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.

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.

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.

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.

Mortality association of nontuberculous mycobacterial infection requiring treatment in Taiwan: a population-based study.

BACKGROUND: Infection due to nontuberculous mycobacteria (NTM) is an emerging issue worldwide, and we aimed to address the epidemiology and mortality association of NTM infection requiring treatment in Taiwan. METHODS: We used the 2003-2018 data of 2 million representative individuals in Taiwan's National Health Insurance Research Database. We identified patients with newly diagnosed NTM infection and received treatment as NTM cases. Age- and sex-matched (1:40) as well as propensity score-matched (PSM) (1:2) non-NTM individuals were selected as non-NTM controls. We used a Cox proportional hazard model to determine hazard ratios (HRs) with 95% confidence intervals (CIs). RESULTS: We identified 558 patients with NTM infection requiring treatment. The mean age was 62.5 ± 15.4 years, and 57.5% of them were male. The incidence increased from 0.54 per 100,000 person-year in 2003 to 3.35 per 100,000 person-year in 2018. The overall mortality was 35.2%, with a mean follow-up duration of 4.1 ± 3.6 years. We found that NTM infection was independently associated with a greater risk of mortality (HR: 1.71; 95% CI: 1.47-1.98) compared with age- and sex-matched controls, and the association remained consistent (HR: 1.44; 95% CI: 1.19-1.75) compared with propensity-matched controls. We also found that old age, male, high Charlson comorbidity index, and the use of steroids or anti-neoplastic agents/immunosuppressants were associated with mortality risk. CONCLUSION: In conclusion, we found a steady increase in patients with NTM infection requiring treatment in Taiwan and further demonstrated that NTM infection was associated with greater risk of mortality using two comparable non-NTM control subjects.

Single-cell profiling reveals novel cellular heterogeneity of monocytes during Hymenoptera venom allergy.

Background: Hymenoptera stings can induce dysregulated inflammation and immediate hypersensitivity reactions including anaphylaxis. However, the molecular mechanisms underlying peripheral immune responses during Hymenoptera venom allergy (HVA) remain elusive. Methods: Here we determined the single-cell transcriptomic profiling from highly heterogeneous peripheral blood cells in patients with HVA through unbiased single-cell RNA sequencing and multiple models of computational analyses. Results: Through clustering analysis by uniform manifold approximation and projection, we revealed an increased number of monocytes in the acute phase and identified innate immune responses, leukocyte activation, and cellular detoxification as the main involved biological processes. We used filter analysis to identify that CLU that encodes clusterin was highly expressed in monocytes, and the co-expressed genes of CLU further supported the key role of monocyte. We further used pseudo-temporal ordering of cells and scRNA velocity analysis to delineate disease-associated monocyte lineages and states in patients with HVA. Conclusions: Our comprehensive molecular profiling of blood samples from patients with HVA revealed previously unknown molecular changes, providing important insights into the mechanism of venom allergy and potential therapeutic targets.

Deep Learning-Based Pain Classifier Based on the Facial Expression in Critically Ill Patients.

Objective: Pain assessment based on facial expressions is an essential issue in critically ill patients, but an automated assessment tool is still lacking. We conducted this prospective study to establish the deep learning-based pain classifier based on facial expressions. Methods: We enrolled critically ill patients during 2020-2021 at a tertiary hospital in central Taiwan and recorded video clips with labeled pain scores based on facial expressions, such as relaxed (0), tense (1), and grimacing (2). We established both image- and video-based pain classifiers through using convolutional neural network (CNN) models, such as Resnet34, VGG16, and InceptionV1 and bidirectional long short-term memory networks (BiLSTM). The performance of classifiers in the test dataset was determined by accuracy, sensitivity, and F1-score. Results: A total of 63 participants with 746 video clips were eligible for analysis. The accuracy of using Resnet34 in the polychromous image-based classifier for pain scores 0, 1, 2 was merely 0.5589, and the accuracy of dichotomous pain classifiers between 0 vs. 1/2 and 0 vs. 2 were 0.7668 and 0.8593, respectively. Similar accuracy of image-based pain classifier was found using VGG16 and InceptionV1. The accuracy of the video-based pain classifier to classify 0 vs. 1/2 and 0 vs. 2 was approximately 0.81 and 0.88, respectively. We further tested the performance of established classifiers without reference, mimicking clinical scenarios with a new patient, and found the performance remained high. Conclusions: The present study demonstrates the practical application of deep learning-based automated pain assessment in critically ill patients, and more studies are warranted to validate our findings.

A Positive Fluid Balance in the First Week Was Associated With Increased Long-Term Mortality in Critically Ill Patients: A Retrospective Cohort Study.

Introduction: Early fluid balance has been found to affect short-term mortality in critically ill patients; however, there is little knowledge regarding the association between early cumulative fluid balance (CFB) and long-term mortality. This study aims to determine the distinct association between CFB day 1-3 (CFB 1-3) and day 4-7 (CFB 4-7) and long-term mortality in critically ill patients. Patients and Methods: This study was conducted at Taichung Veterans General Hospital, a tertiary care referral center in central Taiwan, by linking the hospital critical care data warehouse 2015-2019 and death registry data of the Taiwanese National Health Research Database. The patients followed up until deceased or the end of the study on 31 December 2019. We use the log-rank test to examine the association between CFB 1-3 and CFB 4-7 with long-term mortality and multivariable Cox regression to identify independent predictors during index admission for long-term mortality in critically ill patients. Results: A total of 4,610 patients were evaluated. The mean age was 66.4 ± 16.4 years, where 63.8% were men. In patients without shock, a positive CFB 4-7, but not CFB 1-3, was associated with 1-year mortality, while a positive CFB 1-3 and CFB 4-7 had a consistent and excess hazard of 1-year mortality among critically ill patients with shock. The multivariate Cox proportional hazard regression model identified that CFB 1-3 and CFB 4-7 (with per 1-liter increment, HR: 1.047 and 1.094; 95% CI 1.037-1.058 and 1.080-1.108, respectively) were independently associated with high long-term mortality in critically ill patients after adjustment of relevant covariates, including disease severity and the presence of shock. Conclusions: We found that the fluid balance in the first week, especially on days 4-7, appears to be an early predictor for long-term mortality in critically ill patients. More studies are needed to validate our findings and elucidate underlying mechanisms.

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.