using the Rasch analysis, (3) the 44-item model yields a higher accuracy rate (0.92), and (4) an MI app available for RTs predicting MI was successfully developed and demonstrated in this study. CONCLUSIONS: The 44-item model with 108 parameters was estimated by using CNN to improve the accuracy of mental health for RTs. An MI app developed to help RTs self-detect work-related MI at an early stage should be made more available and viable in the future.