Validation of a Deep Learning-based Automatic Detection Algorithm for Measurement of Endotracheal Tube-to-Carina Distance on Chest Radiographs.

BACKGROUND: Improper endotracheal tube (ETT) positioning is frequently observed and potentially hazardous in the intensive care unit. The authors developed a deep learning-based automatic detection algorithm detecting the ETT tip and carina on portable supine chest radiographs to measure the ETT-carina distance. This study investigated the hypothesis that the algorithm might be more accurate than frontline critical care clinicians in ETT tip detection, carina detection, and ETT-carina distance measurement. METHODS: A deep learning-based automatic detection algorithm was developed using 1,842 portable supine chest radiographs of 1,842 adult intubated patients, where two board-certified intensivists worked together to annotate the distal ETT end and tracheal bifurcation. The performance of the deep learning-based algorithm was assessed in 4-fold cross-validation (1,842 radiographs), external validation (216 radiographs), and an observer performance test (462 radiographs) involving 11 critical care clinicians. The performance metrics included the errors from the ground truth in ETT tip detection, carina detection, and ETT-carina distance measurement. RESULTS: During 4-fold cross-validation and external validation, the median errors (interquartile range) of the algorithm in ETT-carina distance measurement were 3.9 (1.8 to 7.1) mm and 4.2 (1.7 to 7.8) mm, respectively. During the observer performance test, the median errors (interquartile range) of the algorithm were 2.6 (1.6 to 4.8) mm, 3.6 (2.1 to 5.9) mm, and 4.0 (1.7 to 7.2) mm in ETT tip detection, carina detection, and ETT-carina distance measurement, significantly superior to that of 6, 10, and 7 clinicians (all P < 0.05), respectively. The algorithm outperformed 7, 3, and 0, 9, 6, and 4, and 5, 5, and 3 clinicians (all P < 0.005) regarding the proportions of chest radiographs within 5 mm, 10 mm, and 15 mm error in ETT tip detection, carina detection, and ETT-carina distance measurement, respectively. No clinician was significantly more accurate than the algorithm in any comparison. CONCLUSIONS: A deep learning-based algorithm can match or even outperform frontline critical care clinicians in ETT tip detection, carina detection, and ETT-carina distance measurement.

A comparative study of positive and negative electronic word-of-mouth on the SERVQUAL scale during the COVID-19 epidemic - taking a regional teaching hospital in Taiwan as an example.

BACKGROUND: In recent years, studies have shown that electronic WOM (eWOM) directly reflects consumers' post-purchase psychological perception and directly affects repurchase behavior. This information is valued by institutions in various fields. Within the scope of the evaluation of service characteristics, medical service is the least visible and most difficult service attribute to evaluate. Service organizations must have high trust attributes. Therefore, an eWOM review significantly influences people's decision-making process when choosing a healthcare provider. The purpose of this research is to combine eWOM reviews with the SERVQUAL scale in a comparative study of positive and negative eWOM reviews of a regional teaching hospital in Taiwan. METHODS: This research obtained data from publicly available eWOM reviews on Google Maps of a regional teaching hospital in Taiwan over the past 10 years (from June 24, 2011, to December 31, 2021) using website scraping technology. The semantic content analysis method was used in this study to classify eWOM reviews according to the revised PZB SERVQUAL scale. RESULTS: Statistical analysis was conducted. During the COVID-19 pandemic, positive reviews showed a downward trend. Among the five determinants of the SERVQUAL of PZB, positive eWOM reviews performed best in "assurance" with a positive review rate of 60.00%, followed by 42.11% for "reliability". For negative eWOM reviews, "assurance" performed the worst with a positive rate of 72.34%, followed by "responsiveness" at 28.37% and "reliability" at 26.95%. CONCLUSION: Since the onset of COVID-19 in 2020, negative eWOM has increased significantly and exceeded the amount of positive eWOM. Regardless of positive and negative reviews, what patients care most about is "assurance" of the professional attitude and skills of medical staff, which urgently needs to be strengthened. In addition, good "reliability" will help to develop positive eWOM. However, "responsiveness" as indicated by poor service waiting time can easily lead to the spread of negative eWOM. Hospital management should focus on these service-oriented qualities.

Integration of an Intensive Care Unit Visualization Dashboard (i-Dashboard) as a Platform to Facilitate Multidisciplinary Rounds: Cluster-Randomized Controlled Trial.

BACKGROUND: Multidisciplinary rounds (MDRs) are scheduled, patient-focused communication mechanisms among multidisciplinary providers in the intensive care unit (ICU). OBJECTIVE: i-Dashboard is a custom-developed visualization dashboard that supports (1) key information retrieval and reorganization, (2) time-series data, and (3) display on large touch screens during MDRs. This study aimed to evaluate the performance, including the efficiency of prerounding data gathering, communication accuracy, and information exchange, and clinical satisfaction of integrating i-Dashboard as a platform to facilitate MDRs. METHODS: A cluster-randomized controlled trial was performed in 2 surgical ICUs at a university hospital. Study participants included all multidisciplinary care team members. The performance and clinical satisfaction of i-Dashboard during MDRs were compared with those of the established electronic medical record (EMR) through direct observation and questionnaire surveys. RESULTS: Between April 26 and July 18, 2021, a total of 78 and 91 MDRs were performed with the established EMR and i-Dashboard, respectively. For prerounding data gathering, the median time was 10.4 (IQR 9.1-11.8) and 4.6 (IQR 3.5-5.8) minutes using the established EMR and i-Dashboard (P<.001), respectively. During MDRs, data misrepresentations were significantly less frequent with i-Dashboard (median 0, IQR 0-0) than with the established EMR (4, IQR 3-5; P<.001). Further, effective recommendations were significantly more frequent with i-Dashboard than with the established EMR (P<.001). The questionnaire results revealed that participants favored using i-Dashboard in association with the enhancement of care plan development and team participation during MDRs. CONCLUSIONS: i-Dashboard increases efficiency in data gathering. Displaying i-Dashboard on large touch screens in MDRs may enhance communication accuracy, information exchange, and clinical satisfaction. The design concepts of i-Dashboard may help develop visualization dashboards that are more applicable for ICU MDRs. TRIAL REGISTRATION: ClinicalTrials.gov NCT04845698; https://clinicaltrials.gov/ct2/show/NCT04845698.

The impact of the addition of nurse practitioners to surgical intensive care units: A retrospective cohort study.

BACKGROUND: Demand for surgical critical care is increasing, but work-hour restrictions on residents have affected many hospitals. Recently, the use of nurse practitioners (NPs) as providers in the intensive care unit (ICU) has expanded rapidly, although the impacts on quality of care have not been evaluated. OBJECTIVES: To compare the outcomes of critically ill surgical patients before and after the addition of NPs to the ICU team. METHODS: We conducted a retrospective cohort study in a Taiwanese surgical ICU. We compared the outcomes of patients admitted to ICU during the 2-year period before and after the addition of NPs to the ICU team. Patients admitted in the 1-year transition phase were excluded from comparisons. The primary endpoint was ICU mortality. Secondary endpoints included ICU length of stay and incidence of unplanned extubation. RESULTS: A total of 8747 patients were included in the study. For all eligible admissions, primary and secondary outcomes did not differ significantly between the two groups. For scheduled ICU admissions, ICU mortality was significantly lower after the addition of NPs (2.2% before vs. 1.1% after addition of NPs, p = 0.014). For unscheduled ICU admissions, ICU mortality did not differ significantly between the two groups. In the multivariate analysis, admission after the addition of NPs was associated with significantly reduced ICU mortality (odds ratio = 0.481; 95% confidence interval = 0.263-0.865; p = 0.015) among scheduled admissions. CONCLUSION: Incorporating NPs in the ICU team was associated with improved outcomes in scheduled admissions to surgical ICU when compared with a traditional, resident-based team.

The choice of Taiwanese college students to vaccinate against severe special infectious pneumonia COVID-19 based on the integrated theory of planning behavior.

Taiwan's coronavirus (COVID-19) vaccine procurement was delayed until October 2021. With the vaccine's introduction in Taiwan, the public will have an opportunity to choose vaccination. Choosing to vaccinate involves considerations regarding the trade-off between the protective power of the vaccine and its side effects, which is a planned behavior. College students have considered high-risk objects for COVID-19 outbreaks given their lifestyle, and their efficient vaccination may help reduce mutual infection between college students and the general public. This study obtained 707 valid questionnaires from Taiwan college students (20 years old and above). We investigated several factors during our college students' survey regarding vaccination. Among this integrated TPB model, "Attitude," "Subjective Norm," "Perceived Behavioral Control," and "COVID-19 Information Asymmetry" had a positive impact on vaccination "Behavioral Intention." COVID-19 information asymmetry positively and significantly affected behavioral intention through perceived behavioral control, while perceived behavioral control had a mediating effect. To promote the behavioral intention of college students to choose COVID-19 vaccination, public and private departments for epidemic prevention must aim to overcome the self-efficacy barriers of perceived behavioral control and promote the primary group influence effect of subjective norm and the self-interest factor of attitude. Governments and NGOs should also ensure prompt and accurate transmission of epidemic and vaccine information and actively investigate and prohibit misleading details from unknown sources and no scientific basis. Such a policy will generate trust, effectively increasing the vaccination rate and reducing cluster infection.

Detecting Endotracheal Tube and Carina on Portable Supine Chest Radiographs Using One-Stage Detector with a Coarse-to-Fine Attention.

In intensive care units (ICUs), after endotracheal intubation, the position of the endotracheal tube (ETT) should be checked to avoid complications. The malposition can be detected by the distance between the ETT tip and the Carina (ETT-Carina distance). However, it struggles with a limited performance for two major problems, i.e., occlusion by external machine, and the posture and machine of taking chest radiographs. While previous studies addressed these problems, they always suffered from the requirements of manual intervention. Therefore, the purpose of this paper is to locate the ETT tip and the Carina more accurately for detecting the malposition without manual intervention. The proposed architecture is composed of FCOS: Fully Convolutional One-Stage Object Detection, an attention mechanism named Coarse-to-Fine Attention (CTFA), and a segmentation branch. Moreover, a post-process algorithm is adopted to select the final location of the ETT tip and the Carina. Three metrics were used to evaluate the performance of the proposed method. With the dataset provided by National Cheng Kung University Hospital, the accuracy of the malposition detected by the proposed method achieves 88.82% and the ETT-Carina distance errors are less than 5.333±6.240 mm.

Data Science for Extubation Prediction and Value of Information in Surgical Intensive Care Unit.

Besides the traditional indices such as biochemistry, arterial blood gas, rapid shallow breathing index (RSBI), acute physiology and chronic health evaluation (APACHE) II score, this study suggests a data science framework for extubation prediction in the surgical intensive care unit (SICU) and investigates the value of the information our prediction model provides. A data science framework including variable selection (e.g., multivariate adaptive regression splines, stepwise logistic regression and random forest), prediction models (e.g., support vector machine, boosting logistic regression and backpropagation neural network (BPN)) and decision analysis (e.g., Bayesian method) is proposed to identify the important variables and support the extubation decision. An empirical study of a leading hospital in Taiwan in 2015-2016 is conducted to validate the proposed framework. The results show that APACHE II and white blood cells (WBC) are the two most critical variables, and then the priority sequence is eye opening, heart rate, glucose, sodium and hematocrit. BPN with selected variables shows better prediction performance (sensitivity: 0.830; specificity: 0.890; accuracy 0.860) than that with APACHE II or RSBI. The value of information is further investigated and shows that the expected value of experimentation (EVE), 0.652 days (patient staying in the ICU), is saved when comparing with current clinical experience. Furthermore, the maximal value of information occurs in a failure rate around 7.1% and it reveals the "best applicable condition" of the proposed prediction model. The results validate the decision quality and useful information provided by our predicted model.

The association between recent hospitalized COPD exacerbations and adverse outcomes after percutaneous coronary intervention: a nationwide cohort study.

PURPOSE: COPD is associated with coronary artery disease, and exacerbations are major events in COPD. However, the impact of recent hospitalized exacerbations on outcomes of percutaneous coronary intervention (PCI) remains underdetermined. PATIENTS AND METHODS: Using the National Health Insurance Research Database of Taiwan, we identified 215,275 adult patients who underwent first-time PCI between 2000 and 2012. Among these patients, 15,485 patients had COPD. The risks of hospital mortality, overall mortality, and adverse cardiovascular outcomes after PCI (ie, ischemic events, repeat revascularization, cerebrovascular events, and major adverse cardiac and cerebrovascular events [MACCEs]) in relation to COPD, and the frequency and timing of recent hospitalized exacerbations within 1 year before PCI were estimated. RESULTS: COPD was independently associated with increased risks of hospital mortality, overall mortality, ischemic events, cerebrovascular events, and MACCE during follow-up after PCI. Among cerebrovascular events, ischemic rather than hemorrhagic stroke was more likely to occur. In COPD patients, recent hospitalized exacerbations further increased the risks of overall mortality, ischemic events, and MACCE following PCI. Notably, patients with more frequent or more recent hospitalized exacerbations had a trend toward higher risks of these adverse events (all P-values for trend <0.0001), especially those with ≥2 exacerbations within 1 year or any exacerbation within 1 month before PCI. CONCLUSION: Integrated care is urgently needed to alleviate COPD-related morbidity and mortality after PCI, especially for patients with a recent hospitalized exacerbation.

Autophagic proteins regulate cigarette smoke-induced apoptosis: protective role of heme oxygenase-1.

Cigarette smoke-induced cell death contributes to the pathogenesis of chronic obstructive pulmonary disease, though the relative roles of apoptosis and autophagy remain unclear. The inducible stress protein heme oxygenase-1 (HO-1) confers cytoprotection against oxidative stress. We examined the relationships between these processes in human bronchial epithelial cells (Beas-2b) exposed to cigarette smoke extract (CSE). CSE induced morphological and biochemical markers of autophagy in Beas-2b cells and induced autophagosome formation as evidenced by formation of GFP-LC3 puncta and electron microscopic analysis. Furthermore, CSE increased the processing of microtubule-associated protein-1 light chain-3 (LC3B-I) to LC3B-II, within 1 hr of exposure. Increased LC3B-II was associated with increased autophagy, since inhibitors of lysosomal proteases and of autophagosome-lysosome fusion further increased LC3B-II levels during CSE exposure. CSE concurrently induced extrinsic apoptosis in Beas-2b cells involving early activation of death-inducing-signaling-complex (DISC) formation and downstream activation of caspases (-8,-9,-3). The induction of extrinsic apoptosis by CSE was dependent in part on autophagic proteins. Reduction of Beclin 1 levels with beclin 1 siRNA inhibited DISC formation and caspase-3/8 activation in response to CSE. LC3B siRNA also inhibited caspase-3/8 activation. The stress protein HO-1 protected against CSE-induced cell death by concurrently downregulating apoptosis and autophagy-related signaling. Adenoviral mediated expression of HO-1 inhibited DISC formation and caspase-3/9 activation in CSE-treated epithelial cells, diminished the expression of Beclin 1, and partially inhibited the processing of LC3B-I to LC3B-II. Conversely, transfection of Beas-2b with ho-1 siRNA augmented CSE-induced DISC formation and increased intracellular reactive oxygen species formation. HO-1 expression augmented CSE-induced phosphorylation of NFkappaB p65 in Beas-2b cells. Consistently, expression of IkappaB, the inhibitor of NFkappaB, increased CSE-induced DISC formation. LC3B siRNA also enhanced p65 phosphorylation. In fibroblasts from beclin 1 heterozygous knockout mice, p65 phosphorylation was dramatically upregulated, while CSE-induced DISC formation was inhibited, consistent with an anti-apoptotic role for NFkappaB and a pro-apoptotic role for Beclin 1. These studies demonstrated an interdependence of autophagic and apoptogenic signaling in CSE-induced cell death, and their coordinated downregulation by HO-1. An understanding of the regulation of cell death pathways during smoke exposure may provide therapeutic strategies in smoke-related illness.