Association between red blood cell distribution width and 30-day mortality in critically ill septic patients: a propensity score-matched study.

BACKGROUND: Sepsis is the leading cause of death worldwide, and a number of biomarkers have been developed for early mortality risk stratification. Red blood cell distribution width (RDW) is a routinely available hematological data and has been found to be associated with mortality in a number of diseases; therefore, we aim to address the association between RDW and mortality in critically ill patients with sepsis. METHODS: We analyzed data of critically ill adult patients with sepsis on the TriNetX platform, excluding those with hematologic malignancies, thalassemia, and iron deficiency anemia. Propensity score-matching (PSM) (1:1) was used to mitigate confounding effects, and hazard ratio (HR) with 95% confidence (CI) was calculated to determine the association between RDW and 30-day mortality. We further conducted sensitivity analyses through using distinct cut-points of RDW and severities of sepsis. RESULTS: A total of 256,387 critically ill septic patients were included in the analysis, and 40.0% of them had RDW equal to or higher than 16%. After PSM, we found that high RDW was associated with an increased 30-day mortality rate (HR: 1.887, 95% CI 1.847-1.928). The associations were consistent using distinct cut-points of RDW, with the strength of association using cut-points of 12%, 14%, 16%, 18% and 20% were 2.098, 2.204, 1.887, 1.809 and 1.932, respectively. Furthermore, we found consistent associations among critically ill septic patients with distinct severities, with the association among those with shock, receiving mechanical ventilation, bacteremia and requirement of hemodialysis being 1.731, 1.735, 2.380 and 1.979, respectively. CONCLUSION: We found that RDW was associated with 30-day mortality in critically ill septic patients, underscoring the potential as a prognostic marker in sepsis. More studies are needed to explore the underlying mechanisms.

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.

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.

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.

Incidence and Risk Factors of Mental Illnesses Among Patients with Systemic Autoimmune Rheumatic Diseases: An 18-year population-based study.

OBJECTIVE: This study aimed to assess the incidence and risk factors surrounding mental illnesses in patients diagnosed with systemic autoimmune rheumatic diseases (SARDs). METHODS: This retrospective cohort study used nationwide, population-based claim data taken from Taiwan's National Health Insurance Research Database (NHIRD) to identify patients certified as having a catastrophic illness for Systemic lupus erythematosus (SLE), Rheumatoid arthritis (RA), Systemic sclerosis (SSc), Dermatomyositis (DM), Polymyositis (PM) or Sjogren's syndrome (SS) from the years 2002-2020. We furthermore calculated the incidence of mental illness in patients diagnosed with SARDs while exploring factors associated with the development of mental illness using multivariable Cox regression analysis shown as adjusted hazard ratios (HRs) with 95% confidence intervals (CIs). RESULTS: Among the 28 588 participants, the average age was 47.4 (SD 14.9) years, with most participants being female (76.4%). When compared with patients with rheumatoid arthritis, patients with SLE (HR: 1.20, 95% CI: 1.10-1.32), SS (HR: 1.29, 95% CI: 1.19-1.39), and DM (HR: 1.28, 95% CI: 1.04-1.32) showed a significantly increased risk of developing mental illness. Additionally, when compared with patients with rheumatoid arthritis, patients with SLE (HR: 1.32, 95% CI: 1.21-1.44), SSc (HR: 1.20, 95% CI: 1.02-1.41), SS (HR: 1.17, 95% CI: 1.08-1.26), DM (HR: 1.73, 95% CI: 1.44-2.07), and PM (HR: 1.64, 95% CI: 1.32-2.03) showed a significantly increased risk of antidepressant use. CONCLUSIONS: This population-based cohort study revealed that patients diagnosed with SLE, SS and DM had significantly higher risks of developing mental illness when compared with patients with RA.

Ultrasensitive and Rapid Detection of Procalcitonin via Waveguide-Enhanced Nanogold-Linked Immunosorbent Assay for Early Sepsis Diagnosis.

Sepsis, a life-threatening inflammatory response, demands economical, accurate, and rapid detection of biomarkers during the critical "golden hour" to reduce the patient mortality rate. Here, we demonstrate a cost-effective waveguide-enhanced nanogold-linked immunosorbent assay (WENLISA) based on nanoplasmonic waveguide biosensors for the rapid and sensitive detection of procalcitonin (PCT), a sepsis-related inflammatory biomarker. To enhance the limit of detection (LOD), we employed sandwich assays using immobilized capture antibodies and detection antibodies conjugated to gold nanoparticles to bind the target analyte, leading to a significant evanescent wave redistribution and strong nanoplasmonic absorption near the waveguide surface. Experimentally, we detected PCT for a wide linear response range of 0.1 pg/mL to 1 ng/mL with a record-low LOD of 48.7 fg/mL (3.74 fM) in 8 min. Furthermore, WENLISA has successfully identified PCT levels in the blood plasma of patients with sepsis and healthy individuals, offering a promising technology for early sepsis diagnosis.

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.

Prolonged use of neuromuscular blocking agents is associated with increased long-term mortality in mechanically ventilated medical ICU patients: a retrospective cohort study.

BACKGROUND: Neuromuscular blockade agents (NMBAs) can be used to facilitate mechanical ventilation in critically ill patients. Accumulating evidence has shown that NMBAs may be associated with intensive care unit (ICU)-acquired weakness and poor outcomes. However, the long-term impact of NMBAs on mortality is still unclear. METHODS: We conducted a retrospective analysis using the 2015-2019 critical care databases at Taichung Veterans General Hospital, a referral center in central Taiwan, as well as the Taiwan nationwide death registry profile. RESULTS: A total of 5709 ventilated patients were eligible for further analysis, with 63.8% of them were male. The mean age of enrolled subjects was 67.8 ± 15.8 years, and the one-year mortality was 48.3% (2755/5709). Compared with the survivors, the non-survivors had a higher age (70.4 ± 14.9 vs 65.4 ± 16.3, p < 0.001), Acute Physiology and Chronic Health Evaluation II score (28.0 ± 6.2 vs 24.7 ± 6.5, p < 0.001), a longer duration of ventilator use (12.6 ± 10.6 days vs 7.8 ± 8.5 days, p < 0.001), and were more likely to receive NMBAs for longer than 48 h (11.1% vs 7.8%, p < 0.001). After adjusting for age, sex, and relevant covariates, the use of NMBAs for longer than 48 h was found to be independently associated with an increased risk of mortality (adjusted HR: 1.261; 95% CI: 1.07-1.486). The analysis of effect modification revealed that this association was tended to be strong in patients with a Charlson Comorbidity Index of 3 or higher. CONCLUSIONS: Our study demonstrated that prolonged use of NMBAs was associated with an increased risk of long-term mortality in critically ill patients requiring mechanical ventilation. Further studies are needed to validate our findings.

The Association Between Absolute Lymphocyte Count and Long-Term Mortality in Critically Ill Medical Patients: Propensity Score-Based Analyses.

Objective: Absolute lymphocyte count (ALC) has been implicated with short-term outcomes in a number of diseases, and we aimed to investigate the association between week-one ALC and long-term mortality in patients who were admitted to the medical intensive care units (ICUs). Methods: We enrolled patients who were admitted to the medical ICUs at the Taichung Veterans General Hospital, a referral centre located in central Taiwan, between 2015 and 2020 to conduct this retrospective cohort study. The outcome of interest was long-term all-cause mortality, and hazard ratios (HRs) with 95% confidence intervals (CIs) were calculated to determine the association. Furthermore, we employed propensity score-matching (PSM) and weighting techniques, consisting of inverse probability of treatment weighting (IPTW) and covariate balancing propensity score (CBPS), to confirm the association between ALC and mortality. Results: A total of 5722 critically ill patients were enrolled, and the one-year mortality was 44.8%. The non-survivor group had a lower ALC (1549, 1027-2388 vs 1948, 1373-2743 counts/µL, p<0.01) compared with those in the survivor group. Cox regression showed that low ALC was independently associated with mortality (adjHR 1.091, 95% CI 1.050-1.134). Propensity score-based analyses demonstrated the robust association, with adjHRs in the original, PSM, IPTW, and CBPS populations of 1.327 (95% CI 1.224-1.438), 1.301 (95% CI 1.188-1.424), 1.292 (95% CI 1.186-1.407), and 1.297 (95% CI 1.191-1.412), respectively. Sensitivity analyses further showed that the association between low ALC and mortality existed in a dose-response manner. Conclusion: We found that low ALC was associated with long-term mortality in critically ill patients; further studies are warranted to validate and translate these findings into clinical utility.

Association between early blood urea nitrogen-to-albumin ratio and one-year post-hospital mortality in critically ill surgical patients: a propensity score-matched study.

BACKGROUND: Blood urea nitrogen to albumin ratio (BAR) is increasingly recognized as an early predictor for short-term outcomes in critically ill patients, but the association of BAR with long-term outcomes in critically ill surgical patients remains underexplored. METHODS: We enrolled consecutive patients who were admitted to surgical intensive care units (ICUs) at Taichung Veterans General Hospital between 2015 and 2020, and the dates of death were retrieved from Taiwan's National Health Insurance Research Database. In addition to Cox regression, we also used propensity score matching to determine the hazard ratios (HRs) and 95% confidence intervals (CIs) for one-year post-hospital mortality of the variables. RESULTS: A total of 8,073 eligible subjects were included for analyses. We found that age, male gender, high Charlson Comorbidity Index, high Acute Physiology and Chronic Health Evaluation II score, positive microbial culture, and leukocytosis were predictors for mortality, whereas high body mass index, scheduled surgery, and high platelet counts were protective factors against long-term mortality. The high BAR was independently associated with increased post-hospital mortality after adjustment for the aforementioned covariates (adjHR 1.258, 95% CI, 1.127-1.405). Notably, the association tended to be stronger in females and patients with fewer comorbidities and lower disease severity of critical illness. The propensity score matching, dividing subjects by BAR higher or lower than 6, showed a consistent association between week-one BAR and post-hospital mortality (adjHR 1.503, 95% CI 1.247-1.811). CONCLUSIONS: BAR is a newly identified predictor of short-term outcome, and we identified long-term outcome-relevant factors, including BAR, and the identified factors may be useful for risk stratification of long-term outcomes in patients discharged from surgical ICUs.

Different epidemiological characteristics between patients with non-hospital-onset and hospital-onset candidemia: a retrospective cohort study.

Candidemia is a life-threatening infectious disease that has varying incidences. Previous studies revealed the differences in clinical characteristics and outcomes between non-hospital-onset (NHO) and hospital-onset (HO) candidemia. This 4-year retrospective research included adult patients with candidemia in a tertiary medical centre in Taiwan, and cases were categorised as NHO and HO candidemia. Survival analysis and risk factors associated with in-hospital mortality were performed using the Kaplan-Meier method and multivariate Cox proportional-hazards models. The analysis included 339 patients, and the overall incidence was 1.50 per 1,000 admission person-year. Of the cases, 82 (24.18%) were NHO candidemia, and 57.52% (195/339) of patients were diagnosed with at least one malignancy. C. albicans was the most commonly isolated species, accounting for 52.21%. Patients with NHO candidemia had a higher proportion of C. glabrata but a lower ratio of C. tropicalis in comparison to the HO group. The all-cause in-hospital mortality rate was 55.75%. Multivariate Cox proportional-hazards models showed that NHO candidemia was a better outcome predictor (adjusted hazard ratio, 0.44). The administration of antifungal therapy within 2 days was a protective factor. In conclusion, NHO candidemia showed distinct microbiological characteristics and a better outcome than HO candidemia.

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.

Explainable Machine Learning to Predict Successful Weaning of Mechanical Ventilation in Critically Ill Patients Requiring Hemodialysis.

Lungs and kidneys are two vital and frequently injured organs among critically ill patients. In this study, we attempt to develop a weaning prediction model for patients with both respiratory and renal failure using an explainable machine learning (XML) approach. We used the eICU collaborative research database, which contained data from 335 ICUs across the United States. Four ML models, including XGBoost, GBM, AdaBoost, and RF, were used, with weaning prediction and feature windows, both at 48 h. The model's explanations were presented at the domain, feature, and individual levels by leveraging various techniques, including cumulative feature importance, the partial dependence plot (PDP), the Shapley additive explanations (SHAP) plot, and local explanation with the local interpretable model-agnostic explanations (LIME). We enrolled 1789 critically ill ventilated patients requiring hemodialysis, and 42.8% (765/1789) of them were weaned successfully from mechanical ventilation. The accuracies in XGBoost and GBM were better than those in the other models. The discriminative characteristics of six key features used to predict weaning were demonstrated through the application of the SHAP and PDP plots. By utilizing LIME, we were able to provide an explanation of the predicted probabilities and the associated reasoning for successful weaning on an individual level. In conclusion, we used an XML approach to establish a weaning prediction model in critically ill ventilated patients requiring hemodialysis.

Whole transcriptome analysis to explore the impaired immunological features in critically ill elderly patients with sepsis.

BACKGROUND: Sepsis is a frequent complication in critically ill patients, is highly heterogeneous and is associated with high morbidity and mortality rates, especially in the elderly population. Utilizing RNA sequencing (RNA-Seq) to analyze biological pathways is widely used in clinical and molecular genetic studies, but studies in elderly patients with sepsis are still lacking. Hence, we investigated the mortality-relevant biological features and transcriptomic features in elderly patients who were admitted to the intensive care unit (ICU) for sepsis. METHODS: We enrolled 37 elderly patients with sepsis from the ICU at Taichung Veterans General Hospital. On day-1 and day-8, clinical and laboratory data, as well as blood samples, were collected for RNA-Seq analysis. We identified the dynamic transcriptome and enriched pathways of differentially expressed genes between day-8 and day-1 through DVID enrichment analysis and Gene Set Enrichment Analysis. Then, the diversity of the T cell repertoire was analyzed with MiXCR. RESULTS: Overall, 37 patients had sepsis, and responders and non-responders were grouped through principal component analysis. Significantly higher SOFA scores at day-7, longer ventilator days, ICU lengths of stay and hospital mortality were found in the non-responder group, than in the responder group. On day-8 in elderly ICU patients with sepsis, genes related to innate immunity and inflammation, such as ZDHCC19, ALOX15, FCER1A, HDC, PRSS33, and PCSK9, were upregulated. The differentially expressed genes (DEGs) were enriched in the regulation of transcription, adaptive immune response, immunoglobulin production, negative regulation of transcription, and immune response. Moreover, there was a higher diversity of T-cell receptors on day-8 in the responder group, than on day-1, indicating that they had better regulated recovery from sepsis compared with the non-response patients. CONCLUSION: Sepsis mortality and incidence were both high in elderly individuals. We identified mortality-relevant biological features and transcriptomic features with functional pathway and MiXCR analyses based on RNA-Seq data; and found that the responder group had upregulated innate immunity and increased T cell diversity; compared with the non-responder group. RNA-Seq may be able to offer additional complementary information for the accurate and early prediction of treatment outcome.

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.

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.

Analysis of risk factors of mortality in rheumatoid arthritis patients with interstitial lung disease: a nationwide, population-based cohort study in Taiwan.

OBJECTIVE: To examine the risk and risk factors of mortality in patients with rheumatoid arthritis (RA) with interstitial lung disease (ILD). METHODS: Using the 1997-2013 Taiwanese National Health Insurance Research Database, we identified 32 289 incident patients with RA by using International Classification of Diseases, Ninth Revision codes from 2001 to 2013, and 214 patients developed ILD subsequently. We matched (1:10) RA-ILD with controls for sex, age, time of ILD diagnosis and disease duration. In addition, we conducted propensity score matching (PSM) (1:1) for selected comorbidities to choose RA-ILD patients and controls. Using the Cox proportional hazard model, we estimated the association of mortality with ILD for the two matched populations and assessed factors associated with mortality among 214 RA-ILD patients, shown as adjusted HRs (aHRs) with 95% CIs. RESULTS: In the populations selected before and after PSM, we included 164 and 155 patients with RA-ILD and 1640 and 155 controls, respectively. ILD was associated with mortality in the population before PSM (aHR, 1.73; 95% CI 1.19 to 2.52) and in the PSM population (HR 4.38; 95% CI 2.03 to 9.43). Among 214 patients with RA-ILD, age (aHR 1.04; 95% CI 1.03 to 1.08), chronic obstructive pulmonary disease (COPD) (aHR 2.12; 95% CI 1.25 to 3.58), diabetes mellitus (DM) with end-organ damage and corticosteroid dose (prednisolone equivalent, mg/day) (aHR 1.09; 95% CI 1.07 to 1.11) were associated with mortality in RA-ILD. CONCLUSION: This population-based cohort study showed that ILD was associated with risk of mortality in patients with RA, and risk factors associated with mortality in patients with RA-ILD included age, COPD, DM with end-organ damage and average daily prednisolone dose.

Artificial intelligence-aided diagnosis model for acute respiratory distress syndrome combining clinical data and chest radiographs.

Objective: The aim of this study was to develop an artificial intelligence-based model to detect the presence of acute respiratory distress syndrome (ARDS) using clinical data and chest X-ray (CXR) data. Method: The transfer learning method was used to train a convolutional neural network (CNN) model with an external image dataset to extract the image features. Then, the last layer of the model was fine-tuned to determine the probability of ARDS. The clinical data were trained using three machine learning algorithms-eXtreme Gradient Boosting (XGB), random forest (RF), and logistic regression (LR)-to estimate the probability of ARDS. Finally, ensemble-weighted methods were proposed that combined the image model and the clinical data model to estimate the probability of ARDS. An analysis of the importance of clinical features was performed to explore the most important features in detecting ARDS. A gradient-weighted class activation mapping (Grad-CAM) model was used to explain what our CNN sees and understands when making a decision. Results: The proposed ensemble-weighted methods improved the performances of the ARDS classifiers (XGB + CNN, area under the curve [AUC] = 0.916; RF + CNN, AUC = 0.920; LR + CNN, AUC = 0.920; XGB + RF + LR + CNN, AUC = 0.925). In addition, the ML model using clinical data to present the top 15 important features to identify the risk factors of ARDS. Conclusion: This study developed combined machine learning models with clinical data and CXR images to detect ARDS. According to the results of the Shapley Additive exPlanations values and the Grad-CAM techniques, an explicable ARDS diagnosis model is suitable for a real-life scenario.