Association between albumin infusion and septic patients with coronary heart disease: A retrospective study based on medical information mart for intensive care III database

Z, Ye; Gao, Ming; Ge, Chenglong; Lin, Wenrui; Zhang, Lina; Zou, Yu; Peng, Qianyi

doi:10.3389/fcvm.2022.982969

Cited by 9 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most impactful parameters contributing to predicted mortality risk in sepsis patients were Age, AST, invasive ventilation treatment, and BUN. NLR and serum albumin were also highly predictive of in-hospital mortality in ICU sepsis patients, consistent with previous research [ 56 , 57 ]. Interestingly, some inflammatory biomarkers, such as NHR and MHR, critically impacted hospital mortality of sepsis patients in the XGBoost model.…”

Section: Discussionsupporting

confidence: 91%

Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers

Zhang,

Shao,

Yuan

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

Background This study aimed to develop and validate an interpretable machine-learning model that utilizes clinical features and inflammatory biomarkers to predict the risk of in-hospital mortality in critically ill patients suffering from sepsis. Methods We enrolled all patients diagnosed with sepsis in the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.2.0), eICU Collaborative Research Care (eICU-CRD 2.0), and the Amsterdam University Medical Centers databases (AmsterdamUMCdb 1.0.2). LASSO regression was employed for feature selection. Seven machine-learning methods were applied to develop prognostic models. The optimal model was chosen based on its accuracy, F1 score and area under curve (AUC) in the validation cohort. Moreover, we utilized the SHapley Additive exPlanations (SHAP) method to elucidate the effects of the features attributed to the model and analyze how individual features affect the model’s output. Finally, Spearman correlation analysis examined the associations among continuous predictor variables. Restricted cubic splines (RCS) explored potential non-linear relationships between continuous risk factors and in-hospital mortality. Results 3535 patients with sepsis were eligible for participation in this study. The median age of the participants was 66 years (IQR, 55–77 years), and 56% were male. After selection, 12 of the 45 clinical parameters collected on the first day after ICU admission remained associated with prognosis and were used to develop machine-learning models. Among seven constructed models, the eXtreme Gradient Boosting (XGBoost) model achieved the best performance, with an AUC of 0.94 and an F1 score of 0.937 in the validation cohort. Feature importance analysis revealed that Age, AST, invasive ventilation treatment, and serum urea nitrogen (BUN) were the top four features of the XGBoost model with the most significant impact. Inflammatory biomarkers may have prognostic value. Furthermore, SHAP force analysis illustrated how the constructed model visualized the prediction of the model. Conclusions This study demonstrated the potential of machine-learning approaches for early prediction of outcomes in patients with sepsis. The SHAP method could improve the interoperability of machine-learning models and help clinicians better understand the reasoning behind the outcome.

show abstract

Section: Discussionsupporting

confidence: 91%

Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers

Zhang,

Shao,

Yuan

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

show abstract

“…The most impactful input parameters contributing to predicted mortality risk in sepsis patients were age, AST, invasive ventilation treatment, and heart rate. Blood urea nitrogen and serum albumin were also highly predictive of in-hospital mortality in ICU sepsis patients, consistent with previous research 33,34 . Interestingly, some novel in ammatory biomarkers critically impacted hospital mortality of sepsis patients in the XGBoost model.…”

Section: Discussionsupporting

confidence: 90%

An interpretable machine learning models for predicting in-hospital mortality in patients with sepsis based on multiple databases

Zhang,

Shao,

Yuan

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: This study aimed to develop and validate an interpretable machine-learning model that utilizes clinical features and inflammatory biomarkers to predict the risk of in-hospital mortality in critically ill patients suffering from sepsis. Methods: We enrolled all patients diagnosed with sepsis in the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.2.0), eICU Collaborative Research Care (eICU-CRD 2.0), and the Amsterdam University Medical Centers databases (AmsterdamUMCdb 1.0.2). Lasso regression was employed for feature selection. Seven machine-learning methods were applied to develop prognostic models. The optimal model was chosen based on its accuracy and area under curve (AUC) in the validation cohort. Moreover, we utilized the SHapley Additive exPlanations (SHAP) method to elucidate the effects of the features attributed to the model and analyze how individual features affect the model's output. Finally, Spearman correlation analysis examined the associations among continuous predictor variables. Restricted cubic splines (RCS) explored potential non-linear relationships between continuous risk factors and in-hospital mortality. Results: A total of 3,535 patients with sepsis were eligible for participation in this study. The median age of the participants was 66 years (IQR, 55–77 years), and 56% were male. After selection, 12 of the 45 clinical parameters collected on the first day after ICU admission remained associated with prognosis and were used to develop machine-learning models. Among seven constructed models, the eXtreme Gradient Boosting (XGBoost) model achieved the best performance, with an AUC of 0.73 and an accuracy of 85% in the validation cohort. Feature importance analysis revealed that Age, AST, invasive ventilation treatment, and Heart rate were the top four features of the XGBoost model with the most significant impact. Some novel inflammatory biomarkers such as NLR, NHR, and MHR also critically impacted the in-hospital mortality of sepsis patients in the XGBoost model. Furthermore, SHAP force analysis illustrated how the constructed model visualized the prediction of the model. Conclusions: This study demonstrated the potential of machine-learning approaches for early prediction of outcomes in patients with sepsis. The SHAP method could improve the interoperability of machine-learning models and help clinicians better understand the reasoning behind the outcome.

show abstract

“…PE and DVT are collectively referred to as VTE, affecting approximately 10 million people worldwide [20]. Epidemiological evidence has suggested that low serum albumin levels are associated with the occurrence of many cardiovascular diseases, ranging from ischemic heart disease, heart failure, atrial brillation, stroke, and venous thromboembolism itself [21]. Multiple observational studies have revealed that serum albumin levels are correlated negatively with VTE [22][23][24].…”

Section: Discussionmentioning

confidence: 99%

Serum albumin levels and pulmonary embolism risk: insights from observational and mendelian randomization studies

Huang,

Pang

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND: Previous observational studies have linked serum albumin (ALB) to prognosis in patients with pulmonary embolism (PE). Nevertheless, the nature of the association between serum albumin and PE risk remains unclear, and the potential causality requires to be investigated. Our study aimed to integrate an observational study and a two-sample Mendelian randomization (MR) analysis to comprehensively assess the relationship between serum albumin and PE risk. METHODS: A total of 13,326 participants, consisting of 749 PE patients and 12,577 non-PE controls, were selected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database for an observational study. The effects of serum albumin on PE risk were assessed using propensity score matching (PSM) and restricted cubic spline (RCS) model analysis, adjusting for multiple covariates. Subsequently, a two-sample MR analysis was performed using summary statistics from genome-wide association studies (GWAS) to assess the causality between serum albumin and PE risk. Sensitivity analyses were carried out to confirm the robustness of MR results. RESULTS: The results of PSM indicated that the serum albumin levels were lower in PE patients (3.97 g/dL) than in non-PE controls (4.09 g/dL). The RCS model demonstrated a linear negative correlation between serum albumin and PE risk (P for nonlinear > 0.05). MR analysis confirmed a causality between serum albumin (OR = 0.744, 95% CI: 0.642~0.861, P < 0.001) and PE risk. CONCLUSION: Our study provided evidence that low serum albumin appeared to be associated with an increased risk of PE, and this association was possibly causal.

show abstract

Association between albumin infusion and septic patients with coronary heart disease: A retrospective study based on medical information mart for intensive care III database

Cited by 9 publications

References 35 publications

Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers

Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers

An interpretable machine learning models for predicting in-hospital mortality in patients with sepsis based on multiple databases

Serum albumin levels and pulmonary embolism risk: insights from observational and mendelian randomization studies

Contact Info

Product

Resources

About