Prognostic value of blood urea nitrogen-to-serum albumin ratio for mortality of pneumonia in patients receiving glucocorticoids: Secondary analysis based on a retrospective cohort study

Explainable machine learning model for prediction of 28-day all-cause mortality in immunocompromised patients in the intensive care unit: a retrospective cohort study based on MIMIC-IV database

OBJECTIVES

This study aimed to develop and validate an explainable machine learning (ML) model to predict 28-day all-cause mortality in immunocompromised patients admitted to the intensive care unit (ICU). Accurate and interpretable mortality prediction is crucial for clinical decision-making and optimal allocation of critical care resources for this vulnerable patient population.

METHODS

We utilized retrospective clinical data from the MIMIC-IV (version 2.2) database, encompassing ICU admissions at Beth Israel Deaconess Medical Center from 2008 to 2019. Eligible immunocompromised patients, including those with primary immunodeficiencies and chronic acquired conditions, such as hematological malignancies, solid tumors, and organ transplantation, were selected. Data were randomly split into training (80%) and testing (20%) cohorts. Ten ML models (logistic regression, XGBoost, LightGBM, AdaBoost, Random Forest, Gradient Boosting, Gaussian Naive Bayes, Complement Naive Bayes, Multilayer Perceptron, and Support Vector Machine) were developed and evaluated using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, specificity, accuracy, and F1 score. Model explainability was achieved through SHapley Additive exPlanations (SHAP), and decision curve analysis (DCA) assessed clinical utility. In addition, Cox proportional hazards regression was conducted to evaluate the impact of predictive factors on time-to-event outcomes.

RESULTS

Among the evaluated models, the Support Vector Machine (SVM) demonstrated the highest AUROC of 0.863 (95% CI 0.834-0.890) and a notable AUPRC of 0.678 (95% CI 0.624-0.736). Key predictive factors consistently identified across multiple ML models included 24-h urine output, blood urea nitrogen (BUN) levels, presence of metastatic solid tumors, Charlson Comorbidity Index (CCI), and international normalized ratio (INR). SHAP analyses provided detailed insights into how these features influenced model predictions.

CONCLUSIONS

The explainable ML models based on various artificial intelligence methods demonstrated promising clinical applicability in predicting 28-day mortality risk among immunocompromised ICU patients. Factors such as urine output, BUN, metastatic solid tumors, CCI, and INR significantly contributed to prediction outcomes and may serve as important predictors in clinical practice.

The relationship between blood urea nitrogen to serum albumin ratio and cardiovascular diseases, cardiovascular mortality, and all-cause mortality in patients with diabetes mellitus

Background

The relationship between the Blood Urea Nitrogen to Albumin Ratio (BAR) and cardiovascular diseases in diabetes, as well as cardiovascular and all-cause mortality, is not yet entirely understood. This study aimed to examine the correlation between the serum urea nitrogen to albumin ratio and cardiovascular diseases, cardiovascular mortality, and all-cause mortality in diabetes.

Methods

A total of 7043 adult diabetes patients were included from the NHANES database from 2001 to 2018. The relationship between BAR and cardiovascular diseases, cardiovascular mortality and all-cause mortality in patients with diabetes mellitus was verified using baseline characteristic analysis, multivariate logistic regression analysis, multivariate Cox proportional hazards model, Kaplan-Meier (K-M) analysis, smoothed fitted curves, and subgroup analysis.

Results

Results of the logistic regression analysis indicated a substantial positive association, between the BAR and the risk of cardiovascular disease in individuals with diabetes (HR, 1.09 [95% CI 1.06-1.12], p < 0.001). Cox regression analysis revealed a substantial positive association between the BAR and the risk of cardiovascular (OR, 1.13 [95% CI, 1.10-1.17], p < 0.001) and all-cause mortality (OR, 1.12 [95% CI 1.11-1.14], p < 0.001) in diabetes. The restricted cubic spline (RCS) curves indicated a non-linear relationship between BAR and the risk of cardiovascular disease, cardiovascular mortality, and all-cause mortality in diabetes (p < 0.01). The receiver operating characteristic (ROC) curves demonstrated that the BAR had superior predictive performance for cardiovascular risk (AUC: 0.648), cardiovascular mortality (AUC: 0.618), and all-cause mortality (AUC: 0.674) compared to the body mass index (BMI) (cardiovascular risk AUC: 0.525, cardiovascular mortality AUC: 0.563, all-cause mortality AUC: 0.571) and the weight-adjusted-waist index (WWI) (cardiovascular risk AUC: 0.579, cardiovascular mortality AUC: 0.497, all-cause mortality AUC: 0.570). These results underscore the enhanced ability of the BAR to discriminate between positive and negative outcomes, making it a more effective predictor than WWI. Kaplan-Meier analysis further verified the predictive capacity of BAR, for cardiovascular mortality and all-cause mortality in diabetes patients. Subgroup analysis revealed consistent associations between BAR and a variety of subgroups.

Conclusion

The incidence of cardiovascular disease, cardiovascular mortality, and all-cause mortality was substantially elevated, in patients with diabetes with a higher BAR level. Cardiovascular disease, cardiovascular mortality, and all-cause mortality may be more prevalent among diabetic patients with elevated BAR levels. BAR is a novel marker for the prediction of cardiovascular disease, cardiovascular mortality, and all-cause mortality in diabetes.

Comparison of Prognostic Value of 10 Biochemical Indices at Admission for Prediction Postoperative Myocardial Injury and Hospital Mortality in Patients with Osteoporotic Hip Fracture

Aim: To evaluate the prognostic impact at admission of 10 biochemical indices for prediction postoperative myocardial injury (PMI) and/or hospital death in hip fracture (HF) patients. Methods: In 1273 consecutive patients with HF (mean age 82.9 ± 8.7 years, 73.5% women), clinical and laboratory parameters were collected prospectively, and outcomes were recorded. Multiple logistic regression and receiver-operating characteristic analyses (the area under the curve, AUC) were preformed, the number needed to predict (NNP) outcome was calculated. Results: Age ≥ 80 years and IHD were the most prominent clinical factors associated with both PMI (with cardiac troponin I rise) and in-hospital death. PMI occurred in 555 (43.6%) patients and contributed to 80.3% (49/61) of all deaths (mortality rate 8.8% vs. 1.9% in non-PMI patients). The most accurate biochemical predictive markers were parathyroid hormone > 6.8 pmol/L, urea > 7.5 mmol/L, 25(OH)vitamin D < 25 nmol/L, albumin < 33 g/L, and ratios gamma-glutamyl transferase (GGT) to alanine aminotransferase > 2.5, urea/albumin ≥ 2.0 and GGT/albumin ≥ 7.0; the AUC for developing PMI ranged between 0.782 and 0.742 (NNP: 1.84−2.13), the AUC for fatal outcome ranged from 0.803 to 0.722, (NNP: 3.77−9.52). Conclusions: In HF patients, easily accessible biochemical indices at admission substantially improve prediction of hospital outcomes, especially in the aged >80 years with IHD.

Blood urea nitrogen/albumin ratio on admission predicts mortality in patients with non ST segment elevation myocardial infarction

The aim of this study is to reveal the predictive power of biomarkers and SYNTAX (SX) score for short-term mortality in patients diagnosed with non-ST-segment elevation myocardial infarction (NSTEMI) in the emergency department. This is prospective observational cohort study. Demographic characteristics of the patients, laboratory parameters on admission, left ventricular ejection fraction (LVEF) percentages, affected vessels in angiography (CAG) and the treatment strategy [medical therapy, percutaneous transluminal coronary angioplasty (PTCA), coronary angio by-pass graft] and SX scores were recorded on the data collection form. ROC curve was used to investigate the predictivity of blood urea nitrogen/albumin ratio (BAR), procalcitonin, C-reactive protein (CRP), high sensitivity cardiac troponin I (Hs-cTnI), CRP to serum albumin ratio (CAR), neutrophil to lymphocyte ratio (NLR) and SX scores in mortality. Multivariate analysis of biomarkers and SX score was performed to estimate the patients' 30-day mortality. Of the 415 patients were included in the study. ROC analysis of BAR, CAR, CRP, Procalcitonin, Hs-cTnI, NLR and SX score to predict mortality was statistically significant. BAR (OR: 1.280, 95% CI: 1.113-1.472, p = .001) and SX score (OR: 1.071, 95% CI: 1.018-1.126, p = .007) were found to be independent predictors of 30 days mortality. LVEF reduction, SX score, the number of affected vessels and the frequency of LMCA lesions increase were found to be statistically significant in patients with BAR ≥4.8. BAR, which can be calculated easily and quickly on admission to the emergency department and in clinical practice, may be used to predict mortality in patients with NSTEMI.