Course of lactate, pH and base excess for prediction of mortality in medical intensive care patients

Schork, Anja; Moll, Kathrin; Haap, Michael; Riessen, Reimer; Wagner, Róbert

doi:10.1371/journal.pone.0261564

Cited by 19 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the results revealed that a higher APACHE II score, potassium levels, lactate levels, sodium levels, and respiratory rate; multiple organ support use and medication use; and older age as well as lower SPO2, MAP, platelet count, BMI, and O2 saturation were positively correlated with in-hospital death. The findings regarding the importance of variables are consistent with those of a previous study [ 7 , 11 , 12 , 32 , 33 , 34 ]. In this study, an inverse relationship was noted between diabetes mellitus and in-hospital mortality.…”

Section: Discussionsupporting

confidence: 91%

Explainable Machine Learning-Based Risk Prediction Model for In-Hospital Mortality after Continuous Renal Replacement Therapy Initiation

et al. 2022

View full text Add to dashboard Cite

In this study, we established an explainable and personalized risk prediction model for in-hospital mortality after continuous renal replacement therapy (CRRT) initiation. This retrospective cohort study was conducted at Changhua Christian Hospital (CCH). A total of 2932 consecutive intensive care unit patients receiving CRRT between 1 January 2010, and 30 April 2021, were identified from the CCH Clinical Research Database and were included in this study. The recursive feature elimination method with 10-fold cross-validation was used and repeated five times to select the optimal subset of features for the development of machine learning (ML) models to predict in-hospital mortality after CRRT initiation. An explainable approach based on ML and the SHapley Additive exPlanation (SHAP) and a local explanation method were used to evaluate the risk of in-hospital mortality and help clinicians understand the results of ML models. The extreme gradient boosting and gradient boosting machine models exhibited a higher discrimination ability (area under curve [AUC] = 0.806, 95% CI = 0.770–0.843 and AUC = 0.823, 95% CI = 0.788–0.858, respectively). The SHAP model revealed that the Acute Physiology and Chronic Health Evaluation II score, albumin level, and the timing of CRRT initiation were the most crucial features, followed by age, potassium and creatinine levels, SPO2, mean arterial pressure, international normalized ratio, and vasopressor support use. ML models combined with SHAP and local interpretation can provide the visual interpretation of individual risk predictions, which can help clinicians understand the effect of critical features and make informed decisions for preventing in-hospital deaths.

show abstract

Section: Discussionsupporting

confidence: 91%

Explainable Machine Learning-Based Risk Prediction Model for In-Hospital Mortality after Continuous Renal Replacement Therapy Initiation

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Statistical analysis was performed on the original datasets extracted from the NHANES and a complex sample analysis was performed using the stratification, cluster, and sample weight variables provides in the NHANES [ 56 ]. A new sample weight variable for the two combined datasets from 2011 to 2014 was created by taking one twice for the 2-year weight for each participant sampled from 2011 to 2012 and one twice for the 2-year weight for each person sampled from 2013 to 2014.…”

Section: Methodsmentioning

confidence: 99%

Higher Total Cholesterol Concentration May Be Associated with Better Cognitive Performance among Elderly Females

et al. 2022

View full text Add to dashboard Cite

Background: The brain contains the highest level of cholesterol in the body, and the total amount of serum cholesterol in the blood has a huge impact on brain aging and cognitive performance. However, the association of total serum cholesterol with cognitive function remains uncertain. This study determines whether there is an association between the total amount of cholesterol in the blood and cognitive performance in elderly females without a history of stroke. Methods: This population-based cross-sectional study was conducted on elderly (over 60 years old) females and males without a history of stroke from 2011 to 2014 in the US National Health and Nutrition Examination Survey (NHANES). The primary exposure was total blood cholesterol, and the main outcome was cognitive performance; this association was assessed with logistic regression analysis and restricted cubic splines. Results: 1309 female and 1272 male participants were included. In females, higher total cholesterol was significantly associated with higher cognitive scores, particularly in the digit symbol substitution test (OR 0.51, 95% CI (0.36–0.72)) and the animal fluency test (OR 0.64, 95% CI (0.45–0.91)). This association remained significant in models adjusted for age, race, smoking status, education level, and chronic conditions (OR 0.40, 95% CI (0.25–0.63)). This association was not significant in males, however. Conclusions: A higher concentration of total cholesterol measured in later life may be a protective factor for cognitive performance among females over 60 years old without a history of stroke. Further, this association was more pronounced among women with higher levels of education than women with lower or no education.

show abstract

“…A direct comparison of our findings with other studies is problematic. Lactate and BE are routinely measured in critically ill patients suffering from various diseases, and both serve as mortality predictors in ICU (for example, in post-cardiac surgery patients or those with cardiogenic shock, ruptured abdominal aortic aneurysms, or trauma) [ 4 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 ]. Whether BE or lactate concentrations serve as better predictors of mortality in critical care patients has not yet been determined [ 4 , 33 , 34 , 35 , 36 ], with no studies reporting with certainty whether these predictors are both independent and/or additive.…”

Section: Discussionmentioning

confidence: 99%

“…Similarly, Schork et al reported a relationship between lactate, BE, and pH and mortality in 4067 intensive care unit patients [ 40 ]. The predicted mortality by SAPS II was 29%, and only 47% of them required mechanical ventilation.…”

Section: Discussionmentioning

confidence: 99%

“…The predicted mortality by SAPS II was 29%, and only 47% of them required mechanical ventilation. For admission to ICU, the cut-off values for mortality were 2.1 mmol/L for lactate and −3.8 mmol/L for BE [ 40 ]. Compared with that study, all our patients were mechanically ventilated, their predicted mortality assessed by the SOFA score was around 55%, and the cut-offs for lactate and BE were 4.5 mmol/L and −9.5 mmol/L, respectively.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Admission Lactate Concentration, Base Excess, and Alactic Base Excess Predict the 28-Day Inward Mortality in Shock Patients

Smuszkiewicz

Jawień

Szrama

et al. 2022

JCM

View full text Add to dashboard Cite

Base excess (BE) and lactate concentration may predict mortality in critically ill patients. However, the predictive values of alactic BE (aBE; the sum of BE and lactate), or a combination of BE and lactate are unknown. The study aimed to investigate whether BE, lactate, and aBE measured on admission to ICU may predict the 28-day mortality for patients undergoing any form of shock. In 143 consecutive adults, arterial BE, lactate, and aBE were measured upon ICU admission. Receiver Operating Curve (ROC) characteristics and Cox proportional hazard regression models (adjusted to age, gender, forms of shock, and presence of severe renal failure) were then used to investigate any association between these parameters and 28-day mortality. aBE < −3.63 mmol/L was found to be associated with a hazard ratio of 3.19 (HR; 95% confidence interval (CI): 1.62–6.27) for mortality. Risk of death was higher for BE < −9.5 mmol/L (HR: 4.22; 95% CI: 2.21–8.05), particularly at lactate concentrations > 4.5 mmol/L (HR: 4.62; 95% CI: 2.56–8.33). A 15.71% mortality rate was found for the combined condition of BE > cut-off and lactate < cut-off. When BE was below but lactate above their respective cut-offs, the mortality rate increased to 78.91%. The Cox regression model demonstrated that the predictive values of BE and lactate were mutually independent and additive. The 28-day mortality in shock patients admitted to ICU can be predicted by aBE, but BE and lactate deliver greater prognostic value, particularly when combined. The clinical value of our findings deserves further prospective evaluation.

show abstract

Course of lactate, pH and base excess for prediction of mortality in medical intensive care patients

Cited by 19 publications

References 22 publications

Explainable Machine Learning-Based Risk Prediction Model for In-Hospital Mortality after Continuous Renal Replacement Therapy Initiation

Explainable Machine Learning-Based Risk Prediction Model for In-Hospital Mortality after Continuous Renal Replacement Therapy Initiation

Higher Total Cholesterol Concentration May Be Associated with Better Cognitive Performance among Elderly Females

Admission Lactate Concentration, Base Excess, and Alactic Base Excess Predict the 28-Day Inward Mortality in Shock Patients

Contact Info

Product

Resources

About