Information Mart For Intensive Care Research Articles

Association between the triglyceride glucose index and length of hospital stay in patients with heart failure and type 2 diabetes in the intensive care unit: a retrospective cohort study

BackgroundThe coexistence of heart failure and diabetes is prevalent, particularly in Intensive Care Units (ICU). However, the relationship between the triglyceride-glucose (TyG) index, heart failure, diabetes, and the length of hospital stay (LHS) in patients with cerebrovascular disease in the ICU remains uncertain. This study aims to investigate the association between the TyG index and LHS in patients with heart failure and diabetes.MethodsThis retrospective study utilized the Medical Information Mart for Intensive Care (MIMIC)-IV database to analyze patients with diabetes and heart failure. Participants were categorized into quartiles based on the TyG index, and the primary outcome was LHS. The association between the TyG index at ICU admission and LHS was examined through multivariable logistic regression models, restricted cubic spline regression, and subgroup analysis.ResultsThe study included 635 patients with concurrent diabetes and heart failure. The fully adjusted model demonstrated a positive association between the TyG index and LHS. As a tertile variable (Q2 and Q3 vs Q1), the beta (β) values were 0.88 and 2.04, with a 95% confidence interval (95%CI) of -0.68 to 2.44 and 0.33 to 3.74, respectively. As a continuous variable, per 1 unit increment, the β (95% CI) was 1.13 (0.18 to 2.08). The TyG index’s relationship with LHS showed linearity (non-linear p = 0.751). Stratified analyses further confirmed the robustness of this correlation.ConclusionThe TyG index exhibited a linearly positive association with the LHS in patients with both heart failure and diabetes. Nevertheless, prospective, randomized, controlled studies are imperative to substantiate and validate the findings presented in this investigation.

Geriatric nutritional risk index is associated with the occurrence of acute kidney injury in critically ill patients with acute heart failure

Background: During the acute heart failure (AHF), acute kidney injury (AKI) is highly prevalent in critically ill patients. The occurrence of the latter condition increases the risk of mortality in patients with acute heart failure. The current research on the relationship between nutritional risk and the occurrence of acute kidney injury in patients with acute heart failure is very limited. Methods: This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care IV (MIMIC-IV, version 2.1) database. We included adult patients with AHF who were admitted to the intensive care unit in the study. Results: A total of 1310 critically ill patients with acute heart failure were included. The AUC of geriatric nutritional risk index (GNRI) (0.694) is slightly superior to that of controlling nutritional status (CONUT) (0.656) and prognostic nutritional index (PNI) (0.669). The Log-rank test revealed a higher risk of acute kidney injury in patients with high nutritional risk (p < 0.001). Multivariate COX regression analysis indicated that a high GNRI (adjusted HR 0.62, p < 0.001) was associated with a reduced risk of AKI during hospitalization in AHF patients. The final subgroup analysis demonstrated no significant interaction of GNRI in all subgroups except for diabetes subgroup and ventilation subgroup (P for interaction: 0.057-0.785). Conclusion: Our study findings suggest a correlation between GNRI and the occurrence of acute kidney injury in patients hospitalized with acute heart failure.

A Comparative Analysis of Machine Learning Models for the Classification of Heart Failure Patients in the Intensive Care Unit

Background: Heart failure is the leading cause of death globally over the last several decades. This raises the necessity of timely, accurate, and prudent methods for establishing an early diagnosis and implementing timely illness care. Objective: This study aims to develop and validate a classification model for the patients admitted to the Intensive Care Unit (ICU) with heart failure, using various machine learning models applied to the MIMIC (Medical Information Mart for Intensive Care)-III database. Method: A retrospective cohort study was conducted using data extracted from the MIMIC-III database. Machine learning models: Logistic Regression, K-Nearest Neighbor (KNN), Random Forest, Decision Tree, Naïve Bayes, AdaBoost, and XGBoost were utilized to construct the predictive model. The dataset has been preprocessed in two different manners. The study included 1,177 patients with heart failure, selected according to specific inclusion/exclusion criteria and admitted to the ICU. Result: At the end of the study, the most effective model for predicting patients who survived was Logistic Regression, with an accuracy of 0.9025, sensitivity of 0.9763, precision of 0.9196, and F1-score of 0.9471. Conclusion: Classification of the patients into those who survived or could not survive due to heart failure was the primary measure, with various clinical and demographic variables used as predictors.

Bidirectional association between pneumonia and intestinal infection: an analysis of the MIMIC-IV database.

The purpose is to analyze the prevalence of intestinal infection in patients with pneumonia in intensive care units (ICU) and the impact of intestinal infection on the prognosis of patients with pneumonia, so as to explore the bidirectional association between pneumonia and intestinal infection. The study aims to investigate the correlation between the occurrence of pneumonia and intestinal infection among patients in the ICU, utilizing the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, as well as the impact of intestinal infection on the prognosis of pneumonia patients. The enrolled patients were first divided into pneumonia group and non-pneumonia group, and the primary outcome was that patients developed intestinal infection. Multivariate logistic regression was used to elucidate the association between pneumonia and the prevalence of intestinal infection, and propensity score matching (PSM) and inverse probability of treatment weighing (IPTW) were used to validate our findings. We then divided patients with pneumonia into two groups according to whether they were complicated by intestinal infection, and analyzed the effect of intestinal infection on 28-day mortality, length of ICU stay, and length of hospital stay in patients with pneumonia. This study included 50,920 patients, of which 7493 were diagnosed with pneumonia. Compared with non-pneumonia patients, the incidence of intestinal infection in pneumonia patients was significantly increased [OR 1.58 (95% CI 1.34-1.85; P < 0.001)]. Cox proportional hazards regression model showed no significant effect of co-infection on 28-day mortality in patients with pneumonia (P = 0.223). Patients in the intestinal infection group exhibited a longer length stay in ICU and hospital than those without intestinal infection (P < 0.001). In the ICU, patients with pneumonia were more likely linked to intestinal infection. In addition, the presence of concurrent intestinal infections can prolong both ICU and hospital stays for pneumonia patients.

Association between serum sodium trajectory and mortality in patients with acute kidney injury: a retrospective cohort study

IntroductionDysnatremia is strongly associated with poor prognosis in acute kidney injury (AKI); however, the impact of sodium trajectories on the prognosis of patients with AKI has not yet been well elucidated. This study aimed to assess the association between sodium trajectories in patients with AKI and mortality at 30-day and 1-year follow-up.MethodsThis retrospective cohort study used data from Medical Information Mart for Intensive Care (MIMIC)-IV database, and patients diagnosed with AKI within 48 h after admission were enrolled. Group-based trajectory models (GBTM) were applied to map the developmental course of the serum sodium fluctuations. Kaplan–Meier survival curve was used to compare differences in mortality in AKI patients with distinct serum sodium trajectories. Hazard ratios (HRs) were calculated to determine the association between trajectories and prognosis using Cox proportional hazard models.ResultsA total of 9,314 AKI patients were enrolled. Three distinct sodium trajectories were identified including: (i) stable group (ST, in which the serum sodium levels remained relatively stable, n = 4,935; 53.0%), (ii) descending group (DS, in which the serum sodium levels declined, n = 2,994; 32.15%) and (iii) ascending group (AS, in which the serum sodium levels were elevated, n = 1,383; 14.85%). There was no significant difference in age and gender distribution among the groups. The 30-day mortality rates were 7.9% in ST, 9.5% in DS and 16.6% in AS (p < 0.001). The results of 1-year mortality rates were similar (p < 0.001). In adjusted analysis, patients in the DS (HR = 1.22, 95% confidence interval [CI], 1.04–1.43, p = 0.015) and AS (HR = 1.68, 95% CI, 1.42–2.01, p = 0.013) groups had higher risks of 30-day mortality compared to those in the ST group.ConclusionIn patients with AKI, the serum sodium trajectories were independently associated with 30-day and 1-year mortality. Association between serum sodium level trajectories and prognosis in patients with AKI deserve further study.

Balancing therapeutic effect and safety in ventilator parameter recommendation: An offline reinforcement learning approach

Reinforcement learning (RL) is increasingly applied in recommending ventilator parameters, yet existing methods prioritize therapeutic effect over patient safety. This leads to excessive exploration by the RL agent, posing risks. To address this, we propose a novel offline RL approach that leverages existing clinical data for exploration, employing fitted Q evaluation (FQE) for policy evaluation to minimize patient risk compared to online evaluation. Our method introduces a variational auto-encoder-gumble softmax (VAE-GS) model, discerning the hidden relationship between patient physiological status and ventilator parameters to constrain the exploratory space of the agent. Additionally, a noise network aids the agent in fully exploring the reachable space to find optimal ventilator parameters. Our approach significantly enhances safety, as evidenced by experiments on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset. It outperforms existing algorithms including the deterministic policy gradient algorithm (DDPG), soft actor-critic (SAC), batch-constrained deep Q-learning (BCQ), conservative Q-learning (CQL), and closed-form policy improvement operators (CFPI), showing improvements of 76.9%, 82.8%, 23.5%, 49.1% and 23.5%, respectively, while maintaining therapeutic effect.

Triglyceride-glucose index as a potential predictor for in-hospital mortality in critically ill patients with intracerebral hemorrhage: a multicenter, case-control study.

The correlation between the triglyceride-glucose index (TyG) and the prognosis of ischemic stroke has been well established. This study aims to assess the influence of the TyG index on the clinical outcomes of critically ill individuals suffering from intracerebral hemorrhage (ICH). Patients diagnosed with ICH were retrospectively retrieved from the Medical Information Mart for Intensive Care (MIMIC-IV) and the eICU Collaborative Research Database (eICU-CRD). Various statistical methods, including restricted cubic spline (RCS) regression, multivariable logistic regression, subgroup analysis, and sensitivity analysis, were employed to examine the relationship between the TyG index and the primary outcomes of ICH. A total of 791 patients from MIMIC-IV and 1,113 ones from eICU-CRD were analyzed. In MIMIC-IV, the in-hospital and ICU mortality rates were 14% and 10%, respectively, while in eICU-CRD, they were 16% and 8%. Results of the RCS regression revealed a consistent linear relationship between the TyG index and the risk of in-hospital and ICU mortality across the entire study population of both databases. Logistic regression analysis revealed a significant positive association between the TyG index and the likelihood of in-hospital and ICU death among ICH patients in both databases. Subgroup and sensitivity analysis further revealed an interaction between patients' age and the TyG index in relation to in-hospital and ICU mortality among ICH patients. Notably, for patients over 60years old, the association between the TyG index and the risk of in-hospital and ICU mortality was more pronounced compared to the overall study population in both MIMIC-IV and eICU-CRD databases, suggesting a synergistic effect between old age (over 60years) and the TyG index on the in-hospital and ICU mortality of patients with ICH. This study established a positive correlation between the TyG index and the risk of in-hospital and ICU mortality in patients over 60years who diagnosed with ICH, suggesting that the TyG index holds promise as an indicator for risk stratification in this patient population.

Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in Critically Ill Elderly Patients During Hospitalization: Internet-Based and Interpretable Model Study.

Acute kidney disease (AKD) affects more than half of critically ill elderly patients with acute kidney injury (AKI), which leads to worse short-term outcomes. We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps. Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South University were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators within 24 hours of the first diagnosis of AKI and the fluctuation range of some indicators, namely delta (day 3 after AKI minus day 1), as features. Six machine learning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpreting; and the Heroku platform for deploying the best-performing models as web-based apps. For the model of predicting the risk of AKD in elderly patients with AKI during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841-0.865), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addition, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.868, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed users to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model's top 10 influencing factors conducted based on the SHAP value, partial dependence plots revealed the optimal cutoff of some interventionable indicators. The top 5 factors predicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitrogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 factors determining in-hospital mortality were age, BUN on day 1, vasopressor use, BUN on day 3, and partial pressure of carbon dioxide (PaCO2). We developed and validated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively. The top 10 factors that influenced the AKD risk and mortality during hospitalization were identified and explained visually, which might provide useful applications for intelligent management and suggestions for future prospective research.

Relationship between lactate-to-albumin ratio and 28-day mortality in patients with exacerbation of chronic obstructive pulmonary disease admitted to the Intensive Care Unit

AimTo explore the predictive value of lactate-to-albumin ratio (LAR) on 28-day mortality in patients with exacerbation of chronic obstructive pulmonary disease (AECOPD) admitted to the Intensive Care Unit (ICU).MethodsAccording to ICD-9 and ICD-10 diagnosis codes, patients diagnosed with AECOPD in the Medical Information Mart for Intensive Care IV (v.2.2) database were selected. The primary endpoint was 28-day mortality after ICU admission. We used receiver operating characteristic (ROC) curve, Kaplan–Meier (K–M) survival curve, logistic regression analyses and subgroup analysis to assess predictive power of LAR.Results606 patients were included in this study. The 28-day mortality was 29.7%. The area under the ROC curves (AUC) for LAR were 0.641 [95% confidence interval (CI) 0.592–0.689], which was comparable with OASIS (AUC: 0.662; 95% CI 0.616–0.709; p = 0.471) and SOFA (AUC: 0.660; 95% CI 0.612–0.708; p = 0.500). The cutoff value of LAR was 0.645 by ROC curve. The high-LAR group showed a bad prognosis in K–M analysis (p < 0.001). Multivariate logistic regression shown that LAR was significantly associated with a poor outcome (odds ratio: 1.77; 95% CI 1.16–2.71; p = 0.008). Subgroup analysis showed no significant interaction of LAR with each subgroup (p for interaction: 0.175–0.775).ConclusionLAR is a rational and easily accessible marker, which is remarkably associated with 28-day mortality in ICU patients with AECOPD.

Development of a nomogram for predicting in-hospital mortality in patients with liver cirrhosis and sepsis

In this study, we aimed to investigate the risk factors associated with in-hospital mortality in patients with cirrhosis and sepsis, establish and validate the nomogram. This retrospective study included patients diagnosed with liver cirrhosis and sepsis in the Medical Information Mart for Intensive Care IV (MIMIC-IV). Models were compared by the area under the curve (AUC), integrated discriminant improvement (IDI), net reclassification index (NRI) and decision curve analysis (DCA). A total of 1,696 patients with cirrhosis and sepsis were included in the final cohort. Our final model included the following 9 variables: age, heartrate, total bilirubin (TBIL), glucose, sodium, anion gap (AG), fungal infections, mechanical ventilation, and vasopressin. The nomogram were constructed based on these variables. The AUC values of the nomograms were 0.805 (95% CI 0.776–0.833), which provided significantly higher discrimination compared to that of SOFA score [0.684 (95% CI 0.647–0.720)], MELD-Na [0.672 (95% CI 0.636–0.709)] and ABIC [0.674(95% CI 0.638–0.710)]. We established the first nomogram for predicting in-hospital mortality in patients with liver cirrhosis and sepsis based on these factors. This nomogram can performs well and facilitates clinicians to identify people at high risk of in-hospital mortality.

Hypothermia on the first day of ICU admission leads to increased in-hospital mortality in patients with subarachnoid hemorrhage

The relationship between early spontaneous hypothermia and adverse clinical outcomes in patients with subarachnoid hemorrhage (SAH) has not been paid much attention. We designed this retrospective cohort study to determine this relationship by analyzing the association between the lowest body temperature (T-lowest) on the first day of ICU admission and in-hospital mortality. In this study, 550 participants with non-traumatic SAH were chosen from the Medical Information Mart for Intensive Care (MIMIC)-IV database. Multivariate Cox regression analysis showed that T-lowest was nonlinearity correlated with in-hospital mortality (HR = 0.72, 95% CI: 0.59–0.86, p < 0.001). We divided the T-lowest into quartile groups. In comparison to reference group Q1 (31.30–36.06 ℃), group Q3 (36.56–36.72 ℃) had a 50% lower risk of death in the hospital (HR: 0.5, 95% CI: 0.28–0.87, p = 0.014). We further confirmed the curve-like relationship between T-lowest and in-hospital mortality using restricted cubic splines. The mortality is lowest when the T-lowest is close to 36.5 °C, and the risk of death is increased when the temperature is lower or higher than that. Our study demonstrates that in-hospital mortality is associated with T-lowest. Patients with non-traumatic SAH are at increased risk of death if their body temperature on the first day of ICU admission is too low.

Development and validation of a nomogram for predicting in-hospital mortality of intensive care unit patients with liver cirrhosis.

Liver cirrhosis patients admitted to intensive care unit (ICU) have a high mortality rate. To establish and validate a nomogram for predicting in-hospital mortality of ICU patients with liver cirrhosis. We extracted demographic, etiological, vital sign, laboratory test, comorbidity, complication, treatment, and severity score data of liver cirrhosis patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) and electronic ICU (eICU) collaborative research database (eICU-CRD). Predictor selection and model building were based on the MIMIC-IV dataset. The variables selected through least absolute shrinkage and selection operator analysis were further screened through multivariate regression analysis to obtain final predictors. The final predictors were included in the multivariate logistic regression model, which was used to construct a nomogram. Finally, we conducted external validation using the eICU-CRD. The area under the receiver operating characteristic curve (AUC), decision curve, and calibration curve were used to assess the efficacy of the models. Risk factors, including the mean respiratory rate, mean systolic blood pressure, mean heart rate, white blood cells, international normalized ratio, total bilirubin, age, invasive ventilation, vasopressor use, maximum stage of acute kidney injury, and sequential organ failure assessment score, were included in the multivariate logistic regression. The model achieved AUCs of 0.864 and 0.808 in the MIMIC-IV and eICU-CRD databases, respectively. The calibration curve also confirmed the predictive ability of the model, while the decision curve confirmed its clinical value. The nomogram has high accuracy in predicting in-hospital mortality. Improving the included predictors may help improve the prognosis of patients.

The obesity paradox in younger adult patients with sepsis: analysis of the MIMIC-IV database.

The obesity paradox suggests that individuals with obesity may have a survival advantage against specific critical illnesses, including sepsis. However, whether this paradox occurs at younger ages remains unclear. Therefore, we aimed to investigate whether obesity could improve survival in younger adult patients with sepsis. We used clinical data sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Patients with Sequential Organ Failure Assessment score ≥2 and suspected infection at the time of ICU admission were identified as having sepsis, following the Sepsis-3 definition. Individuals were classified into the obesity (BMI ≥30 kg/m²) and non-obesity (BMI <30 kg/m²) groups. Patients aged <50 and ≥50 years were categorized as younger adult patients and older patients, respectively. Of 73,181 patients in the MIMIC-IV ICU database, 18,120 satisfied the inclusion criteria: 2642 aged <50 years and 15,478 aged ≥50 years. The Kaplan-Meier curve showed that obesity was not associated with an improved mortality rate among younger adult patients with sepsis (log-rank test: P = 0.197), while obesity exhibited a survival benefit in older patients with sepsis (log-rank test: P < 0.001). After propensity score matching, in-hospital mortality did not differ significantly between the obesity and non-obesity groups (13.3% vs. 12.2%; P = 0.457) in the younger adult patients with sepsis. Multivariate logistic regression analysis revealed that BMI was not an independent risk factor for in-hospital mortality in younger adult patients with sepsis (underweight: adjusted odds ratio [aOR] 1.72, P = 0.076; overweight: aOR 0.88, P = 0.437; obesity: aOR 0.93, P = 0.677; and severe obesity: aOR 1.22, P = 0.580, with normal weight as the reference). Contrary to findings regarding older patients with sepsis, our findings suggest that the obesity paradox does not apply to younger adult patients with sepsis.

Nomogram predictive model for in-hospital mortality risk in elderly ICU patients with urosepsis

BackgroundUrinary tract infection (UTI) is a common cause of sepsis. Elderly patients with urosepsis in intensive care unit (ICU) have more severe conditions and higher mortality rates owing to factors such as advanced age, immunosenescence, and persistent host inflammatory responses. However, comprehensive studies on nomograms to predict the in-hospital mortality risk in elderly patients with urosepsis are lacking. This study aimed to construct a nomogram predictive model to accurately assess the prognosis of elderly patients with urosepsis and provide therapeutic recommendations.MethodsData of elderly patients with urosepsis were extracted from the Medical Information Mart for Intensive Care (MIMIC) IV 2.2 database. Patients were randomly divided into training and validation cohorts. A predictive nomogram model was constructed from the training set using logistic regression analysis, followed by internal validation and sensitivity analysis.ResultsThis study included 1,251 patients. LASSO regression analysis revealed that the Glasgow Coma Scale (GCS) score, red cell distribution width (RDW), white blood count (WBC), and invasive ventilation were independent risk factors identified from a total of 43 variables studied. We then created and verified a nomogram. The area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA) of the nomogram were superior to those of the traditional SAPS-II, APACHE-II, and SOFA scoring systems. The Hosmer-Lemeshow test results and calibration curves suggested good nomogram calibration. The IDI and NRI values showed that our nomogram scoring tool performed better than the other scoring systems. The DCA curves showed good clinical applicability of the nomogram.ConclusionsThe nomogram constructed in this study is a convenient tool for accurately predicting in-hospital mortality in elderly patients with urosepsis in ICU. Improving the treatment strategies for factors related to the model could improve the in-hospital survival rates of these patients.

Effect of Histamine H2 Receptor Antagonists on All-Cause Mortality in Critically Ill Patients With Essential Hypertension: A Retrospective Cohort Study.

Previous studies found that histamine H2 receptor antagonists (H2RAs) had blood pressure lowering and cardioprotective effects, but the impact of H2RAs on the survival outcomes of critically ill patients with essential hypertension is still unclear. The aim of this study was to investigate the association of H2RAs exposure with all-cause mortality in patients with essential hypertension based on Medical Information Mart for Intensive Care III database. A total of 17,739 patients were included, involving 8482 H2RAs users and 9257 non-H2RAs users. Propensity score matching (PSM) was performed to improve balance between 2 groups that were exposed to H2RAs or not. Kaplan-Meier survival curves were used to compare the cumulative survival rates and multivariable Cox regression models were performed to evaluate the association between H2RAs exposure and all-cause mortality. After 1:1 PSM, 4416 pairs of patients were enrolled. The results revealed potentially significant association between H2RAs exposure and decreased 30-day, 90-day, and 1-year mortalities in multivariate analyses (HR = 0.783, 95% CI: 0.696-0.882 for 30-day; HR = 0.860, 95% CI: 0.778-0.950 for 90-day; and HR = 0.883, 95% CI: 0.811-0.961 for 1-year mortality, respectively). Covariate effect analyses showed that the use of H2RAs was more beneficial in essential hypertension patients with age ≥ 60, BMI ≥ 25 kg/m2, coronary arteriosclerosis, stroke, and acute kidney failure, respectively. In conclusion, H2RAs exposure was related to lower mortalities in critically ill patients with essential hypertension, which provided novel potential strategy for the use of H2RAs in essential hypertension patients.

Long-term survival in stroke patients: insights into triglyceride-glucose body mass index from ICU data

BackgroundThe Triglyceride Glucose-Body Mass Index (TyG-BMI) has been established as a robust indicator of insulin resistance (IR), reflecting metabolic health across various populations. In general, lower TyG-BMI values are often associated with better metabolic health outcomes and a reduced risk of adverse health events in non-critically ill populations. Previous studies have highlighted a significant negative association between TyG-BMI and all-cause mortality (ACM) among critically ill atrial fibrillation patients. Given the high prevalence and severe outcomes associated with stroke, understanding how TyG-BMI at the time of ICU admission correlates with ACM in critically ill stroke patients becomes imperative. This study aims to assess the correlation between TyG-BMI and ACM in this specific patient cohort, exploring how traditional associations between TyG-BMI and metabolic health may differ in the context of acute, life-threatening illness.MethodsPatient data were retrieved by accessing the Medical Information Mart for Intensive Care IV (MIMIC-IV 2.2) database, categorizing patients into three groups on the basis of TyG-BMI tertiles. The study evaluated both primary and secondary outcomes: the primary outcomes included the 90-day, 180-day, and 1-year ACM, while secondary outcomes encompassed ICU, in-hospital, and 30-day ACM. Our study employed the Kaplan–Meier (K–M) curve method for outcome comparison across the groups while utilizing multivariate Cox proportional-hazards regression models and restricted cubic splines (RCS) to explore TyG-BMI association with these outcomes. Additionally, interaction and subgroup analyses were performed, focusing on different mortality time points.ResultsAmong a cohort of 1707 individuals diagnosed with stroke, the average age was 68 years (interquartile range [IQR]: 58–78 years), with 946 (55.42%) of the participants being male. The analysis of K-M curves suggested that patients having a lower TyG-BMI level faced a heightened risk of long-term ACM, whereas the short-term ACM exhibited no statistically significant differences across the three TyG-BMI groups. Furthermore, Cox proportional-hazards regression analysis validated a statistically significant increased risk of long-term ACM among patients belonging to the lowest TyG-BMI tertile. Additionally, RCS analysis results demonstrated L-shaped correlations between the TyG-BMI index and both short- and long-term ACM. These findings underscore the TyG-BMI predictive value for long-term mortality in stroke patients, highlighting a nuanced relationship that varies over different time frames. The results revealed no interactions between TyG-BMI and the stratified variables, with the exception of age.ConclusionIn our study, lower TyG-BMI levels in critically ill stroke patients are significantly related to a higher risk of long-term ACM within the context of the United States. This finding suggests the potential of TyG-BMI as a marker for stratifying long-term risk in this patient population. However, it's crucial to note that this association was not observed for short-term ACM, indicating that the utility of TyG-BMI may be more pronounced in long-term outcome prediction. Additionally, our conclusion that TyG-BMI could serve as a reliable indicator for managing and stratifying stroke patients over the long term is preliminary. To confirm our findings and assess the universal applicability of TyG-BMI as a prognostic tool, it is crucial to conduct rigorously designed research across various populations.

Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networks

Synthetic data generation offers a promising solution to enhance the usefulness of Electronic Healthcare Records (EHR) by generating realistic de-identified data. However, the existing literature primarily focuses on the quality of synthetic health data, neglecting the crucial aspect of fairness in downstream predictions. Consequently, models trained on synthetic EHR have faced criticism for producing biased outcomes in target tasks. These biases can arise from either spurious correlations between features or the failure of models to accurately represent sub-groups. To address these concerns, we present Bias-transforming Generative Adversarial Networks (Bt-GAN), a GAN-based synthetic data generator specifically designed for the healthcare domain. In order to tackle spurious correlations (i), we propose an information-constrained Data Generation Process (DGP) that enables the generator to learn a fair deterministic transformation based on a well-defined notion of algorithmic fairness. To overcome the challenge of capturing exact sub-group representations (ii), we incentivize the generator to preserve sub-group densities through score-based weighted sampling. This approach compels the generator to learn from underrepresented regions of the data manifold. To evaluate the effectiveness of our proposed method, we conduct extensive experiments using the Medical Information Mart for Intensive Care (MIMIC-III) database. Our results demonstrate that Bt-GAN achieves state-of-the-art accuracy while significantly improving fairness and minimizing bias amplification. Furthermore, we perform an in-depth explainability analysis to provide additional evidence supporting the validity of our study. In conclusion, our research introduces a novel and professional approach to addressing the limitations of synthetic data generation in the healthcare domain. By incorporating fairness considerations and leveraging advanced techniques such as GANs, we pave the way for more reliable and unbiased predictions in healthcare applications.

Development and validation of a nomogram for predicting 28-day mortality in patients with ischemic stroke.

We aimed to construct a validated nomogram model for predicting short-term (28-day) ischemic stroke mortality among critically ill populations. We collected raw data from the Medical Information Mart for Intensive Care IV database, a comprehensive repository renowned for its depth and breadth in critical care information. Subsequently, a rigorous analytical framework was employed, incorporating a 10-fold cross-validation procedure to ensure robustness and reliability. Leveraging advanced statistical methodologies, specifically the least absolute shrinkage and selection operator regression, variables pertinent to 28-day mortality in ischemic stroke were meticulously screened. Next, binary logistic regression was utilized to establish nomogram, then applied concordance index to evaluate discrimination of the prediction models. Predictive performance of the nomogram was assessed by integrated discrimination improvement (IDI) and net reclassification index (NRI). Additionally, we generated calibration curves to assess calibrating ability. Finally, we evaluated the nomogram's net clinical benefit using decision curve analysis (DCA), in comparison with scoring systems clinically applied under common conditions. A total of 2089 individuals were identified and assigned into training (n = 1443) or validation (n = 646) cohorts. Various identified risk factors, including age, ethnicity, marital status, underlying metastatic solid tumor, Charlson comorbidity index, heart rate, Glasgow coma scale, glucose concentrations, white blood cells, sodium concentrations, potassium concentrations, mechanical ventilation, use of heparin and mannitol, were associated with short-term (28-day) mortality in ischemic stroke individuals. A concordance index of 0.834 was obtained in the training dataset, indicating that our nomogram had good discriminating ability. Results of IDI and NRI in both cohorts proved that our nomogram had positive improvement of predictive performance, compared to other scoring systems. The actual and predicted incidence of mortality showed favorable concordance on calibration curves (P > 0.05). DCA curves revealed that, compared with scoring systems clinically used under common conditions, the constructed nomogram yielded a greater net clinical benefit. Utilizing a comprehensive array of fourteen readily accessible variables, a prognostic nomogram was meticulously formulated and rigorously validated to provide precise prognostication of short-term mortality within the ischemic stroke cohort.

The association between albumin-corrected calcium and prognosis in patients with cardiac arrest: a retrospective study based on the MIMIC-IV database

BackgroundCardiac arrest (CA) is one of the leading causes of death globally, characterized by high incidence and mortality. It is of particular significance to determine the prognosis of patients with CA early and accurately. Therefore, we aim to investigate the correlation between albumin-corrected calcium (ACC) and the prognosis in patients diagnosed with CA.MethodsWe retrospectively collected data from medical information mart for intensive care IV database. Patients were divided into two groups (survival and non-survival groups), according to the 90-day prognosis. In the Restricted cubic spline (RCS) analysis, the cut-off values (8.86 and 10.32) were obtained to categorize patients into three groups: low ACC group (< 8.86), moderate ACC group (8.86–10.32), and high ACC group (> 10.32). The least absolute shrinkage and selection operator with a ten-fold cross-validation regression analysis was performed to identify variables linked to the mortality. The inverse probability treatment weighting (IPTW) was used to address the confounding factors, and a weighted cohort was generated. RCS, Kaplan–Meier curve, and Cox regression analyses were used to explore the relationship between ACC and the mortality. Sensitivity analysis was employed to validate the stability of the results.ResultsCut-off values for ACC of 8.86 and 10.32 were determined. RCS analyses showed that there was an overall non-linear trend relationship between ACC and the risk of 90-day and 360-day mortalities. After IPTW adjustment, compared to the moderate ACC group, the 90-day and 360-day mortalities in the high ACC group were higher (P < 0.05). The Cox analyses before and after IPTW adjustment showed that both low ACC and high ACC group were independent risk factors for 90-day and 360-day all-cause mortality in patients with CA (P < 0.05). The results obtained from sensitivity analyses indicated the stability of the findings. The Kaplan–Meier survival curves indicated that 90- and 360-day cumulative survival rates in the low ACC and high ACC groups were lower than that in the moderate ACC group (χ2 = 11.350, P = 0.003; χ2 = 14.110, P = 0.001).ConclusionBoth low ACC (< 8.86) and high ACC groups (> 10.32) were independent risk factors for 90-day and 360-day all-cause mortality in patients with CA (P < 0.05). For those CA patients with high and low ACC, it deserved the attention of clinicians.

Assessment of Blood Pressure and Heart Rate Related Variables in Acute Stroke Patients Receiving Intravenous Antihypertensive Medication Infusions.

We performed an analysis of a large intensive care unit electronic database to provide preliminary estimates of various blood pressure parameters in patients with acute stroke receiving intravenous (IV) antihypertensive medication and determine the relationship with in-hospital outcomes. We identified the relationship between pre-treatment and post-treatment systolic blood pressure (SBP) and heart rate (HR)-related variables and in-hospital mortality and acute kidney injury in patients with acute stroke receiving IV clevidipine, nicardipine, or nitroprusside using data provided in the Medical Information Mart for Intensive Care (MIMIC) IV database. A total of 1830 patients were treated with IV clevidipine (n = 64), nicardipine (n = 1623), or nitroprusside (n = 143). The standard deviations [SDs] of pre-treatment SBP (16.3 vs. 13.7, p ≤ 0.001) and post-treatment SBP (15.4 vs. 14.4, p = 0.004) were higher in patients who died compared with those who survived, particularly in patients with intracerebral hemorrhage (ICH). The mean SBP was significantly lower post treatment compared with pre-treatment values for clevidipine (130.7mm Hg vs. 142.5mm Hg, p = 0.006), nicardipine (132.8mm Hg vs. 141.6mm Hg, p ≤ 0.001), and nitroprusside (126.2mm Hg vs. 139.6mm Hg, p ≤ 0.001). There were no differences in mean SDs post treatment compared with pre-treatment values for clevidipine (14.5 vs. 13.5, p = 0.407), nicardipine (14.2 vs. 14.6, p = 0.142), and nitroprusside (14.8 vs. 14.8, p = 0.997). The SDs of pre-treatment and post-treatment SBP were not significantly different in patients with ischemic stroke treated with IV clevidipine, nicardipine, or nitroprusside or for patients with ICH treated with IV clevidipine or nitroprusside. However, patients with ICH treated with IV nicardipine had a significantly higher SD of post-treatment SBP (13.1 vs. 14.2, p = 0.0032). We found that SBP fluctuations were associated with in-hospital mortality in patients with acute stroke. IV antihypertensive medication reduced SBP but did not reduce SBP fluctuations in this observational study. Our results highlight the need for optimizing therapeutic interventions to reduce SBP fluctuations in patients with acute stroke.