Nurse-led intervention to improve oral mucosal health of intubated patients in the intensive care unit: A prospective study.

BACKGROUND: This prospective study aimed to explore the effectiveness of an oral care intervention with Tegaderm on the oral mucosal health of intubated patients. METHODS: A total of 70 intubated patients were included and randomly assigned to 1 of 3 groups, clean water brushing teeth (n = 23), brushing teeth combined with mouthwash (BTM) (n = 23), and brushing teeth combined with mouthwash and Tegaderm (BTMT) (n = 24). The Oral Mucositis Assessment Scale (OMAS) was applied to evaluate the patient's oral mucosal health before and after oral care intervention. RESULTS: The BTMT group had lower OMAS scores in almost all regions of the oral cavity, compared to the brushing teeth and BTM groups. The general linear model for repeated measurement indicated the BTMT group had the lowest total OMAS scores from Day 2 to Day 4 after the initiation of baseline OMAS evaluation. Of the 3 intervention groups, the BTMT group had the shortest length of endotracheal intubation. The BTMT group had the lowest incidence rate of ventilator-associated pneumonia; however, no significant between-group differences were found. CONCLUSIONS: BTMT effectively reduced the decline in oral mucosal health that was caused by endotracheal intubation and shortened the length of endotracheal intubation.

Self-Supervised Learning-Based General Laboratory Progress Pretrained Model for Cardiovascular Event Detection.

OBJECTIVE: Leveraging patient data through machine learning techniques in disease care offers a multitude of substantial benefits. Nonetheless, the inherent nature of patient data poses several challenges. Prevalent cases amass substantial longitudinal data owing to their patient volume and consistent follow-ups, however, longitudinal laboratory data are renowned for their irregularity, temporality, absenteeism, and sparsity; In contrast, recruitment for rare or specific cases is often constrained due to their limited patient size and episodic observations. This study employed self-supervised learning (SSL) to pretrain a generalized laboratory progress (GLP) model that captures the overall progression of six common laboratory markers in prevalent cardiovascular cases, with the intention of transferring this knowledge to aid in the detection of specific cardiovascular event. METHODS AND PROCEDURES: GLP implemented a two-stage training approach, leveraging the information embedded within interpolated data and amplify the performance of SSL. After GLP pretraining, it is transferred for target vessel revascularization (TVR) detection. RESULTS: The proposed two-stage training improved the performance of pure SSL, and the transferability of GLP exhibited distinctiveness. After GLP processing, the classification exhibited a notable enhancement, with averaged accuracy rising from 0.63 to 0.90. All evaluated metrics demonstrated substantial superiority ([Formula: see text]) compared to prior GLP processing. CONCLUSION: Our study effectively engages in translational engineering by transferring patient progression of cardiovascular laboratory parameters from one patient group to another, transcending the limitations of data availability. The transferability of disease progression optimized the strategies of examinations and treatments, and improves patient prognosis while using commonly available laboratory parameters. The potential for expanding this approach to encompass other diseases holds great promise. CLINICAL IMPACT: Our study effectively transposes patient progression from one cohort to another, surpassing the constraints of episodic observation. The transferability of disease progression contributed to cardiovascular event assessment.

Undergraduate nurses' reflections on visual thinking learning to construct inductive reasoning through situated patient pictures: A mixed-method study.

BACKGROUND/OBJECTIVE: Deductive logic has often been used to develop critical thinking. However, inductive logical thinking, essential to care decision-making, has yet to be emphasized. This study aimed to explore visual thinking learning among undergraduate nursing students by asking them to draw situated patient pictures in order to integrate theoretical knowledge and promote inductive logical thinking. METHODS: A mixed-methods research design was used to obtain quantitative and qualitative data from a convenience sample of 100 students. The study was conducted in a Taiwanese university from September 2022 to January 2023. In the quantitative component, learners' views of situated patient pictures were captured based on 15 paired identifiers and two questions: (a) What word should be used in describing the situated patient's picture? (b) How strongly do you feel about the selection? Written feedback was analyzed using qualitative content analysis. RESULTS: Quantitative analysis identified specific, unpretentious, humorous, harmonious, conservative, realistic, rational, entire, image performance, professional performance, understandable, expressive, static performance, rigorous, and profuse with a reasonable degree of choice. Qualitative analysis identified four stages in participants' development of inductive reasoning through situated patient pictures and visual thinking learning. These were: exploration, intuition, theme, and logic and creation. CONCLUSIONS: The results suggest that visual thinking learning is a practical pedagogical approach to increasing learners' communication abilities, group cooperation, theoretical knowledge integration, and logical thinking. Neither educators nor learners required any artistic skills. Nonetheless, participants demonstrated creativity and innovation through continuous visual thinking learning.

Identifying KCNJ5 Mutation in Aldosterone-Producing Adenoma Patients With Baseline Characteristics Using Machine Learning Technology.

Background: Primary aldosteronism is characterized by inappropriate aldosterone production, and unilateral aldosterone-producing adenoma (uPA) is a common type of PA. KCNJ5 mutation is a protective factor in uPA; however, there is no preoperative approach to detect KCNJ5 mutation in patients with uPA. Objectives: This study aimed to provide a personalized surgical recommendation that enables more confidence in advising patients to pursue surgical treatment. Methods: We enrolled 328 patients with uPA harboring KCNJ5 mutations (n = 158) or not (n = 170) who had undergone adrenalectomy. Eighty-seven features were collected, including demographics, various blood and urine test results, and clinical comorbidities. We designed 2 versions of the prediction model: one for institutes with complete blood tests (full version), and the other for institutes that may not be equipped with comprehensive testing facilities (condensed version). Results: The results show that in the full version, the Light Gradient Boosting Machine outperformed other classifiers, achieving area under the curve and accuracy values of 0.905 and 0.864, respectively. The Light Gradient Boosting Machine also showed excellent performance in the condensed version, achieving area under the curve and accuracy values of 0.867 and 0.803, respectively. Conclusions: We simplified the preoperative diagnosis of KCNJ5 mutations successfully using machine learning. The proposed lightweight tool that requires only baseline characteristics and blood/urine test results can be widely applied and can aid personalized prediction during preoperative counseling for patients with uPA.

Professional Accountability of Caring for Patients with COVID-19: A Phenomenographic Study.

The purpose of this study was to explore nurses' care experiences for COVID-19 patients during the pandemic in Taiwan. The qualitative approach of phenomenography was used. Thirty-four nurses were recruited from two assigned hospitals in which COVID-19 patients were treated in Taiwan from July to May 2021. The method of data collection in the study involved a semi-structured interview and drawing. Interviews were audio-recorded and transcribed verbatim. Phenomenographic analysis was used to analyze the qualitative data. Four categories of description of experiences of caring for COVID-19 patients were identified: facing uncountable stresses from all sides, strict implementation of infection control interventions to provide safe care, confronting ethical dilemmas and making difficult decisions, and reflecting on the meaning of care in nursing. Professional accountability was the core theme found to represent the central meaning of nurses caring for COVID-19 patients. Nurses were under enormous stress while caring for COVID-19 patients during the pandemic and were negatively affected physically, psychologically, and socially. Professional accountability in caring for COVID-19 patients can be enhanced through adequate support from nursing managers and by in-service training designed to update knowledge and skills related to infection control intervention.

Clinical Instructors' Perspectives on the Assessment of Clinical Knowledge of Undergraduate Nursing Students: A Descriptive Phenomenological Approach.

This study aimed to determine clinical instructors' perceptions of the assessments used to evaluate the clinical knowledge of undergraduate nursing students. This study uses a descriptive phenomenological approach. Purposive sampling was used to recruit sixteen clinical instructors for semi-structured interviews between August and December 2019. All interviews were audio recorded and transcribed verbatim. Data were analyzed using a modified Colaizzi's seven-step method. Four criteria were used to ensure the study's validity: credibility, transferability, dependability, and confirmability. Three themes were identified in the clinical instructors' views on evaluating the clinical performance of student nurses: familiarity with students, patchwork clinical learning, and differing perceptions of the same scoring system. The study results suggest a need for a reliable, valid, and consistent approach to evaluating students' clinical knowledge. If the use of patchwork clinical internships for student nurses is unavoidable, a method for assessing student nurses' clinical performance that requires instructor consensus is necessary.

Experiences of oncology healthcare personnel in international medical service quality: a phenomenological study.

BACKGROUND: With the globalization of medical services on the rise, Asia has ascended to a destination of choice for its high-quality medical services at very reasonable rates. Monitoring the quality of the international medical industry is vital to maintain service demand. The experiences of healthcare personnel (HCP) involved in international medical services (IMS) regarding the provision of services to international cancer patients have not yet been discussed. This study aimed to explore oncology HCP experiences of IMS quality in caring for international cancer patients in Taiwan. METHODS: Descriptive phenomenological method and were analyzed through Colaizzi's seven-step approach. In this study, 19 respondents were collected data by using in-depth semi-structured interviews. An average interview lasted approximately 45 min. RESULTS: Four major themes were identified from the interviews: patient selection, psycho-oncology care, predicaments, and promoting suggestions. Additionally, thirteen subthemes emerged, including necessary selection of patients, reasons for unwillingness to enroll international patients, helpless patients, emotional distress, care with warmth, insufficient manpower, an unfair reward mechanism, poor hardware equipment, the predicaments of oncology care, various publicity strategies, one-on-one service model, design of a designated area, and reasonable benefit distribution. CONCLUSIONS: This study explored oncology HCP experiences of IMS quality in caring for international cancer patients, with implications for hospitals in developing high-quality IMS. Due to the fact that IMS is a global trend, HCPs, administrators, and policy-makers are advised to improve the quality of IMS in the oncology department, which has been the least studied field in IMS quality.

An Exploration of Psychological Resilience among Undergraduate Nursing Students Undertaking an Adult Nursing Virtual Practicum during the Coronavirus Pandemic in Taiwan: A Qualitative Study.

This qualitative study aimed to explore the psychological resilience of undergraduate nursing students partaking in a virtual practicum during the coronavirus pandemic (COVID-19) in Taiwan. The virtual practicum, a form of online learning, creates challenges compared to the traditional teaching-learning experience of an actual clinical placement. Exploring how students overcome learning difficulties and build resilience is necessary for a new learning environment or for future online learning. Constructivist grounded theory and the Standards for Reporting Qualitative Research checklist were followed. Purposive and theoretical sampling were used to recruit 18 student nurses for data saturation. Semi-structured, face-to-face interviews were conducted individually to collect data. Initial, focused, and theoretical coding and constant comparative data analysis were performed. Credibility, originality, resonance, and usefulness guided the assessment of the study's quality. The core category of psychological resilience in the virtual practicum was constructed to reflect Taiwanese nursing students' progress and experiences of learning during the virtual practicum. This core category consisted of three subcategories: (i) learning difficulties within one's inner self; (ii) staying positive and confident; and (iii) knowing what is possible. The findings identified psychological resilience as an important factor for students to adjust to the adverse experiences of a rapidly changing learning environment, such as the virtual practicum. The substantive theory of psychological resilience provided a frame of reference for coping with possible future difficulties. Correspondingly, psychological resilience reflected individuals' potential characteristics and may help students to enter and remain in the nursing profession.

Risk of cognitive impairment in men with advanced prostate cancer treated with NHAs: A systematic review and network meta-analysis.

Novel hormonal agents (NHAs) have significantly improved outcomes in men with advanced prostate cancer. However, it remains unclear whether NHAs are associated with subsequent cognitive impairment. Thus, we sought to perform a network meta-analysis to compare the risk of cognitive impairment across NHA types. Databases (PubMed, Embase, Scopus, and Web of Science), trial registries (Clinicaltrial.gov), the European Medicines Agency, and the US Food and Drug Administration drug safety reports were searched from inception through July 30, 2021. Eligible studies were clinical trials evaluating the risk of cognitive impairment between NHAs and placebo/standard care. Two independent investigators extracted the data and performed quality assessments using the Cochrane Risk of Bias Tool and ROBINS-I. We estimated the risk ratios by the frequentist approach and calculated the ranking probabilities of all treatments with the surface under the cumulative ranking probabilities. The primary outcome and secondary outcome were odds ratio (OR) and incidence rate ratio of cognitive impairment, respectively. We identified 15 trials with 14,723 participants comparing HNAs with placebo/standard care. Treatments associated with cognitive impairment, from the most to the least, were enzalutamide (OR, 3.66; 95% confidence interval [CI], 2.84-4.73), apalutamide (OR, 1.76; 95% CI, 1.08-2.87), abiraterone acetate (OR, 1.64; 95% CI, 1.01-2.45), and darolutamide (OR, 1.11 95% CI, 0.51-2.39). After adjustment of treatment time duration, enzalutamide still had the highest risk of cognitive impairment with an incidence rate ratio of 2.17 (95% CI, 1.65-2.78). These findings suggest that NHAs, especially enzalutamide, may increase the risk of cognitive impairment compared with placebo/standard care.

Family Caregivers' Experiences of Preventing Harm to Older People during Hospitalization: A Phenomenographic Study.

Hospital admission is associated with a high risk of harm, particularly for older people, and family members play a critical role in providing care. The aim of this study was to explore family caregivers' experiences in preventing harm to older people during hospitalization. The phenomenographic approach was applied. Thirty family caregivers were asked to describe their experiences of preventing harm to older people. Semi-structured interviews were audiotaped and transcribed. Participants described preventing harm as "essential care", "an important step toward recovery", "a load off the mind", "outcomes of collaboration among caregivers and health professionals", and "improvement in the quality of life after discharge". The core theme was to achieve the goal of integrated care for older people. The results can help improve caregiving processes and prevent harm to older people during hospitalizations. They can assist in developing strategies for the delivery of safe care for older people.

Deep Learning and Explainable Artificial Intelligence to Predict Patients' Choice of Hospital Levels in Urban and Rural Areas.

Maldistribution of healthcare resources among urban and rural areas is a significant challenge worldwide. People living in rural areas may have limited access to medical resources, and often neglect their health problems or receive insufficient care services. This research uses a deep learning approach to predict patient choices regarding hospital levels (primary, secondary or tertiary hospitals) and interpret the model decision using explainable artificial intelligence. We proposed an autoencoder-deep neural network framework and trained region-based models for the urban and rural areas. The models achieve an area under the receiver operating characteristics curve (AUC) of 0.94 and 0.95, and an accuracy of 0.93 and 0.92 for the urban and rural areas, respectively. This result indicates that region-based models are effective in improving the performance. The result is potentially leading to appropriate policy planning. Further interpretation can be done to investigate the explicit differentiation of the rural and urban scenarios.

Effectiveness of the use of concept maps and simulated cases as a teaching-learning strategy in enhancing the learning confidence of baccalaureate nursing students: A qualitative approach.

BACKGROUND: Didactic lectures and exam-oriented learning can lead to students becoming passive learners who rely on rote memory. This learning style negatively impacts their ability to cultivate the core nursing values and critical thinking. OBJECTIVES: This study aimed to investigate the impact of a concept mapping teaching-learning strategy on undergraduate nursing students' ability to integrate theoretical biosciences knowledge into care practice and on their skills in critical thinking and teamwork. METHODS: A qualitative research design was adopted. A course entitled Evaluation and Analysis of Adult Nursing Cases was developed based on a concept mapping strategy involving 24 simulated cases relevant to medical and surgical nursing. The participants were students from the two-year undergraduate nursing programme at a university in Taiwan. Data were collected from September 2020 to February 2021. Qualitative data were collected from semi-structured face-to-face interviews with 20 students and from 100 reflective reports on students' learning journeys. The data were analysed using qualitative content analysis. RESULTS: Two major themes were identified: (1) changes in learning style and thinking and (2) rewards from learning. The participants reported that their learning style had changed from reliance on rote learning to image memory, and their thinking process from linear (cause-effect) to multifaceted thinking at different levels. The teaching and learning strategies contributed to feelings of ability advancement and psychological safety, which led to learning achievement and confidence. CONCLUSION: The use of a concept mapping strategy and simulated cases enhanced students' learning by enabling them to integrate theoretical knowledge and improve their thinking abilities. The teaching and learning strategies helped participants in learning about psychological safety and increased their learning confidence.

Exploring the experience of reflective writing among Taiwanese undergraduate nursing students: A qualitative study.

BACKGROUND: Reflective learning plays an important role in students' professional and personal development. However, some nursing curricula provide insufficient opportunity for students to understand how to reflect and what reflection is. PURPOSE: The study aimed to explore baccalaureate nursing students' experiences of reflective writing. DESIGN: The study used a hermeneutic phenomenological approach. METHODS: Through purposive sampling, 15 participants were recruited for individual in-depth face-to-face interviews which were conducted after they had completed the course 'Application of Emergency Nursing'. Interviews were semi-structured and audio-recorded. Additional data were obtained from 20 documents on consulting faculty for reflective writing. Data analysis was undertaken through a hermeneutic phenomenological framework based on van Manen's approach. RESULTS: Participants reported that reflective writing had helped them to optimise their personal and professional development. Four themes emerged from the analysis: recording a personal story, presenting a process of events, confronting challenges, and strengthening personal characteristics. CONCLUSIONS: Students were satisfied with their learning achievements and growth and felt they had become better through reflective writing. The results demonstrated that: reflective writing needs to be elaborated objectively and carefully; continuing self-dialogue can reveal the true meaning of an incident; students learned strategies to apply in future situations.

Predicting Postoperative Mortality With Deep Neural Networks and Natural Language Processing: Model Development and Validation.

BACKGROUND: Machine learning (ML) achieves better predictions of postoperative mortality than previous prediction tools. Free-text descriptions of the preoperative diagnosis and the planned procedure are available preoperatively. Because reading these descriptions helps anesthesiologists evaluate the risk of the surgery, we hypothesized that deep learning (DL) models with unstructured text could improve postoperative mortality prediction. However, it is challenging to extract meaningful concept embeddings from this unstructured clinical text. OBJECTIVE: This study aims to develop a fusion DL model containing structured and unstructured features to predict the in-hospital 30-day postoperative mortality before surgery. ML models for predicting postoperative mortality using preoperative data with or without free clinical text were assessed. METHODS: We retrospectively collected preoperative anesthesia assessments, surgical information, and discharge summaries of patients undergoing general and neuraxial anesthesia from electronic health records (EHRs) from 2016 to 2020. We first compared the deep neural network (DNN) with other models using the same input features to demonstrate effectiveness. Then, we combined the DNN model with bidirectional encoder representations from transformers (BERT) to extract information from clinical texts. The effects of adding text information on the model performance were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). Statistical significance was evaluated using P<.05. RESULTS: The final cohort contained 121,313 patients who underwent surgeries. A total of 1562 (1.29%) patients died within 30 days of surgery. Our BERT-DNN model achieved the highest AUROC (0.964, 95% CI 0.961-0.967) and AUPRC (0.336, 95% CI 0.276-0.402). The AUROC of the BERT-DNN was significantly higher compared to logistic regression (AUROC=0.952, 95% CI 0.949-0.955) and the American Society of Anesthesiologist Physical Status (ASAPS AUROC=0.892, 95% CI 0.887-0.896) but not significantly higher compared to the DNN (AUROC=0.959, 95% CI 0.956-0.962) and the random forest (AUROC=0.961, 95% CI 0.958-0.964). The AUPRC of the BERT-DNN was significantly higher compared to the DNN (AUPRC=0.319, 95% CI 0.260-0.384), the random forest (AUPRC=0.296, 95% CI 0.239-0.360), logistic regression (AUPRC=0.276, 95% CI 0.220-0.339), and the ASAPS (AUPRC=0.149, 95% CI 0.107-0.203). CONCLUSIONS: Our BERT-DNN model has an AUPRC significantly higher compared to previously proposed models using no text and an AUROC significantly higher compared to logistic regression and the ASAPS. This technique helps identify patients with higher risk from the surgical description text in EHRs.

GRK3 as a Prognosis Biomarker in Gastric Cancer.

Background: Globally, gastric cancer is ranked 4th and 3rd in terms of incidence and mortality rate among all cancer types. This study aimed to examine the relationship between G protein-coupled receptor kinase 3 (GRK3) and gastric cancer prognosis and investigate the role of GRK3 in gastric cancer carcinogenesis. Methods: GRK3 level in gastric tissues and cells were determined using immunohistochemistry and immunoblotting. Kaplan-Meier analysis with the log-rank test was employed to evaluate the relationship between GRK3 expression and gastric cancer prognosis. RNAi technology was applied to examine the effects of GRK3 inhibition on gastric cancer proliferation and spread. Results: GRK3 overexpression was correlated significantly with lymphatic metastasis (P = 0.0011), distant metastasis (P < 0.0001), TNM stage (P = 0.0035), and vascular invasion (P = 0.0025). Kaplan-Meier survival analysis showed that the disease-free survival and overall survival of patients with high GRK3 expression were significantly shorter than those of patients with low GRK3 expression. Multivariate Cox regression analysis also showed that the overexpression of GRK3 was an independent prognostic biomarker of gastric cancer (P = 0.029). In cultured gastric cancer cells, GRK3 knockdown inhibited cell proliferation, migration, and invasion. Further analysis revealed that more GRK3-knockdown cells were in G0/G1 phase and few cells were in S phase, thereby inhibiting cell proliferation. Conclusions: GRK3 overexpression can be a candidate biomarker for gastric cancer prognosis. GRK3 is also a potential therapeutic target for gastric cancer.

Predicting the Travel Distance of Patients to Access Healthcare Using Deep Neural Networks.

OBJECTIVE: Improving geographical access remains a key issue in determining the sufficiency of regional medical resources during health policy design. However, patient choices can be the result of the complex interactivity of various factors. The aim of this study is to propose a deep neural network approach to model the complex decision of patient choice in travel distance to access care, which is an important indicator for policymaking in allocating resources. METHOD: We used the 4-year nationwide insurance data of Taiwan and accumulated the possible features discussed in earlier literature. This study proposes the use of a convolutional neural network (CNN)-based framework to make predictions. The model performance was tested against other machine learning methods. The proposed framework was further interpreted using Integrated Gradients (IG) to analyze the feature weights. RESULTS: We successfully demonstrated the effectiveness of using a CNN-based framework to predict the travel distance of patients, achieving an accuracy of 0.968, AUC of 0.969, sensitivity of 0.960, and specificity of 0.989. The CNN-based framework outperformed all other methods. In this research, the IG weights are potentially explainable; however, the relationship does not correspond to known indicators in public health. CONCLUSIONS: Our results demonstrate the feasibility of the deep learning-based travel distance prediction model. It has the potential to guide policymaking in resource allocation. Clinical and Translational Impact Statement- Deep learning technology is feasible in investigating the distance that patients would travel while accessing care. It is a tool that integrates complex interactive variables with highly imbalanced data distributions.

Effect of implementing decision support to activate a rapid response system by automated screening of verified vital sign data: A retrospective database study.

AIM: Activating a rapid response system (RRS) at general wards requires memorizing trigger criteria, identifying deterioration, and timely notification of abnormalities. We aimed to assess the effect of decision support (DS)-linked RRS activation on management and outcomes. METHODS: We retrospectively analyzed general ward RRS activation cases from 2013 to 2017 and the incidence of cardiopulmonary resuscitations (CPR) from 2013 to 2020. A DS-alerting mechanism was added to the conventional RRS activation process in 2017, with an alert window appearing whenever the system automatically detected any verified abnormal vital sign entry, alerting the nurse to take further action. Logistic and linear regression analyses were used to compare outcomes. RESULTS: We analyzed 27,747 activations and 64,592 DS alerts. RRS activations increased from 3.5 to 30.3 per 1,000 patient-days (P < 0.001) after DS implementation. The first DS activations occurred earlier than conventional ones (-2.9 days, 95% confidence interval = -3.6 to -2.1 days). After adjustment with inverse probability of treatment weighting, main (conventional vs DS-linked activations after implementation) and sensitivity analyses showed that DS activation cases had a lower risk of CPR and in-hospital mortality. Cases with more DS alerts before RRS activation had a higher risk of CPR (P trend = 0.017) and in-hospital mortality (P trend < 0.001). The incidence of CPR at the general ward decreased. CONCLUSION: Implementing a DS mechanism with an automated screening of verified abnormal vital signs linked to RRS activations at general wards was associated with improved practice and timeliness of hospital-wide RRS activations and reduced in-hospital resuscitations and mortality.

Using a Motivational Paradigm to Develop an Exercise Program for Nurses with High Risk of Metabolic Syndrome.

Nurses are frontline care providers whose health is vital to providing good quality of care to patients. The purpose of this study was to develop an exercise program for high-risk metabolic syndrome nurses based on the transtheoretical model. The transtheoretical model was used in this study due to its popular use in exercise behavior change and it can clearly identify the stage of exercise so as to plan an effective program to promote health. This was a quasi-experimental pilot study with a total of 40 participants who met the inclusion criteria. Exercise programs were developed for three groups distinguished by their commitment to exercising for health. Sixteen (40%) nurses moved one step forward, six (15%) nurses moved backward, and eighteen (45%) nurses maintained at the same stage over time (stable sedentary, 40%; stable active, 5%). Bowker's test of symmetry, χ2 = 14.00 (p < 0.01), revealed that the population exercising increased significantly after the intervention. After the program, the perceived benefits from exercise in the decisional balance significantly increased to 1.53 (t = 2.223, p < 0.05), perceived exercise barriers significantly decreased to 3.10 (t = −3.075, p < 0.05), and self-efficacy significantly increased to 2.90 (t = 3.251, p < 0.01), respectively. Applying the transtheoretical model to health behavior enables significant change. The benefits of applying the transtheoretical model for promoting exercise include increasing perceived exercise benefits and self-efficacy, decreasing perceived exercise barriers, and increasing physical activity levels.

Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database-HF_Lung_V1.

A reliable, remote, and continuous real-time respiratory sound monitor with automated respiratory sound analysis ability is urgently required in many clinical scenarios-such as in monitoring disease progression of coronavirus disease 2019-to replace conventional auscultation with a handheld stethoscope. However, a robust computerized respiratory sound analysis algorithm for breath phase detection and adventitious sound detection at the recording level has not yet been validated in practical applications. In this study, we developed a lung sound database (HF_Lung_V1) comprising 9,765 audio files of lung sounds (duration of 15 s each), 34,095 inhalation labels, 18,349 exhalation labels, 13,883 continuous adventitious sound (CAS) labels (comprising 8,457 wheeze labels, 686 stridor labels, and 4,740 rhonchus labels), and 15,606 discontinuous adventitious sound labels (all crackles). We conducted benchmark tests using long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional LSTM (BiLSTM), bidirectional GRU (BiGRU), convolutional neural network (CNN)-LSTM, CNN-GRU, CNN-BiLSTM, and CNN-BiGRU models for breath phase detection and adventitious sound detection. We also conducted a performance comparison between the LSTM-based and GRU-based models, between unidirectional and bidirectional models, and between models with and without a CNN. The results revealed that these models exhibited adequate performance in lung sound analysis. The GRU-based models outperformed, in terms of F1 scores and areas under the receiver operating characteristic curves, the LSTM-based models in most of the defined tasks. Furthermore, all bidirectional models outperformed their unidirectional counterparts. Finally, the addition of a CNN improved the accuracy of lung sound analysis, especially in the CAS detection tasks.

Standard risk assessment forms help reduce preventable harm in older adult inpatients: A retrospective chart review study.

AIMS: To examine nurse documentation of assessments using standard risk assessment forms in older inpatients, and to determine the value of such assessment. DESIGN: Cross-sectional retrospective chart review. METHODS: This retrospective review of risk evaluation documentation in patients' medical records focused on skin, continence, medical complications, nutrition, cognition, mobility, medications and pain. RESULTS: A total of 1000 medical records from Taiwan hospitals were reviewed from January 2016 to December 2017, and 379 from Australian hospitals were reviewed from March 2011 to February 2012. Taiwanese patients with documented assessment of skin (aOR =2.94, 95%CI =1.88-4.54), nutrition (aOR =3.22, 95%CI =1.08-9.59), cognition (aOR =2.61, 95%CI =1.32-5.16) and pain (aOR =5.01, 95%CI=1.63-15.38) had significantly higher odds of developing new problems; while Australian patients with documented assessments of continence (aOR =11.55, 95%CI =1.48-90.45) and nutrition (aOR =12.90, 95%CI =1.67-99.06) had significantly higher odds of developing new problems. DISCUSSION: Nursing assessments and interventions documented in standard risk assessment forms help clinical nurses detect new preventable problems and prevent harm in older hospital inpatients across geographic locations and hospital types. Standard nursing forms can be used in clinical practice to guide proactive care by nurses to prevent harm during hospitalisation. IMPACT: Older inpatients are at risk of preventable harm and new health problems. The present study found that incorporating eight factors sensitive to nursing care into standard risk assessment forms can help reduce preventable harm in older inpatients. In addition, these forms guide assessment and intervention effectively in different countries.