Understanding the Workplace-Violence-Related Perceptions and Coping Strategies of Nurses in Emergency Rooms.

BACKGROUND: Workplace violence (WPV) is a well-known and serious issue in most countries, and WPV against healthcare providers is of particular concern, especially among nurses working in emergency rooms (ERs). PURPOSE: We aimed to develop a deeper understanding of nurses' perceptions and coping strategies related to WPV that took place over a 1-year period from the perspective of nursing victims still working in ERs in southern Taiwan. METHODS: This is a qualitative study with in-depth and semistructured interviews. Nineteen ER nurse victims were recruited from six hospitals in southern Taiwan from June 2015 to April 2016. All of the interview recordings were analyzed using content analysis. RESULTS: The content analysis identified two themes of perceptions and two themes of coping strategies toward WPV. The two themes of perceptions were "adversity" and "dilemma," with the former covering the three subthemes of "misunderstanding of health policy," "unsafe environment," and "nursing shortage" and the latter covering the two subthemes of "burnout" and "keeping or quitting the job." The two themes of coping strategies were "adjustment" and "resilience," with the former covering the three subthemes of "acceptance of the reality of WPV," "self-regulation," and "culture and belief" and the latter covering the two subthemes of "living with WPV" and "problem solving." CONCLUSIONS/IMPLICATIONS FOR PRACTICE: The findings revealed that ER nurse victims of WPV experienced a complicated journey after encountering WPV. Their coping strategies may be referenced by other ER nurses to better prevent and manage violent events in ERs. To prevent and manage violence in ERs, hospital managers should create a safe working environment through, for example, assigning sufficient security personnel and staff; provide relevant training to ER nurses in communications and other skills; and implement support systems to strengthen nurse resilience.

Nursing Assistant Staffing Model: Implementation and Outcome Evaluation in Taiwan Hospitals.

BACKGROUND: A key policy of the Taiwan healthcare system is promoting the hiring of nursing assistants (NAs) to reduce the workload of nurses. However, few studies in the literature have compared the relative effectiveness of different nurse staffing policies, and no studies have addressed the impact of the NA staffing (NAS) model. PURPOSE: This study explored the current status of the NAS model as implemented in Taiwan hospitals and to investigate the methods used to evaluate the outcomes of NAS model implementation. METHODS: A cross-sectional online survey was performed in hospitals nationwide from June 1 to December 31, 2018. There were 153 government-accredited hospitals being invited to participate in the survey. RESULTS: Of the 139 hospitals that completed the online survey, 26% (36 hospitals) had implemented the NAS model. Many of the hospitals had hired full-time, certified NAs. Most of the tasks assigned to NAs were in the nonprofessional/general and technical work categories. In addition, medical wards were the most frequently assigned workplace, especially on day shifts. Few of the surveyed hospitals had evaluated the effectiveness of the NAS model. Improvement after implementation of the NAS model (based on the 35 outcome indicators) was found to vary significantly. The most commonly used outcome indicator was patient satisfaction. All the stakeholders, including patients, family caregivers, nurses, and nurse supervisors, supported implementation of the NAS model. However, some of the participants expressed concerns regarding the difficulties involved with model implementation. CONCLUSIONS/IMPLICATIONS FOR PRACTICE: Although the NAS model may be beneficial, further empirical research is necessary to confirm the contributions of NAs. Additional evidence regarding the benefits of the NAS model for hospital performance and patient outcomes may be expected to motivate more hospital administrators to adopt this model.

[A Correlational Study of Leadership Styles and Nurses' Morale and Intention to Stay].

BACKGROUND: The leadership style of head nurses affects the organizational atmosphere of nursing teams. PURPOSE: The aim of this study was to analyze the correlation between head nurse leadership styles and nurses' morale and intention to stay, as well as the explained variance for each. METHODS: The descriptive correlational design employed in this study used a convenience sample of 790 nursing staff working at a medical center in southern Taiwan. We cross-sectionally surveyed each participant's intention to stay, morale, and perception of their head nurse's leadership style. RESULTS: The participants perceived their head nurses as having both transformational and transactional leadership styles. A moderate to highly positive correlation was identified among leadership style, morale, and intention to stay. One-way analyses of variance found that the participants who were seniors, were married, had children, were at clinical ladder N3 or above, had rotation experience, and held a public servant position had relatively higher morale and intention to stay. After controlling for potentially confounding factors, hierarchical regression analyses revealed that the explained variance of leadership styles on intention to stay and morale was 22% and 28%, respectively. Transformational leadership was found to significantly predict intention to stay and morale. However, transactional leadership significantly impacted morale only, albeit at a lower level than transformational leadership. CONCLUSIONS / IMPLICATIONS FOR PRACTICE: How nurses perceive the leadership style of their head nurses may affect their intention to stay and morale while at work. Advanced training to strengthen and internalize leadership styles for head nurses is suggested. Creating a positive and friendly working environment is conducive to improving the morale of nurses and retention rates in the nursing workplace.

Automatic identifying and counting blood cells in smear images by using single shot detector and Taguchi method.

BACKGROUND: Researchers have tried to identify and count different blood cells in microscopic smear images by using deep learning methods of artificial intelligence to solve the highly time-consuming problem. RESULTS: The three types of blood cells are platelets, red blood cells, and white blood cells. This study used the Resnet50 network as a backbone network of the single shot detector (SSD) for automatically identifying and counting different blood cells and, meanwhile, proposed a systematic method to find a better combination of algorithm hyperparameters of the Resnet50 network for promoting accuracy for identifying and counting blood cells. The Resnet50 backbone network of the SSD with its optimized algorithm hyperparameters, which is called the Resnet50-SSD model, was developed to enhance the feature extraction ability for identifying and counting blood cells. Furthermore, the algorithm hyperparameters of Resnet50 backbone networks of the SSD were optimized by the Taguchi experimental method for promoting detection accuracy of the Resnet50-SSD model. The experimental result shows that the detection accuracy of the Resnet50-SSD model with 512 × 512 × 3 input images was better than that of the Resnet50-SSD model with 300 × 300 × 3 input images on the test set of blood cells images. Additionally, the detection accuracy of the Resnet50-SSD model using the combination of algorithm hyperparameters got by the Taguchi method was better than that of the Resnet50-SSD model using the combination of algorithm hyperparameters given by the Matlab example. CONCLUSION: In blood cell images acquired from the BCCD dataset, the proposed Resnet50-SSD model had higher accuracy in identifying and counting blood cells, especially white blood cells and red blood cells.

Computerized tool and interdisciplinary care for older patients with delirium in the emergency department: a novel model in Taiwan.

AIMS: A computerized tool and interdisciplinary care were implemented to develop a novel model for older patients with delirium in the emergency department (ED). METHODS: We developed a computerized tool using a delirium triage screen and brief confusion assessment in the hospital information system, performed education for the healthcare providers, and developed a continuous care protocol. Comparisons for outcomes between pre- and post-intervention periods were performed. RESULTS: Compared with the pre-intervention period, patients in the post-intervention period had shorter hospitalization stay, lower expenditure of hospitalization, more likely to return home, lower ED revisits of ≤ 3 days, re-hospitalization of ≤ 14 days, and mortality of ≤ 1 month. All mentioned differences were not statistically significant. CONCLUSIONS: A novel model was successfully developed for delirium management in older patients in the ED. Outcome differences were not significant; however, the result is promising, which gives us an important reference in the future.

Classifying microscopic images as acute lymphoblastic leukemia by Resnet ensemble model and Taguchi method.

BACKGROUND: Researchers have attempted to apply deep learning methods of artificial intelligence for rapidly and accurately detecting acute lymphoblastic leukemia (ALL) in microscopic images. RESULTS: A Resnet101-9 ensemble model was developed for classifying ALL in microscopic images. The proposed Resnet101-9 ensemble model combined the use of the nine trained Resnet-101 models with a majority voting strategy. Each trained Resnet-101 model integrated the well-known pre-trained Resnet-101 model and its algorithm hyperparameters by using transfer learning method to classify ALL in microscopic images. The best combination of algorithm hyperparameters for the pre-trained Resnet-101 model was determined by Taguchi experimental method. The microscopic images used for training of the pre-trained Resnet-101 model and for performance tests of the trained Resnet-101 model were obtained from the C-NMC dataset. In experimental tests of performance, the Resnet101-9 ensemble model achieved an accuracy of 85.11% and an F1-score of 88.94 in classifying ALL in microscopic images. The accuracy of the Resnet101-9 ensemble model was superior to that of the nine trained Resnet-101 individual models. All other performance measures (i.e., precision, recall, and specificity) for the Resnet101-9 ensemble model exceeded those for the nine trained Resnet-101 individual models. CONCLUSION: Compared to the nine trained Resnet-101 individual models, the Resnet101-9 ensemble model had superior accuracy in classifying ALL in microscopic images obtained from the C-NMC dataset.

Epidemic prediction of dengue fever based on vector compartment model and Markov chain Monte Carlo method.

BACKGROUND: Dengue epidemics is affected by vector-human interactive dynamics. Infectious disease prevention and control emphasize the timing intervention at the right diffusion phase. In such a way, control measures can be cost-effective, and epidemic incidents can be controlled before devastated consequence occurs. However, timing relations between a measurable signal and the onset of the pandemic are complex to be discovered, and the typical lag period regression is difficult to capture in these complex relations. This study investigates the dynamic diffusion pattern of the disease in terms of a probability distribution. We estimate the parameters of an epidemic compartment model with the cross-infection of patients and mosquitoes in various infection cycles. We comprehensively study the incorporated meteorological and mosquito factors that may affect the epidemic of dengue fever to predict dengue fever epidemics. RESULTS: We develop a dual-parameter estimation algorithm for a composite model of the partial differential equations for vector-susceptible-infectious-recovered with exogeneity compartment model, Markov chain Montel Carlo method, and boundary element method to evaluate the epidemic periodicity under the effect of environmental factors of dengue fever, given the time series data of 2000-2016 from three cities with a population of 4.7 million. The established computer model of "energy accumulation-delayed diffusion-epidemics" is proven to be effective to predict the future trend of reported and unreported infected incidents. Our artificial intelligent algorithm can inform the authority to cease the larvae at the highest vector infection time. We find that the estimated dengue report rate is about 20%, which is close to the number of official announcements, and the percentage of infected vectors increases exponentially yearly. We suggest that the executive authorities should seriously consider the accumulated effect among infected populations. This established epidemic prediction model of dengue fever can be used to simulate and evaluate the best time to prevent and control dengue fever. CONCLUSIONS: Given our developed model, government epidemic prevention teams can apply this platform before they physically carry out the prevention work. The optimal suggestions from these models can be promptly accommodated when real-time data have been continuously corrected from clinics and related agents.

Classifying chest CT images as COVID-19 positive/negative using a convolutional neural network ensemble model and uniform experimental design method.

BACKGROUND: To classify chest computed tomography (CT) images as positive or negative for coronavirus disease 2019 (COVID-19) quickly and accurately, researchers attempted to develop effective models by using medical images. RESULTS: A convolutional neural network (CNN) ensemble model was developed for classifying chest CT images as positive or negative for COVID-19. To classify chest CT images acquired from COVID-19 patients, the proposed COVID19-CNN ensemble model combines the use of multiple trained CNN models with a majority voting strategy. The CNN models were trained to classify chest CT images by transfer learning from well-known pre-trained CNN models and by applying their algorithm hyperparameters as appropriate. The combination of algorithm hyperparameters for a pre-trained CNN model was determined by uniform experimental design. The chest CT images (405 from COVID-19 patients and 397 from healthy patients) used for training and performance testing of the COVID19-CNN ensemble model were obtained from an earlier study by Hu in 2020. Experiments showed that, the COVID19-CNN ensemble model achieved 96.7% accuracy in classifying CT images as COVID-19 positive or negative, which was superior to the accuracies obtained by the individual trained CNN models. Other performance measures (i.e., precision, recall, specificity, and F1-score) obtained bythe COVID19-CNN ensemble model were higher than those obtained by individual trained CNN models. CONCLUSIONS: The COVID19-CNN ensemble model had superior accuracy and excellent capability in classifying chest CT images as COVID-19 positive or negative.

Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning.

BACKGROUND: To diagnose key pathologies of age-related macular degeneration (AMD) and diabetic macular edema (DME) quickly and accurately, researchers attempted to develop effective artificial intelligence methods by using medical images. RESULTS: A convolutional neural network (CNN) with transfer learning capability is proposed and appropriate hyperparameters are selected for classifying optical coherence tomography (OCT) images of AMD and DME. To perform transfer learning, a pre-trained CNN model is used as the starting point for a new CNN model for solving related problems. The hyperparameters (parameters that have set values before the learning process begins) in this study were algorithm hyperparameters that affect learning speed and quality. During training, different CNN-based models require different algorithm hyperparameters (e.g., optimizer, learning rate, and mini-batch size). Experiments showed that, after transfer learning, the CNN models (8-layer Alexnet, 22-layer Googlenet, 16-layer VGG, 19-layer VGG, 18-layer Resnet, 50-layer Resnet, and a 101-layer Resnet) successfully classified OCT images of AMD and DME. CONCLUSIONS: The experimental results further showed that, after transfer learning, the VGG19, Resnet101, and Resnet50 models with appropriate algorithm hyperparameters had excellent capability and performance in classifying OCT images of AMD and DME.

Fuzzy logic and Gagné learning hierarchy for assessing mathematics skills.

This study developed a fuzzy logic and Gagné learning hierarchy (FL-GLH) for assessing mathematics skills and identifying learning barrier points. Fuzzy logic was used to model the human reasoning process in linguistic terms. Specifically, fuzzy logic was used to build relationships between skill level concepts as inputs and learning achievement as an output. Gagné learning hierarchy was used to develop a learning hierarchy diagram, which included learning paths and test questions for assessing mathematics skills. First, the Gagné learning hierarchy was used to generate learning path diagrams and test questions. In the second step, skill level concepts were grouped, and their membership functions were established to fuzzify the input parameters and to build membership functions of learning achievement as an output. Third, the inference engine generated fuzzy values by applying fuzzy rules based on fuzzy reasoning. Finally, the defuzzifier converted fuzzy values to crisp output values for learning achievement. Practical applications of the FL-GLH confirmed its effectiveness for evaluating student learning achievement, for finding student learning barrier points, and for providing teachers with guidelines for improving learning efficiency in students.

Primary diagnoses and outcomes of emergency department visits in older people with dementia: a hospital-based retrospective study in Taiwan.

OBJECTIVES: The objectives of this study were to investigate the primary diagnoses and outcomes of emergency department visits in older people with dementia and to compare these parameters with those in older adults without dementia. DESIGN AND SETTING: This hospital-based retrospective study retrieved patient records from a hospital research database, which included the outpatient and inpatient claims of two hospitals. PARTICIPANTS: The patient records were retrieved from the two hospitals in an urban setting. The inclusion criteria were all patients aged 65 and older who had attended the two hospitals as an outpatient or inpatient between January 1, 2009, and December 31, 2016. Patients with dementia were identified to have at least three reports of diagnostic codes, either during outpatient visits, during emergency department visits, or in hospitalized database records. The other patients were categorized as patients without dementia. MEASUREMENTS: The primary diagnosis during the emergency department visit, cost of emergency department treatment, cost of hospital admission, length of hospital stay, and diagnosis of death were collected. RESULTS: A total of 149,203 outpatients and inpatients aged 65 and older who were admitted to the two hospitals were retrieved. The rate of emergency department visits in patients with dementia (23.2%) was lower than that in those without dementia (48.6%). The most frequent primary reason for emergency department visits and the main cause of patient death was pneumonia. Patients with dementia in the emergency department had higher hospital admission rates and longer hospital stays; however, the cost of treatment did not show a significant difference between the two groups. CONCLUSIONS: Future large and prospective studies should explore the severity of disease in older people with dementia and compare results with older adults without dementia in the emergency department.

[The Correlates of Nurses' Self-Efficacy for End-of-Life Care].

BACKGROUND: Self-efficacy plays an important role in maintaining health-related behaviors in humans. Nursing staffs should understand the factors that influence self-efficacy in end-of-life (EOL) care in order to ensure their ability to provide appropriate palliative care to EOL-stage patients. PURPOSE: To explore the important variables affecting the self-efficacy of nursing staffs in providing EOL care and the correlations between self-efficacy and these variables. METHODS: This study adopted a descriptive, correlational design. The participants were convenience sampled from registered nurses employed at a teaching hospital in southern Taiwan. The data collection was cross-sectional and 214 registered nurses completed a structured questionnaire on knowledge, attitudes, and self-efficacy with regard to providing EOL care. RESULTS: The results indicated that that participants had (1) an average knowledge level of EOL care (13.99 ± 1.63), demonstrating that nursing staff need to improve their knowledge of EOL care, (2) an average level of attitude (46.74 ± 4.39), demonstrating a slightly positive attitude toward EOL care, and (3) an average level of self-efficacy (48.46 ± 10.37), demonstrating inadequate confidence in providing EOL care. A Pearson product-moment correlation analysis was conducted, showing significant and positive correlations between self-efficacy and the variables of EOL-care knowledge and attitude. Multiple regression analyses revealed that work unit, experience providing EOL care, knowledge regarding EOL care, and attitude toward providing EOL care together explained 42.54% of the variance in EOL care self-efficacy. CONCLUSIONS / IMPLICATIONS FOR PRACTICE: Accurate knowledge about and positive attitude toward providing EOL care are important in fostering confidence in nurses to help patients and their family make appropriate medical decisions and to provide appropriate EOL care. Hospital administrations should provide onsite or offsite continuous education and, when appropriate, arrange interdisciplinary and cross-training programs to enhance the EOL-care-related experience and self-efficacy of nurses.

Intention to care for gay and lesbian patients and knowledge about homosexuality: A comparison of Taiwanese nurses in 2005 and in 2017.

OBJECTIVE: To examine the differences in the levels of intention to care for gay and lesbian patients and knowledge regarding homosexuality among Taiwanese nurses between 2005 and 2017 and the moderators of these differences. DESIGN AND SAMPLE: This two-wave survey study was conducted on nurses in 2005 (N = 1,176; Survey 2005) and 2017 (N = 1,519; Survey 2017) recruited from three hospitals. MEASUREMENTS: An anonymous self-report questionnaire was used. RESULTS: In Survey 2017, the nurses expressed both a higher intention to care for gay and lesbian patients and degree of knowledge regarding homosexuality than did those in Survey 2005. The experience of providing care for gay or lesbian patients moderated the association between the time of the survey and intention to care for gay and lesbian patients. Moreover, having gay or lesbian friends or relatives moderated the association between the time of the survey and knowledge about homosexuality. CONCLUSIONS: Nurses' intention to care for gay and lesbian patients and knowledge regarding homosexuality in Taiwan significantly increased from 2005 to 2017. The experience of providing care for gay and lesbian patients and having gay or lesbian friends or relatives moderated the increase of nurses' intention to care and knowledge.

Prevalence of pain-related diagnoses in patients with dementia: a nationwide study.

PURPOSES: To investigate the prevalence of pain-related diagnoses in patients with dementia and evaluate the association of pain-related diagnoses with demographic characteristics and dementia subtypes. PATIENTS AND METHODS: In this population-based retrospective cohort study, participants were recruited from a cohort of 2 million people randomly sampled from the general population in the National Health Insurance Research Database of Taiwan from 2000 to 2013. The index year was defined as the period of 1 year from the date of the first diagnosis of dementia. RESULTS: The study group comprised 28,450 patients with the dementia subtypes of vascular dementia, Alzheimer's disease, or other dementia subtypes. The mean age of patients with dementia was 76.75 years. Of all patients with dementia, 49.07% had at least one pain-related diagnosis documented in their outpatient or inpatient claim records within the index year. The top three pain-related diagnoses were osteoarthritis (29.27%), headache (12.53%), and osteoporosis (11.43%). Musculoskeletal diagnosis was more likely in female patients with vascular dementia. Although patients with vascular dementia had a significantly lower prevalence of pain-related diagnosis, they had a significantly higher risk of 1-year mortality than patients with other dementia subtypes. CONCLUSION: During the index year, 49.07% of patients with dementia had at least one pain-related diagnosis. To investigate the differences of the use of pain medication in patients with different dementia subtypes and the difference of pain-related diagnosis and treatment in patients with and without dementia, future studies are recommended.

Association among components of resilience and workplace violence-related depression among emergency department nurses in Taiwan: a cross-sectional study.

AIM AND OBJECTIVES: This correlation study examined the relationship among recently workplace violence, depressive tendency, social support, and resilience of victimised nurses, and we also tried to identify protective factors and potential targets for preventive interventions for these nurses. BACKGROUND: Workplace violence in hospitals negatively affects occupational health and safety of medical professionals, especially for emergency department nurses. DESIGN: A cross-sectional, correlation research design was applied. METHODS: Hierarchical regression was used to examine data which were collected from June 2013 to December 2013 from emergency departments in Taiwan. One hundred and eighty nurses were recruited from two hospitals. Structured interviews and questionnaires were applied to collect data, including the Social Support Scale, the Resilience Scale and the Center for Epidemiologic Studies Depression. RESULTS: A total of 159 (88·33%) nurses had suffered from physical or verbal violence by patients or their family. Resilience and peer support were significantly higher in the group without depressive tendency. Components of resilience of personal strength, social competence, structure style and religious beliefs were significant factors which accounted for 46·0% of variance in depressive tendency. Three of the five components of resilience: personal strength, social competence and structured style were found to have profounder effects against depressive tendency than peer support. CONCLUSIONS: Hospital managers should establish a safer working environment for emergency department nurses and reinforce their resilience against depression when they encounter workplace violence. RELEVANCE TO CLINICAL PRACTICE: This study showed that three of the five components of resilience: personal strength, social competence and structured style are protective factors against depressive tendency in victimised nurses. Improving these three components with coping and problem-solving skills by healthcare manager would be effective measures for enhancing their resilience in situations of workplace violence.

[Action Plan to Improve the Utilization of Stationary Bikes in a Health Promotion Exercise Program].

BACKGROUND & PROBLEM: Research has shown that exercise helps reduce the risk and the severity of metabolic syndrome. Since 2009, KMHK hospital has implemented a primary-prevention health promotion program that targets individuals who are at elevated risk of metabolic syndrome. The program engages participants in an exercise protocol that asks them to exercise regularly on a stationary bike three times a week for six months. The utilization rate of the stationary bikes averaged 75% in 2010, but reduced to 34.7% in 2011, with an average withdrawal rate of 24.3%. Therefore, an action team was assembled in order to enhance the effectiveness of the program. PURPOSE: This project used two primary strategies to increase the utilization of stationary bikes. These strategies included: increasing referrals and decreasing withdrawals. METHODS: Surveys of participants who, respectfully, failed to complete and successfully completed the exercise protocol were conducted to identify the factors associated with non-completion / completion. The enrollment policies, the equipment, and the environment were inspected comprehensively. After identifying the causes and effects, several interventions were implemented. These interventions included: installing insulation curtains to block direct sunlight, upgrading the stationary bikes to newer models, creating an environment more conducive to exercise, promoting the referral policies, marketing the health promotion program, and securing family support. RESULTS: After three months, the utilization rate of stationary bikes increased to 77.8%, representing an improvement rate of 124%. Furthermore, the number of case referrals significantly increased and the withdrawal rate decreased to 4.8%. Finally, longer-term follow up indicates that the utilization rate and the withdrawal rate have continued to improve. CONCLUSIONS: The program implemented in the present study successfully enrolled more participants in the exercise protocol, as evidenced by the increased utilization of stationary bikes and by the lower withdrawal rate. Meanwhile, the risk factors for metabolic syndrome among the participants improved dramatically, which in turn achieved the goal of primary prevention and demonstrated program effectiveness.

The association between rotating shift work and increased occupational stress in nurses.

PURPOSE: The aim of this study was to investigate whether rotating shift work increases occupational stress in nurses. METHODS: This study measured shift work scheduling and occupational stress by using the Effort-Reward Imbalance model with self-reported questionnaires in a sample of 654 female nurses. RESULTS: Overcommitment risk was higher in nurses who worked rotating shifts than in those who worked day/non-night shifts (OR, 2.16; 95% CI, 1.03-4.66). However, an effort/reward imbalance was not directly associated with work schedules (OR, 1.88; 95% CI, 0.87-4.35). Among nurses working rotation rotating shifts, those who had 2 days off after their most recent night shifts showed an alleviated risk of overcommitment (OR, 0.52; 95% CI, 0.32-0.82), but those who had worked for at least one series of 7 consecutive work days per month had an increased risk of effort/reward imbalance (OR, 2.75; 95% CI, 1.69-4.48). Additionally, those who had little or no participation in planning working hours and shift scheduling and worked overtime at least three times per week during the preceding 2 months tended to have high stress. CONCLUSIONS: The nurses who worked rotating shifts tended to experience work-related stress, but their stress levels improved if they had at least 2 days off after their most recent night shift and if they were not scheduled to work 7 consecutive days. These empirical data can be used to optimize work schedules for nurses to alleviate work stress.

Effects of marital status and shift work on family function among registered nurses.

This study aims to assess the interactive effect of marital status and shift work on family function. A population-based sample of 1,438 nurses between the ages of 20-45 yr was recruited from Taiwan during the period from July 2005 to April 2006 using a mailed questionnaire. The self-administered questionnaire contained information about demographic data, work status, shift work schedule, and the Family APGAR (Adaptation, Partnership, Growth, Affection, and Resolve) Scale, to evaluate family function. Compared to day shift nurses, non-night and rotation shift nurses had 1.53- and 1.38-fold (95% CI=1.09-2.14 and 1.01-1.88) risk to have poor family function after adjusting for other covariates. Married nurses, by contrast, had a 0.44-fold (95% CI=0.29-0.66) risk to have poor family function compared to single nurses. In addition, married nurses who worked non-night or rotation shifts had a significantly higher percent of poor family function than those married nurses working day shifts; however, similar results were not replicated in single nurses. We concluded that shift work and marital status could influence family function.

Predicting quality of life after breast cancer surgery using ANN-based models: performance comparison with MR.

PURPOSE: The goal was to develop models for predicting long-term quality of life (QOL) after breast cancer surgery. METHODS: Data were obtained from 203 breast cancer patients who completed the SF-36 health survey before and 2 years after surgery. Two of the models used to predict QOL after surgery were artificial neural networks (ANNs), which included one multilayer perceptron (MLP) network and one radial basis function (RBF) network. The third model was a multiple regression (MR) model. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE). RESULTS: Compared to the MR model, the ANN-based models generally had smaller MSE values and smaller MAPE values in the test data set. One exception was the second year MSE for the test value. Most MAPE values for the ANN models ranged from 10 to 20 %. The one exception was the 6-month physical component summary score (PCS), which ranged from 23.19 to 26.86 %. Comparison of criteria for evaluating system performance showed that the ANN-based systems outperformed the MR system in terms of prediction accuracy. In both the MLP and RBF networks, surgical procedure type was the most sensitive parameter affecting PCS, and preoperative functional status was the most sensitive parameter affecting mental component summary score. CONCLUSION: The three systems can be combined to obtain a conservative prediction, and a combined approach is a potential supplemental tool for predicting long-term QOL after surgical treatment for breast cancer. RELEVANCE: Patients should also be advised that their postoperative QOL might depend not only on the success of their operations but also on their preoperative functional status.

Predicting two-year quality of life after breast cancer surgery using artificial neural network and linear regression models.

The purpose of this study was to validate the use of artificial neural network (ANN) models for predicting quality of life (QOL) after breast cancer surgery and to compare the predictive capability of ANNs with that of linear regression (LR) models. The European Organization for Research and Treatment of Cancer Quality of Life Questionnaire and its supplementary breast cancer measure were completed by 402 breast cancer patients at baseline and at 2 years postoperatively. The accuracy of the system models were evaluated in terms of mean square error (MSE) and mean absolute percentage error (MAPE). A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to the LR model, the ANN model generally had smaller MSE and MAPE values in both the training and testing datasets. Most ANN models had MAPE values ranging from 4.70 to 19.96 %, and most had high prediction accuracy. The ANN model also outperformed the LR model in terms of prediction accuracy. According to global sensitivity analysis, pre-operative functional status was the best predictor of QOL after surgery. Compared with the conventional LR model, the ANN model in the study was more accurate for predicting patient-reported QOL and had higher overall performance indices. Further refinements are expected to obtain sufficient performance improvements for its routine use in clinical practice as an adjunctive decision-making tool.