The Value of Admission Serological Indicators for Predicting 28-Day Mortality in Intensive Care Patients With Acute Heart Failure: Construction and Validation of a Nomogram

Development and performance assessment of novel machine learning models for predicting postoperative pneumonia in aneurysmal subarachnoid hemorrhage patients: external validation in MIMIC-IV

Background

Postoperative pneumonia (POP) is one of the primary complications after aneurysmal subarachnoid hemorrhage (aSAH) and is associated with postoperative mortality, extended hospital stay, and increased medical fee. Early identification of pneumonia and more aggressive treatment can improve patient outcomes. We aimed to develop a model to predict POP in aSAH patients using machine learning (ML) methods.

Methods

This internal cohort study included 706 patients with aSAH undergoing intracranial aneurysm embolization or aneurysm clipping. The cohort was randomly split into a train set (80%) and a testing set (20%). Perioperative information was collected from participants to establish 6 machine learning models for predicting POP after surgical treatment. The area under the receiver operating characteristic curve (AUC), precision-recall curve were used to assess the accuracy, discriminative power, and clinical validity of the predictions. The final model was validated using an external validation set of 97 samples from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database.

Results

In this study, 15.01% of patients in the training set and 12.06% in the testing set with POP after underwent surgery. Multivariate logistic regression analysis showed that mechanical ventilation time (MVT), Glasgow Coma Scale (GCS), Smoking history, albumin level, neutrophil-to-albumin Ratio (NAR), c-reactive protein (CRP)-to-albumin ratio (CAR) were independent predictors of POP. The logistic regression (LR) model presented significantly better predictive performance (AUC: 0.91) than other models and also performed well in the external validation set (AUC: 0.89).

Conclusion

A machine learning model for predicting POP in aSAH patients was successfully developed using a machine learning algorithm based on six perioperative variables, which could guide high-risk POP patients to take appropriate preventive measures.

Lactate dehydrogenase to albumin ratio is associated with in-hospital mortality in patients with acute heart failure: Data from the MIMIC-III database

The effect of the lactate dehydrogenase to albumin ratio (LAR) on the survival of patients with acute heart failure (AHF) is unclear. We aimed to analyze the impact of LAR on survival in patients with AHF. We retrieved eligible patients for our study from the Monitoring in Intensive Care Database III. For each patient in our study, we gathered clinical data and demographic information. We conducted multivariate logistic regression modeling and smooth curve fitting to assess whether the LAR score could be used as an independent indicator for predicting the prognosis of AHF patients. A total of 2,177 patients were extracted from the database. Survivors had an average age of 69.88, whereas nonsurvivors had an average age of 71.95. The survivor group had a mean LAR ratio of 13.44, and the nonsurvivor group had a value of 17.38. LAR and in-hospital mortality had a nearly linear correlation, according to smooth curve fitting (P < 0.001). According to multivariate logistic regression, the LAR may be an independent risk factor in predicting the prognosis of patients with AHF (odd ratio = 1.09; P < 0.001). The LAR ratio is an independent risk factor associated with increased in-hospital mortality rates in patients with AHF.

Interpretable Machine Learning Models Using Peripheral Immune Cells to Predict 90-Day Readmission or Mortality in Acute Heart Failure Patients

BACKGROUND

Acute heart failure (AHF) carries a grave prognosis, marked by high readmission and mortality rates within 90 days post-discharge. This underscores the urgent need for enhanced care transitions, early monitoring, and precise interventions for at-risk individuals during this critical period.

OBJECTIVE

Our study aims to develop and validate an interpretable machine learning (ML) model that integrates peripheral immune cell data with conventional clinical markers. Our goal is to accurately predict 90-day readmission or mortality in patients AHF.

METHODS

In our study, we conducted a retrospective analysis on 1210 AHF patients, segregating them into training and external validation cohorts. Patients were categorized based on their 90-day outcomes post-discharge into groups of 'with readmission/mortality' and 'without readmission/mortality'. We developed various ML models using data from peripheral immune cells, traditional clinical indicators, or both, which were then internally validated. The feature importance of the most promising model was examined through the Shapley Additive Explanations (SHAP) method, culminating in external validation.

RESULTS

In our cohort of 1210 patients, 28.4% (344) faced readmission or mortality within 90 days post-discharge. Our study pinpointed 10 significant indicators-spanning peripheral immune cells and traditional clinical metrics-that predict these outcomes, with the support vector machine (SVM) model showing superior performance. SHAP analysis further distilled these predictors to five key determinants, including three clinical indicators and two immune cell types, essential for assessing 90-day readmission or mortality risks.

CONCLUSION

Our analysis identified the SVM model, which merges traditional clinical indicators and peripheral immune cells, as the most effective for predicting 90-day readmission or mortality in AHF patients. This innovative approach promises to refine risk assessment and enable more targeted interventions for at-risk individuals through continuous improvement.

The predictive values of admission characteristics for 28-day all-cause mortality in septic patients with diabetes mellitus: a study from the MIMIC database

Background

Septic patients with diabetes mellitus (DM) are more venerable to subsequent complications and the resultant increase in associated mortality. Therefore, it is important to make tailored clinical decisions for this subpopulation at admission.

Method

Data from large-scale real-world databases named the Medical Information Mart for Intensive Care Database (MIMIC) were reviewed. The least absolute selection and shrinkage operator (LASSO) was performed with 10 times cross-validation methods to select the optimal prognostic factors. Multivariate COX regression analysis was conducted to identify the independent prognostic factors and nomogram construction. The nomogram was internally validated via the bootstrapping method and externally validated by the MIMIC III database with receiver operating characteristic (ROC), calibration curves, decision curve analysis (DCA), and Kaplan-Meier curves for robustness check.

Results

A total of 3,291 septic patients with DM were included in this study, 2,227 in the MIMIC IV database and 1,064 in the MIMIC III database, respectively. In the training cohort, the 28-day all-cause mortality rate is 23.9% septic patients with DM. The multivariate Cox regression analysis reveals age (hazard ratio (HR)=1.023, 95%CI: 1.016-1.031, p<0.001), respiratory failure (HR=1.872, 95%CI: 1.554-2.254, p<0.001), Sequential Organ Failure Assessment score (HR=1.056, 95%CI: 1.018-1.094, p=0.004); base excess (HR=0.980, 95%CI: 0.967-0.992, p=0.002), anion gap (HR=1.100, 95%CI: 1.080-1.120, p<0.001), albumin (HR=0.679, 95%CI: 0.574-0.802, p<0.001), international normalized ratio (HR=1.087, 95%CI: 1.027-1.150, p=0.004), red cell distribution width (HR=1.056, 95%CI: 1.021-1.092, p=0.001), temperature (HR=0.857, 95%CI: 0.789-0.932, p<0.001), and glycosylated hemoglobin (HR=1.358, 95%CI: 1.320-1.401, p<0.001) at admission are independent prognostic factors for 28-day all-cause mortality of septic patients with DM. The established nomogram shows satisfied accuracy and clinical utility with AUCs of 0.870 in the internal validation and 0.830 in the external validation cohort as well as 0.820 in the septic shock subpopulation, which is superior to the predictive value of the single SOFA score.

Conclusion

Our results suggest that admission characteristics show an optimal prediction value for short-term mortality in septic patients with DM. The established model can support intensive care unit physicians in making better initial clinical decisions for this subpopulation.

Predictive value of blood urea nitrogen in heart failure: a systematic review and meta-analysis

Background

The mortality rate of patients with heart failure (HF) remains high, and when heart failure occurs, blood urea nitrogen (BUN) is involved in the perfusion of renal blood flow. Some studies have shown an association between heart failure prognosis and blood urea nitrogen, but the results of some other studies were inconsistent. Therefore, we conducted a comprehensive meta-analysis to investigate the value of BUN on the prognosis of patients with heart failure.

Methods

A computerized systematic search of all English literature was performed in four databases, PubMed, Cochrane, Embase and Web of Science, from their inception to May 2022. The data of BUN were classified into continuous and categorical variables after passing the inclusion and exclusion criteria. The BUN data of both types were extracted separately into stata15.0 for statistical analysis.

Results

A total of 19 cohort studies involving 56,003 patients were included. When BUN was used as a categorical variable, the risk of death in heart failure was 2.29 times higher for high levels of BUN than for low levels of BUN (RR = 2.29, 95% CI:1.42-3.70, P < 0.001). The results showed statistical significance in multifactorial and univariate groups, the prospective cohort, and European and Asian groups. When BUN was used as a continuous variable, the risk of death in heart failure was 1.02 times higher for each unit increase in BUN (RR = 1.02, 95% CI:1.01-1.03, p < 0.001). Subgroup analysis showed statistical significance in retrospective cohort, American and Asian.

Conclusion

High BUN is an independent predictor of all-cause mortality in heart failure. Lower BUN was associated with better prognosis in patients with heart failure.

Construction of a web-based dynamic nomogram for predicting the prognosis in acute heart failure

AIMS

The early identification and appropriate management may provide clinically meaningful and substained benefits in patients with acute heart failure (AHF). This study aimed to develop an integrative nomogram with myocardial perfusion imaging (MPI) for predicting the risk of all-cause mortality in AHF patients.

METHODS AND RESULTS

Prospective study of 147 patients with AHF who received gated MPI (59.0 [47.5, 68.0] years; 78.2% males) were enrolled and followed for the primary endpoint of all-cause mortality. We analysed the demographic information, laboratory tests, electrocardiogram, and transthoracic echocardiogram by the least absolute shrinkage and selection operator (LASSO) regression for selection of key features. A multivariate stepwise Cox analysis was performed to identify independent risk factors and construct a nomogram. The predictive values of the constructed model were compared by Kaplan-Meier curve, area under the curves (AUCs), calibration plots, continuous net reclassification improvement, integrated discrimination improvement, and decision curve analysis. The 1, 3, and 5 year cumulative rates of death were 10%, 22%, and 29%, respectively. Diastolic blood pressure [hazard ratio (HR) 0.96, 95% confidence interval (CI) 0.93-0.99; P = 0.017], valvular heart disease (HR 3.05, 95% CI 1.36-6.83; P = 0.007), cardiac resynchronization therapy (HR 0.37, 95% CI 0.17-0.82; P = 0.014), N-terminal pro-B-type natriuretic peptide (per 100 pg/mL; HR 1.02, 95% CI 1.01-1.03; P < 0.001), and rest scar burden (HR 1.03, 95% CI 1.01-1.06; P = 0.008) were independent risk factors for patients with AHF. The cross-validated AUCs (95% CI) of nomogram constructed by diastolic blood pressure, valvular heart disease, cardiac resynchronization therapy, N-terminal pro-B-type natriuretic peptide, and rest scar burden were 0.88 (0.73-1.00), 0.83 (0.70-0.97), and 0.79 (0.62-0.95) at 1, 3, and 5 years, respectively. Continuous net reclassification improvement and integrated discrimination improvement were also observed, and the decision curve analysis identified the greater net benefit of the nomogram across a wide range of threshold probabilities (0-100% at 1 and 3 years; 0-61% and 62-100% at 5 years) compared with dismissing the included factors or using either factor alone.

CONCLUSIONS

A predictive nomogram for the risk of all-cause mortality in patients with AHF was developed and validated in this study. The nomogram incorporated the rest scar burden by MPI is highly predictive, and may help to better stratify clinical risk and guide treatment decisions in patients with AHF.

Development and Validation of a Novel Nomogram to Predict Improved Left Ventricular Ejection Fraction in Patients With Heart Failure After Successful Percutaneous Coronary Intervention for Chronic Total Occlusion

Background

Heart failure with improved left ventricular ejection fraction (HFiEF) is linked to a good clinical outcome. The purpose of this study was to create an easy-to-use model to predict the occurrence of HFiEF in patients with heart failure (HF), 1 year after successful percutaneous coronary intervention (PCI) for chronic total occlusion (CTO) (CTO PCI).

Methods

Patients diagnosed with HF who successfully underwent CTO PCI between January 2016 and August 2019 were included. To mitigate the effect of residual stenosis on left ventricular (LV) function, we excluded patients with severe residual stenosis, as quantitatively measured by a residual synergy between PCI with Taxus and Cardiac Surgery score (rSS) of &gt;8. We gathered demographic data, medical history, angiographic and procedural characteristics, echocardiographic parameters, laboratory results, and medication information. The least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression models were used to identify predictors of HFiEF 1 year after CTO revascularization. A nomogram was established and validated according to the area under the receiver operating characteristic curve (AUC) and calibration curves. Internal validation was performed using bootstrap resampling.

Results

A total of 465 patients were finally included in this study, and 165 (35.5%) patients experienced HFiEF 1 year after successful CTO PCI. According to the LASSO regression and multivariate logistic regression analyses, four variables were selected for the final prediction model: age [odds ratio (OR): 0.969; 95% confidence interval (CI): 0.952–0.988; p = 0.001], previous myocardial infarction (OR: 0.533; 95% CI: 0.357–0.796; p = 0.002), left ventricular end-diastolic dimension (OR: 0.940; 95% CI: 0.910–0.972; p &lt; 0.001), and sodium glucose cotransporter two inhibitors (OR: 5.634; 95% CI: 1.756–18.080; p = 0.004). A nomogram was constructed to present the results. The C-index of the model was 0.666 (95% CI, 0.613–0.719) and 0.656 after validation. The calibration curve demonstrated that the nomogram agreed with the actual observations.

Conclusions

We developed an simple and effective nomogram for predicting the occurrence of HFiEF in patients with HF, 1 year after successful CTO PCI without severe residual stenosis.