Analysis of the impact of maternal sepsis on pregnancy outcomes: a population-based retrospective study.

BACKGROUND: To investigate the association between maternal sepsis during pregnancy and poor pregnancy outcome and to identify risk factors for poor birth outcomes and adverse perinatal events. METHODS: We linked the Taiwan Birth Cohort Study (TBCS) database and the Taiwanese National Health Insurance Database (NHID) to conduct this population-based study. We analysed the data of pregnant women who met the criteria for sepsis-3 during pregnancy between 2005 and 2017 as the maternal sepsis cases and selected pregnant women without infection as the non-sepsis comparison cohort. Sepsis during pregnancy and fulfilled the sepsis-3 definition proposed in 2016. The primary outcome included low birth weight (LBW, < 2500 g) and preterm birth (< 34 weeks), and the secondary outcome was the occurrence of adverse perinatal events. RESULTS: We enrolled 2,732 women who met the criteria for sepsis-3 during pregnancy and 196,333 non-sepsis controls. We found that the development of maternal sepsis was highly associated with unfavourable pregnancy outcomes, including LBW (adjOR 9.51, 95% CI 8.73-10.36), preterm birth < 34 weeks (adjOR 11.69, 95%CI 10.64-12.84), and the adverse perinatal events (adjOR 3.09, 95% CI 2.83-3.36). We also identified that socio-economically disadvantaged status was slightly associated with an increased risk for low birth weight and preterm birth. CONCLUSION: We found that the development of maternal sepsis was highly associated with LBW, preterm birth and adverse perinatal events. Our findings highlight the prolonged impact of maternal sepsis on pregnancy outcomes and indicate the need for vigilance among pregnant women with sepsis.

The application of machine learning for identifying frailty in older patients during hospital admission.

BACKGROUND: Early identification of frail patients and early interventional treatment can minimize the frailty-related medical burden. This study investigated the use of machine learning (ML) to detect frailty in hospitalized older adults with acute illnesses. METHODS: We enrolled inpatients of the geriatric medicine ward at Taichung veterans general hospital between 2012 and 2022. We compared four ML models including logistic regression, random forest (RF), extreme gradient boosting, and support vector machine (SVM) for the prediction of frailty. The feature window as well as the prediction window was set as half a year before admission. Furthermore, Shapley additive explanation plots and partial dependence plots were used to identify Fried's frailty phenotype for interpreting the model across various levels including domain, feature, and individual aspects. RESULTS: We enrolled 3367 patients. Of these, 2843 were frail. We used 21 features to train the prediction model. Of the 4 tested algorithms, SVM yielded the highest AUROC, precision and F1-score (78.05%, 94.53% and 82.10%). Of the 21 features, age, gender, multimorbidity frailty index, triage, hemoglobin, neutrophil ratio, estimated glomerular filtration rate, blood urea nitrogen, and potassium were identified as more impactful due to their absolute values. CONCLUSIONS: Our results demonstrated that some easily accessed parameters from the hospital clinical data system can be used to predict frailty in older hospitalized patients using supervised ML methods.

An automated ICU agitation monitoring system for video streaming using deep learning classification.

OBJECTIVE: To address the challenge of assessing sedation status in critically ill patients in the intensive care unit (ICU), we aimed to develop a non-contact automatic classifier of agitation using artificial intelligence and deep learning. METHODS: We collected the video recordings of ICU patients and cut them into 30-second (30-s) and 2-second (2-s) segments. All of the segments were annotated with the status of agitation as "Attention" and "Non-attention". After transforming the video segments into movement quantification, we constructed the models of agitation classifiers with Threshold, Random Forest, and LSTM and evaluated their performances. RESULTS: The video recording segmentation yielded 427 30-s and 6405 2-s segments from 61 patients for model construction. The LSTM model achieved remarkable accuracy (ACC 0.92, AUC 0.91), outperforming other methods. CONCLUSION: Our study proposes an advanced monitoring system combining LSTM and image processing to ensure mild patient sedation in ICU care. LSTM proves to be the optimal choice for accurate monitoring. Future efforts should prioritize expanding data collection and enhancing system integration for practical application.

Anaemia in the first week may be associated with long-term mortality among critically ill patients: propensity score-based analyses.

BACKGROUND: Anaemia is highly prevalent in critically ill patients; however, the long-term effect on mortality remains unclear. METHODS: We retrospectively included patients admitted to the medical intensive care units (ICUs) during 2015-2020 at the Taichung Veterans General Hospital. The primary outcome of interest was one-year mortality, and hazard ratios (HRs) with 95% confidence intervals (CIs) were determined to assess the association. We used propensity score matching (PSM) and propensity score matching methods, including inverse probability of treatment weighting (IPTW) as well as covariate balancing propensity score (CBPS), in the present study. RESULTS: A total of 7,089 patients were eligible for analyses, and 45.0% (3,189/7,089) of them had anaemia, defined by mean levels of haemoglobin being less than 10 g/dL. The standardised difference of covariates in this study were lower than 0.20 after matching and weighting. The application of CBPS further reduced the imbalance among covariates. We demonstrated a similar association, and adjusted HRs in original, PSM, IPTW and CBPS populations were 1.345 (95% CI 1.227-1.474), 1.265 (95% CI 1.145-1.397), 1.276 (95% CI 1.142-1.427) and 1.260 (95% CI 1.125-1.411), respectively. CONCLUSIONS: We used propensity score-based analyses to identify that anaemia within the first week was associated with increased one-year mortality in critically ill patients.

Week-One Anaemia was Associated with Increased One-Year Mortality in Critically Ill Surgical Patients.

Background: Anaemia has a deleterious effect on surgical patients, but the long-term impact of anaemia in critically ill surgical patients remains unclear. Methods: We enrolled consecutive patients who were admitted to surgical intensive care units (ICUs) at a tertiary referral centre in central Taiwan between 2015 and 2020. We used both Cox proportional hazards analysis and propensity score-based analyses, including propensity score matching (PSM), inverse probability of treatment weighting (IPTW), and covariate balancing propensity score (CBPS) to determine hazard ratios (HRs) and 95% confidence intervals (CIs) for one-year mortality. Results: A total of 7,623 critically ill surgical patients were enrolled, and 29.9% (2,280/7,623) of them had week-one anaemia (haemoglobin <10 g/dL). We found that anaemia was independently associated with an increased risk of one-year mortality after adjustment for relevant covariates (aHR, 1.170; 95% CI, 1.045-1.310). We further identified a consistent strength of association between anaemia and one-year mortality in propensity score-based analyses, with the adjusted HRs in the PSM, IPTW, and CBPS were 1.164 (95% CI 1.025-1.322), 1.179 (95% CI 1.030-1.348), and 1.181 (1.034-1.349), respectively. Conclusions: We identified the impact on one-year mortality of anaemia in critically ill surgical patients, and more studies are needed to validate our findings.

Explainable machine learning approach to predict extubation in critically ill ventilated patients: a retrospective study in central Taiwan.

BACKGROUND: Weaning from mechanical ventilation (MV) is an essential issue in critically ill patients, and we used an explainable machine learning (ML) approach to establish an extubation prediction model. METHODS: We enrolled patients who were admitted to intensive care units during 2015-2019 at Taichung Veterans General Hospital, a referral hospital in central Taiwan. We used five ML models, including extreme gradient boosting (XGBoost), categorical boosting (CatBoost), light gradient boosting machine (LightGBM), random forest (RF) and logistic regression (LR), to establish the extubation prediction model, and the feature window as well as prediction window was 48 h and 24 h, respectively. We further employed feature importance, Shapley additive explanations (SHAP) plot, partial dependence plot (PDP) and local interpretable model-agnostic explanations (LIME) for interpretation of the model at the domain, feature, and individual levels. RESULTS: We enrolled 5,940 patients and found the accuracy was comparable among XGBoost, LightGBM, CatBoost and RF, with the area under the receiver operating characteristic curve using XGBoost to predict extubation was 0.921. The calibration and decision curve analysis showed well applicability of models. We also used the SHAP summary plot and PDP plot to demonstrate discriminative points of six key features in predicting extubation. Moreover, we employed LIME and SHAP force plots to show predicted probabilities of extubation and the rationale of the prediction at the individual level. CONCLUSIONS: We developed an extubation prediction model with high accuracy and visualised explanations aligned with clinical workflow, and the model may serve as an autonomous screen tool for timely weaning.

Explainable machine learning to predict long-term mortality in critically ill ventilated patients: a retrospective study in central Taiwan.

BACKGROUND: Machine learning (ML) model is increasingly used to predict short-term outcome in critically ill patients, but the study for long-term outcome is sparse. We used explainable ML approach to establish 30-day, 90-day and 1-year mortality prediction model in critically ill ventilated patients. METHODS: We retrospectively included patients who were admitted to intensive care units during 2015-2018 at a tertiary hospital in central Taiwan and linked with the Taiwanese nationwide death registration data. Three ML models, including extreme gradient boosting (XGBoost), random forest (RF) and logistic regression (LR), were used to establish mortality prediction model. Furthermore, we used feature importance, Shapley Additive exPlanations (SHAP) plot, partial dependence plot (PDP), and local interpretable model-agnostic explanations (LIME) to explain the established model. RESULTS: We enrolled 6994 patients and found the accuracy was similar among the three ML models, and the area under the curve value of using XGBoost to predict 30-day, 90-day and 1-year mortality were 0.858, 0.839 and 0.816, respectively. The calibration curve and decision curve analysis further demonstrated accuracy and applicability of models. SHAP summary plot and PDP plot illustrated the discriminative point of APACHE (acute physiology and chronic health exam) II score, haemoglobin and albumin to predict 1-year mortality. The application of LIME and SHAP force plots quantified the probability of 1-year mortality and algorithm of key features at individual patient level. CONCLUSIONS: We used an explainable ML approach, mainly XGBoost, SHAP and LIME plots to establish an explainable 1-year mortality prediction ML model in critically ill ventilated patients.

Acute delirium as an initial manifestation of COVID-19 patients with acute ischemic stroke: Report on two cases.

Psychiatric and neurological complications of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection are common. Psychiatric symptoms are so common that they are easily misinterpreted as an affective disorder induced by SARSCoV-2 infection. However, psychiatric symptoms, such as acute delirium, though rarely seen, can be the initial manifestations of acute ischemic stroke (AIS). These psychiatric symptoms may confuse the diagnosis of acute stroke, which needs correct and timely management. We report two hospitalized cases with SARS-CoV-2 infection and elevated serum D-dimer levels having acute delirium as the initial manifestation of AIS. The diagnostic processes were challenging and time-consuming, so reperfusion therapy could not be given in the therapeutic time window. The diagnoses of AIS were finally made by brain magnetic resonance imaging which showed diffusion restriction at the right middle cerebral artery territory in both cases. Features of psychiatric complications and stroke in coronavirus disease 2019 (COVID-19) patients are reviewed. For the hospitalized COVID-19 patients with elevated levels of serum Ddimer and acute delirium, acute stroke with neuropsychiatric manifestations should beconsidered.

Comparison of prone positioning and extracorporeal membrane oxygenation in acute respiratory distress syndrome: A multicenter cohort study and propensity-matched analysis.

BACKGROUND/PURPOSE: Both prone positioning and extracorporeal membrane oxygenation (ECMO) are used as rescue therapies for severe hypoxemia in patients with acute respiratory distress syndrome (ARDS). This study compared outcomes between patients with severe influenza pneumonia-related ARDS who received prone positioning and those who received ECMO. METHODS: This retrospective cohort study included eight tertiary referral centers in Taiwan. All patients who were diagnosed as having influenza pneumonia-related severe ARDS were enrolled between January and March 2016. We collected their demographic data and prone positioning and ECMO outcomes from medical records. RESULTS: In total, 263 patients diagnosed as having ARDS were included, and 65 and 53 of them received prone positioning and ECMO, respectively. The baseline PaO2/FiO2 ratio, Acute Physiology and Chronic Health Evaluation II score and Sequential Organ Failure Assessment score did not significantly differ between the two groups. The 60-day mortality rate was significantly higher in the ECMO group than in the prone positioning group (60% vs. 28%, p = 0.001). A significantly higher mortality rate was still observed in the ECMO group after propensity score matching (59% vs. 36%, p = 0.033). In the multivariate Cox regression analysis, usage of prone positioning or ECMO was the single independent predictor for 60-day mortality (hazard ratio: 2.177, p = 0.034). CONCLUSION: While the patients receiving prone positioning had better outcome, the causality between prone positioning and the prognosis is unknown. However, the current data suggested that patients with influenza-related ARDS may receive prone positioning before ECMO support.

Culture positivity may correlate with long-term mortality in critically ill patients.

BACKGROUND: The long-term outcome is currently a crucial issue in critical care, and we aim to address the association between culture positivity and long-term mortality in critically ill patients. METHODS: We used the 2015-2019 critical care database at Taichung Veterans General Hospital and Taiwanese nationwide death registration files. Multivariable Cox proportional hazards regression model was conducted to determine hazard ratio (HR) and 95% confidence interval (CI). RESULTS: We enrolled 4488 critically ill patients, and the overall mortality was 55.2%. The follow-up duration among survivors was 2.2 ± 1.3 years. We found that 52.6% (2362/4488) of critically ill patients had at least one positive culture during the admission, and the number of patients with positive culture in the blood, respiratory tract and urinary tract were 593, 1831 and 831, respectively. We identified that a positive culture from blood (aHR 1.233; 95% CI 1.104-1.378), respiratory tract (aHR 1.217; 95% CI 1.109-1.364) and urinary tract (aHR 1.230; 95% CI 1.109-1.364) correlated with an increased risk of long-term mortality after adjusting relevant covariates. CONCLUSIONS: Through linking two databases, we found that positive culture in the blood, respiratory tract and urinary tract during admission correlated with increased long-term overall mortality in critically ill patients.

First tidal volume greater than 8 mL/kg is associated with increased mortality in complicated influenza infection with acute respiratory distress syndrome.

BACKGROUNDS: Severe influenza infection causes substantial morbidity and mortality worldwide and remains an important threat to global health. This study addressed factors related to treatment outcomes in subjects of complicated influenza infection with acute respiratory distress syndrome (ARDS) during the Taiwan epidemic in the Spring of 2016. METHODS: This is a retrospective study conducted by Taiwan Severe Influenza Research Consortium (TSIRC), including eight tertiary referral medical centers. Patients with virology-proven influenza infection admitted to intensive care unit (ICU) between January and March 2016 were included for analysis. RESULTS: We identified 263 patients with complicated influenza infection who fulfilled ARDS criteria; the mean age was 59.8 ± 14.6 (years), and 66.1% (166/263) were male. Type A influenza (77.9%, 205/263) virus was the main pathogen during this epidemic. The 30-day mortality rate was 23.2% (61/263). The mean tidal volume (VT) in the first three days after intubation was greater than 8 mL/kg of predicted body weight (PBW). Patients whose first measured VT was >8 mL/kg PBW had an increased 30-day mortality (p = 0.04, log-rank test). In a multivariate Cox proportional hazard regression model, an increase of 1 mL/kg PBW of first VT was associated with 26.1% increase in 30-day mortality (adjusted hazard ratio 1.261, 95% confidence interval [CI] 1.072-1.484, p < 0.01). CONCLUSION: First tidal volume, shortly after intubation, greater than 8 mL/kg PBW is an independent risk factor for mortality in complicated influenza infection with ARDS. Timely recognition of ARDS with strict adherence to protective ventilation strategy of lowering VT may be important in reducing mortality.

Using genotyping to delineate tuberculosis transmission in long-term care facilities: single facility 4-year experience.

BACKGROUND: Residents in long-term care facilities (LTCFs) are vulnerable to tuberculosis (TB) transmission; however, to delineate possible routes of TB transmission in LTCFs is difficult. This study aimed to address the use of regular genotyping surveillance to delineate TB transmission in LTCFs. METHODS: All of Mycobacterium tuberculosis isolates in the reported 620-bed LTCF between July 2011 and August 2015 were genotyped, and we retrospectively compared epidemiological data and genotyping results. RESULTS: A total of 42 subjects were diagnosed with culture-positive pulmonary TB infection during the 4-year period. Their median age was 76.5 years, and 64.3% (27/42) of them were male. Genotyping identified 5 clustered TB infections involving 76.2% (32/42) of all TB subjects. In a multivariate logistic regression model adjusted for age, sex, chronic obstructive pulmonary disease, and body mass index, subjects with clustered TB infection were less likely to be Activities of Daily Living (ADL)-dependence (adjOR 0.073, 95% CI 0.007-0.758) when compared with subjects having individual TB infections. Prolonged surveillance is essential given that the median interval to diagnose secondary subjects was 673 days. Finally, only 63.0% (17/27) of the 27 secondary TB subjects in this study had contact history with index subject in the same ward. CONCLUSIONS: In conclusion, possible routes of TB transmission in a complex TB outbreak at LTCFs might be delineated by routine genotyping surveillance and regular health check-up.

Underlying influence of perception of management leadership on patient safety climate in healthcare organizations - A mediation analysis approach.

OBJECTIVE: We aim to draw insights on how medical staff's perception of management leadership affects safety climate with key safety related dimensions-teamwork climate, job satisfaction and working conditions. DESIGN/SETTING: A cross-sectional survey using Safety Attitude Questionnaire (SAQ) was performed in a medical center in Taichung City, Taiwan. The relationships among the dimensions in SAQ were then analyzed by structural equation modeling with a mediation analysis. PARTICIPANTS: 2205 physicians and nurses of the medical center participated in the survey. Because not all questions in the survey are suitable for entire hospital staff, only the valid responses (n = 1596, response rate of 72%) were extracted for analysis. MAIN OUTCOME MEASURE(S): Key measures are the direct and indirect effects of teamwork climate, job satisfaction, perception of management leadership, and working conditions on safety climate. RESULTS: Outcomes show that effect of perception of management leadership on safety climate is significant (standardized indirect effect of 0.892 with P-value 0.002) and fully mediated by other dimensions, where 66.9% is mediated through teamwork climate, 24.1% through working conditions and 9.0% through job satisfaction. CONCLUSIONS: Our findings point to the importance of management leadership and the mechanism of its influence on safety climate. To improve safety climate, the implication is that commitment by management on leading safety improvement needs to be demonstrated when it implements daily supportive actions for other safety dimensions. For future improvement, development of a management system that can facilitate two-way trust between management and staff over the long term is recommended.

Mechanisms underlying lung resistance-related protein (LRP)-mediated doxorubicin resistance of non-small cell lung cancer cells.

Lung resistance-related protein (LRP) is a human major vault protein (MVP) implicated in drug resistance of cancer cells in a cell-type dependent manner. The primary goal of the study was to understand the role(s) of LRP in doxorubicin (DOX) resistance of non-small cell lung cancer (NSCLC) cells and the underlying working mechanisms. In the study, the roles of LRP in the regulation of DOX dynamics, nuclear import of minor vault proteins (vault poly (ADP-ribose) polymerase, vPARP and telomerase associated protein-1, TEP-1) and DOX-mediated cytotoxicity were examined in CH27 and H460 cells. Our results were the first to show that the CH27 cells with higher LRP expression levels were more resistant to DOX-induced cytotoxicity as shown in apoptosis experiments. LRP at the nuclear membrane could regulate DOX efflux from the nucleus to the cytosol, and also the reverse vPARP/TEP1 influx from the cytosol, to protect NSCLC cells from DOX-induced apoptosis. Cytosolic LRP could bind to DOX, vPARP and TEP1 to clear DOX away from the nucleus and promote the assembly of vaults for cell protection again. Based on the data obtained, the molecular mechanisms responsible for DOX resistance of NSCLC were delineated to demonstrate that LRP, vPARP and TEP1 were potential targets for NSCLC therapy. Inhibitors of these proteins, including small interfering LRP (siLRP), wheat-germ agglutenin (WGA) (WGA), 3-aminobenzamide (3-AB) and 3,6,9-trisubstituted acridine 9-[4-(N,N-dimethylamino) phenylamino]-3,6-bis(3-pyrrolodinopropionamido) acridine (BRACO-19), break down the DOX resistance of NSCLC cells, particularly in CH27 cells, and may have therapeutic values in the control of NSCLC.

Factors associated with mental illness in patients with rheumatoid arthritis initiating b/ts DMARDs: A population-based study.

AIM: Mental health is an essential issue in patients with rheumatoid arthritis (RA) but remains unclear among those receiving biological and targeted synthetic disease-modifying antirheumatic drugs (b/tsDMARDs). We aim to assess the incidence and factors associated with mental illness among patients with RA who underwent b/tsDMARD therapy. METHOD: We used Taiwan's National Health Insurance Research Database for the period 2001-2020 to identify patients with RA receiving b/tsDMARDs. The primary outcome was newly developed mental illness, including anxiety and mood disorders. We performed a Cox regression analysis to determine factors associated with mental illness and presented as hazard ratios (HR) with 95% confidence interval (CI). RESULTS: We enrolled 10 852 patients, with 7854 patients receiving tumor necrosis factors inhibitors (TNFi), 1693 patients receiving non-TNFi bDMARDs, and 1305 patients treated with tsDMARD. We found that 13.62% of enrolled patients developed mental illness, with an incidence rate of 4054 per 100 000 person-year. Those receiving tocilizumab (aHR 0.64, 95% CI: 0.51-0.82), abatacept (aHR 0.69, 95% CI: 0.55-0.86), or tsDMARDs (aHR 0.58, 95% CI: 0.47-0.73) had a lower risk of mental illness compared with those receiving TNFi. We also found that old age, low income, diabetes mellitus, use of cyclosporine, and use of steroids were associated with incident mental illness. CONCLUSION: This population-based study investigated the incidence and factors associated with mental illness among patients with RA receiving b/tsDMARDs. Our findings highlight the need for vigilance with respect to the possibility of mental illness in patients with RA.

Early absolute lymphocyte count was associated with one-year mortality in critically ill surgical patients: A propensity score-matching and weighting study.

BACKGROUND: Absolute lymphocyte count (ALC) is a crucial indicator of immunity in critical illness, but studies focusing on long-term outcomes in critically ill patients, particularly surgical patients, are still lacking. We sought to explore the association between week-one ALC and long-term mortality in critically ill surgical patients. METHODS: We used the 2015-2020 critical care database of Taichung Veterans General Hospital (TCVGH), a referral hospital in central Taiwan, and the primary outcome was one-year all-cause mortality. We assessed the association between ALC and long-term mortality by measuring hazard ratios (HRs) with 95% confidence intervals (CIs). Furthermore, we used propensity score-matching and -weighting analyses, consisting of propensity score matching (PSM), inverse probability of treatment weighting (IPTW), and covariate balancing propensity score (CBPS), to validate the association. RESULTS: A total of 8052 patients were enrolled, with their one-year mortality being 24.2%. Cox regression showed that low ALC was independently associated with mortality (adjHR 1.140, 95% CI 1.091-1.192). Moreover, this association tended to be stronger among younger patients, patients with fewer comorbidities and lower severity. The association between low ALC and mortality in original, PSM, IPTW, and CBPS populations were 1.497 (95% CI 1.320-1.697), 1.391 (95% CI 1.169-1.654), 1.512 (95% CI 1.310-1.744), and 1.511 (95% CI 1.310-1.744), respectively. Additionally, the association appears to be consistent, using distinct cutoff levels to define the low ALC. CONCLUSIONS: We identified that early low ALC was associated with increased one-year mortality in critically ill surgical patients, and prospective studies are warranted to confirm the finding.

Predictive approach for liberation from acute dialysis in ICU patients using interpretable machine learning.

Renal recovery following dialysis-requiring acute kidney injury (AKI-D) is a vital clinical outcome in critical care, yet it remains an understudied area. This retrospective cohort study, conducted in a medical center in Taiwan from 2015 to 2020, enrolled patients with AKI-D during intensive care unit stays. We aimed to develop and temporally test models for predicting dialysis liberation before hospital discharge using machine learning algorithms and explore early predictors. The dataset comprised 90 routinely collected variables within the first three days of dialysis initiation. Out of 1,381 patients who received acute dialysis, 27.3% experienced renal recovery. The cohort was divided into the training group (N = 1135) and temporal testing group (N = 251). The models demonstrated good performance, with an area under the receiver operating characteristic curve of 0.85 (95% CI, 0.81-0.88) and an area under the precision-recall curve of 0.69 (95% CI, 0.62-0.76) for the XGBoost model. Key predictors included urine volume, Charlson comorbidity index, vital sign derivatives (trend of respiratory rate and SpO2), and lactate levels. We successfully developed early prediction models for renal recovery by integrating early changes in vital signs and inputs/outputs, which have the potential to aid clinical decision-making in the ICU.

Lower body mass index is an independent predictor of mortality in older patients with acute respiratory distress syndrome.

Background: Acute respiratory distress syndrome (ARDS) is associated with high mortality. The impacts of body mass index (BMI) on the morality of older patients with ARDS remain unclear. Methods: This is a single-center cohort study which was conducted at Taichung Veterans General Hospital, Taiwan. Adult patients admitted to the ICU needing mechanical ventilation with ARDS were included for analysis. We compared the data of older patients (age ≥65 years) with those of younger patients (Age <65 years). The factors associated with in-hospital mortality of older patients were investigated. Results: This study included a total of 728 (mean age: 66 years; men: 63%) patients, and 425 (58.4%) of them aged ≥65 years. Older patients exhibited lower body mass index (BMI) (23.8 vs 25.2), higher Acute Physiology and Chronic Health Evaluation (APACHE) II scores (28.9 vs 26.3), higher Charlson Comorbidity Index (CCI) (4.0 vs 3.4), and lower Sequential Organ Failure Assessment (SOFA) scores (10.0 vs 11.1) than younger patients. Furthermore, older patients had mortality rates similar to younger patients (40.5% vs 42.9%, P = 0.542), but had longer length of stay in the ICU (17.6 vs 15.6 days, P = 0.047). For older patients, BMI <18.5 (odds ratio [OR], 2.78; 95% confidence interval [CI], 1.45-5.34), high SOFA score (OR, 1.20; 95% CI, 1.12-1.28), and moderate (OR, 1.95; 95% CI 1.20-3.14) or severe ARDS (OR, 2.30; 95% CI 1.26-4.22) were independent risk factors for mortality. Conclusions: In this cohort, critical ill older patients with ARDS had lower BMI, more comorbidities, and higher APACHE II scores than younger patients. Mortality rate was similar between older and younger patients. Low BMI, high SOFA score, and moderate or severe ARDS were independently associated with mortality in older patients with ARDS.

Deep-Learning-Based Automated Anomaly Detection of EEGs in Intensive Care Units.

An intensive care unit (ICU) is a special ward in the hospital for patients who require intensive care. It is equipped with many instruments monitoring patients' vital signs and supported by the medical staff. However, continuous monitoring demands a massive workload of medical care. To ease the burden, we aim to develop an automatic detection model to monitor when brain anomalies occur. In this study, we focus on electroencephalography (EEG), which monitors the brain electroactivity of patients continuously. It is mainly for the diagnosis of brain malfunction. We propose the gated-recurrent-unit-based (GRU-based) model for detecting brain anomalies; it predicts whether the spike or sharp wave happens within a short time window. Based on the banana montage setting, the proposed model exploits characteristics of multiple channels simultaneously to detect anomalies. It is trained, validated, and tested on separated EEG data and achieves more than 90% testing performance on sensitivity, specificity, and balanced accuracy. The proposed anomaly detection model detects the existence of a spike or sharp wave precisely; it will notify the ICU medical staff, who can provide immediate follow-up treatment. Consequently, it can reduce the medical workload in the ICU significantly.

Antimicrobial drug-resistant microbes associated with hospitalized community-acquired and healthcare-associated pneumonia: a multi-center study in Taiwan.

BACKGROUND/PURPOSE: Community-acquired pneumonia (CAP) and healthcare-associated pneumonia (HCAP) may be caused by potential antimicrobial drug-resistant (PADR) microbes. The aims of this study were to evaluate the incidences and risk factors associated with PADR microbes observed in patients with pneumonia occurring outside the hospital setting in Taiwan. METHODS: We conducted a retrospective study of patients with CAP or HCAP admitted to six medical centers in the northern, central, and southern regions of Taiwan in 2007. The pathogens were evaluated by microbiological specimens within 72 hours after admission. The patients' comorbidities, pathogens, and outcomes were evaluated. The risk factors of PADR microbes were identified by logistic regression analysis. RESULTS: The enrolled patients exhibited HCAP (n=713) and CAP (n=933). The pathogens associated with HCAP (n=383) and CAP (n=441) included Pseudomonas spp. (29%vs. 10%, p<0.001), Klebsiella spp. (24% vs. 25%, p=0.250), Escherichia coli (6% vs. 8%, p=0.369), Haemophilus influnezae (3% vs. 7%, p=0.041), Streptococcus pneumoniae (2% vs. 6%, p=0.003) and methicillin-resistant Staphylococcus aureus (MRSA) (8% vs. 4%, p=0.008). The core pathogens of CAP and HCAP differed among the three regions of Taiwan. PADR microbes, including Pseudomonas spp. (n=191), Acinetobacter spp. (n=41), MRSA (n=49) and cefotaxime- or ceftazidime-resistant Enterbacteriaceae (n=25), were isolated from 13% of patients with CAP and 23% of patients with HCAP. Previous hospitalization, and neoplastic and neurological diseases were significant risk factors for acquiring PADR microbes. CONCLUSION: PADR microbes were common in patients with HCAP and CAP in Taiwan. Broad-spectrum antibiotics targeting PADR microbes should be administered to patients who have undergone previous hospitalization and who exhibit neurological disorders and/or malignancies.