A decrease in serum creatinine after ICU admission is associated with increased mortality

Development of Acute Kidney Injury Predictor Score in Intensive Care Unit Patients in Padang, Indonesia

OBJECTIVE

This study aims to develop and create a specialized acute kidney injury (AKI) predictor score for the intensive care unit (ICU) patients in Padang, Indonesia.

PATIENTS AND METHODS

This study was a prospective observational study on 352 ICU patients at three specialized hospitals in Padang City; Dr. M. Djamil General Hospital, Dr. Rasidin General Hospital, and Siti Rahmah Islamic Hospital. Data regarding demographics, clinical characteristics, laboratory results, and outcomes related to AKI were gathered. The factors that predict AKI were identified using multivariate logistic regression analysis to determine independent factors. The predictor scores were created using regression coefficients and then internally confirmed.

RESULTS

Out of a total of 352 patients, 128 individuals (36.4%) suffered from AKI. Factors that independently predict the occurrence of AKI include age over 60 years old, having a history of chronic kidney disease, having sepsis, need for vasopressors, and having creatinine level 1.3 mg/dL (IQR 1.0-1.8) upon admission to ICU. An area under the curve (AUC) of 0.85 (95% CI 0.80-0.90) indicated the strong performance of the constructed predictor score.

CONCLUSION

The constructed AKI predictor score a scale factor of 10, resulting in a range of 0-10 for the AKI predictor score. It demonstrates a good level of accuracy in predicting AKI in ICU patients in Padang. This score can be used by healthcare professionals to quickly identify and categorize individuals based on their risk level, facilitating timely intervention and personalized treatment.

Association between Red Blood Cell Distribution Width and Short-Term Mortality in Patients with Paralytic Intestinal Obstruction: Retrospective Data Analysis Based on the MIMIC-III Database

Objective

Elevated red cell distribution (RDW) has been reported to be associated with mortality in patients with acute pancreatitis and cholecystitis admitted to the intensive care unit (ICU). However, evidence for the relationship between RDW and paralytic intestinal obstruction is lacking. Therefore, the article aims to investigate the relationship between RDW and 28-day mortality of the patients with paralytic intestinal obstruction. Patients and Methods. This is a single-center retrospective study. Based on a particular screening criterion, 773 patients with paralytic intestinal obstruction were selected from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Indicators of the first 24 h into the ICU were used to analyze the relationship between RDW and 28-day death from paralytic intestinal obstruction by Kaplan-Meier (K-M) analysis, logistic regression analysis, and stratification analysis.

Results

The curve fitting exhibited a nonlinear relationship. The K-M curve showed that groups with higher RDW values had lower survival rates. The logistic regression analysis revealed that RDW increased with 28-day mortality in patients with paralytic intestinal obstruction in the fully adjusted model. In the fully adjusted model, OR value and 95% CI from the second to the third quantiles compared to the first quartile (reference group) were 1.89 (1.04, 3.44) and 3.29 (1.82, 5.93), respectively. The results of stratified analysis of each layer had the same trend as those of regression analysis, and the interaction results were not significant.

Conclusion

Elevated RDW was associated with increased 28-day mortality from paralytic intestinal obstruction in the ICU. This study can help to further explore the relationship between RDW and death in patients with paralytic intestinal obstruction.

A generalizable and interpretable model for mortality risk stratification of sepsis patients in intensive care unit

PURPOSE

This study aimed to construct a mortality model for the risk stratification of intensive care unit (ICU) patients with sepsis by applying a machine learning algorithm.

METHODS

Adult patients who were diagnosed with sepsis during admission to ICU were extracted from MIMIC-III, MIMIC-IV, eICU, and Zigong databases. MIMIC-III was used for model development and internal validation. The other three databases were used for external validation. Our proposed model was developed based on the Extreme Gradient Boosting (XGBoost) algorithm. The generalizability, discrimination, and validation of our model were evaluated. The Shapley Additive Explanation values were used to interpret our model and analyze the contribution of individual features.

RESULTS

A total of 16,741, 15,532, 22,617, and 1,198 sepsis patients were extracted from the MIMIC-III, MIMIC-IV, eICU, and Zigong databases, respectively. The proposed model had an area under the receiver operating characteristic curve (AUROC) of 0.84 in the internal validation, which outperformed all the traditional scoring systems. In the external validations, the AUROC was 0.87 in the MIMIC-IV database, better than all the traditional scoring systems; the AUROC was 0.83 in the eICU database, higher than the Simplified Acute Physiology Score III and Sequential Organ Failure Assessment (SOFA),equal to 0.83 of the Acute Physiology and Chronic Health Evaluation IV (APACHE-IV), and the AUROC was 0.68 in the Zigong database, higher than those from the systemic inflammatory response syndrome and SOFA. Furthermore, the proposed model showed the best discriminatory and calibrated capabilities and had the best net benefit in each validation.

CONCLUSIONS

The proposed algorithm based on XGBoost and SHAP-value feature selection had high performance in predicting the mortality of sepsis patients within 24 h of ICU admission.

Circulating protein and lipid markers of early sepsis diagnosis and prognosis: a scoping review

PURPOSE OF REVIEW

Sepsis is the extreme response to infection associated with high mortality, yet reliable biomarkers for its identification and stratification are lacking.

RECENT FINDINGS

Our scoping review of studies published from January 2017 to September 2022 that investigated circulating protein and lipid markers to inform non-COVID-19 sepsis diagnosis and prognosis identified interleukin (IL)-6, IL-8, heparin-binding protein (HBP), and angiopoietin-2 as having the most evidence. Biomarkers can be grouped according to sepsis pathobiology to inform biological data interpretation and four such physiologic processes include: immune regulation, endothelial injury and coagulopathy, cellular injury, and organ injury. Relative to proteins, the pleiotropic effects of lipid species' render their categorization more difficult. Circulating lipids are relatively less well studied in sepsis, however, low high-density lipoprotein (HDL) is associated with poor outcome.

SUMMARY

There is a lack of robust, large, and multicenter studies to support the routine use of circulating proteins and lipids for sepsis diagnosis or prognosis. Future studies will benefit from standardizing cohort design as well as analytical and reporting strategies. Incorporating biomarker dynamic changes and clinical data in statistical modeling may improve specificity for sepsis diagnosis and prognosis. To guide future clinical decisions at the bedside, point-of-care circulating biomarker quantification is needed.

Association between predialysis creatinine and mortality in acute kidney injury patients requiring dialysis

BACKGROUND

Creatinine is widely used to estimate renal function, but this is not practical in critical illness. Low creatinine has been associated with mortality in many clinical settings. However, the associations between predialysis creatinine level, Sepsis-related Organ Failure Assessment (SOFA) score, fluid overload, and mortality in acute kidney injury patients receiving dialysis therapy (AKI-D) has not been fully addressed.

METHODS

We extracted data for AKI-D patients in the eICU and MIMIC databases. We conducted a retrospective observational cohort study using the eICU dataset. The study cohort was divided into the high-creatine group and the low-creatinine group by the median value (4 mg/dL). The baseline patient information included demographic data, laboratory tests, medications, and comorbid conditions. The independent association of creatinine level with 30-day mortality was examined using multivariate logistic regression analysis. In sensitivity analyses, the associations between creatinine, SOFA score, and mortality were analyzed in patients with or without fluid overload. We also carried out an external validity using the MIMIC dataset.

RESULTS

In all 1,600 eICU participants, the 30-day mortality rate was 34.2%. The crude overall mortality rate in the low-creatinine group (44.9%) was significantly higher than that in the high-creatinine group (21.9%; P < 0.001). In the fully adjusted models, the low-creatinine group was associated with a higher risk of 30-day mortality (odds ratio, 1.77; 95% confidence interval, 1.29-2.42; P < 0.001) compared with the high-creatinine group. The low-creatinine group had higher SOFA and nonrenal SOFA scores. In sensitivity analyses, the low-creatinine group had a higher 30-day mortality rate with regard to the BMI or albumin level. Fluid overloaded patients were associated with a significantly worse survival in the low-creatinine group. The results were consistent when assessing the external validity using the MIMIC dataset.

CONCLUSIONS

In patients with AKI-D, lower predialysis creatinine was associated with increased mortality risk. Moreover, the mortality rate was substantially higher in patients with lower predialysis creatinine with concomitant elevation of fluid overload status.

Admission creatinine is associated with poor outcomes in burn patients

INTRODUCTION

Renal failure is the most common organ failure in severely burned patients. However, defining acute kidney injury and renal failure is very challenging. This study was designed to determine the relationship between a biomarker commonly measured on admission, serum creatinine, and outcomes in burn patients.

METHODS

We conducted a retrospective cohort study of adult patients (≥ 18 years) with a burn ≥ 5% total body surface area (TBSA) and a serum creatinine level measured within the first 72 h after injury. Patients were admitted over an 11-year period and divided into two groups based on creatinine levels measured within the first 72 h after injury. Patients were categorized in the high creatinine group if they had a measured creatinine ≥107 μmol/L (≥1.21 mg/dL); this value was chosen as the threshold for creatinine based on our institution's reference range. Clinical outcomes included morbidities, hospital length of stay, and mortality. Multivariable logistic regression was used to model the association between high admission creatinine and each outcome, adjusting for patient and injury characteristics.

RESULTS

We studied 923 patients, mean age 47 ± 18 years and median 13% (IQR 8-24) TBSA burned. There were 718 patients categorized with low admission creatinine and 205 patients with high admission creatinine. After adjustment for patient and injury characteristics, high admission creatinine was associated with a significantly higher rate of sepsis (OR 3.44; 95% CI 2.11-5.59), pneumonia (OR 4.56; 95% CI 1.8-11.53), and mortality (OR 3.59; 95% CI 1.91-6.75).

CONCLUSIONS

Elevated creatinine on admission is associated with an increased risk of morbidity and mortality. We suggest that admission creatinine can be used as a "red flag" to identify patients at a higher risk for poor outcomes.

Data analytics and clinical feature ranking of medical records of patients with sepsis

Background

Sepsis is a life-threatening clinical condition that happens when the patient’s body has an excessive reaction to an infection, and should be treated in one hour. Due to the urgency of sepsis, doctors and physicians often do not have enough time to perform laboratory tests and analyses to help them forecast the consequences of the sepsis episode. In this context, machine learning can provide a fast computational prediction of sepsis severity, patient survival, and sequential organ failure by just analyzing the electronic health records of the patients. Also, machine learning can be employed to understand which features in the medical records are more predictive of sepsis severity, of patient survival, and of sequential organ failure in a fast and non-invasive way.

Dataset and methods

In this study, we analyzed a dataset of electronic health records of 364 patients collected between 2014 and 2016. The medical record of each patient has 29 clinical features, and includes a binary value for survival, a binary value for septic shock, and a numerical value for the sequential organ failure assessment (SOFA) score. We disjointly utilized each of these three factors as an independent target, and employed several machine learning methods to predict it (binary classifiers for survival and septic shock, and regression analysis for the SOFA score). Afterwards, we used a data mining approach to identify the most important dataset features in relation to each of the three targets separately, and compared these results with the results achieved through a standard biostatistics approach.

Results and conclusions

Our results showed that machine learning can be employed efficiently to predict septic shock, SOFA score, and survival of patients diagnoses with sepsis, from their electronic health records data. And regarding clinical feature ranking, our results showed that Random Forests feature selection identified several unexpected symptoms and clinical components as relevant for septic shock, SOFA score, and survival. These discoveries can help doctors and physicians in understanding and predicting septic shock. We made the analyzed dataset and our developed software code publicly available online.

Supplementary Information

The online version contains supplementary material available at (10.1186/s13040-021-00235-0).

The effect of admission and pre-admission serum creatinine as baseline to assess incidence and outcomes of acute kidney injury in acute medical admissions

BACKGROUND

Acute kidney injury (AKI) in hospital-admitted patients is a common complication associated with increased mortality. The diagnosis of AKI relies on the ascertainment of peak increase in serum creatinine (SCr). This study evaluated the incidence of AKI using the increase from mean 7-365 days pre-admission (AKIpre) and admission (AKIadm) SCr levels, and examined the associations of AKI and changes in SCr levels with all-cause mortality.

METHODS

A total of 2436 patients admitted to a tertiary hospital were recruited and followed-up for a median of 47.70 (interquartile range 18.20) months. AKI incidence and severity were defined according to the Kidney Disease: Improving Global Outcomes-AKI Guidelines. Follow-up data were collected from the Hospital Episode Statistics and Office of National Statistics. Mortality was evaluated during a short- (30 days), mid- (1 year) and long-term (4 years) period.

RESULTS

No difference in the AKI rates using AKIpre and AKIadm (12.5% versus 12.2%; P = 0.695) or in the AKI severity (P = 0.261) was evident. Agreement between the two definitions was modest (Kappa-statistic = 0.596, P < 0.001). Patients with AKIpre or AKIadm had increased all-cause mortality compared with those without AKI during all follow-up periods. In fully adjusted regression analysis, AKIpre [hazard ratio (HR) = 2.226, 95% confidence interval (CI) 1.140-4.347; P = 0.027] and AKIadm (HR = 2.105, 95% CI 1.090-4.064; P = 0.027) remained associated with 30-day mortality. Results for the 1- and 4-year periods were similar. Increases of >4.00 μmol/L and >6.06% from pre-admission or >6.00 μmol/L and >17.24% from admission SCr levels presented increased mortality risk during follow-up.

CONCLUSIONS

Use of admission or pre-admission SCr provides similar incidence rates, but they diagnose different sets of patients. Even minor increases in SCr, below those required for the classification of AKI, were associated with increased mortality. These findings can help the clinicians to identify patients at higher risk for adverse outcomes.

A statistically rigorous deep neural network approach to predict mortality in trauma patients admitted to the intensive care unit

BACKGROUND

Trauma patients admitted to critical care are at high risk of mortality because of their injuries. Our aim was to develop a machine learning-based model to predict mortality using Fahad-Liaqat-Ahmad Intensive Machine (FLAIM) framework. We hypothesized machine learning could be applied to critically ill patients and would outperform currently used mortality scores.

METHODS

The current Deep-FLAIM model evaluates the statistically significant risk factors and then supply these risk factors to deep neural network to predict mortality in trauma patients admitted to the intensive care unit (ICU). We analyzed adult patients (≥18 years) admitted to the trauma ICU in the publicly available database Medical Information Mart for Intensive Care III version 1.4. The first phase selection of risk factor was done using Cox-regression univariate and multivariate analyses. In the second phase, we applied deep neural network and other traditional machine learning models like Linear Discriminant Analysis, Gaussian Naïve Bayes, Decision Tree Model, and k-nearest neighbor models.

RESULTS

We identified a total of 3,041 trauma patients admitted to the trauma surgery ICU. We observed that several clinical and laboratory-based variables were statistically significant for both univariate and multivariate analyses while others were not. With most significant being serum anion gap (hazard ratio [HR], 2.46; 95% confidence interval [CI], 1.94-3.11), sodium (HR, 2.11; 95% CI, 1.61-2.77), and chloride (HR, 2.11; 95% CI, 1.69-2.64) abnormalities on laboratories, while clinical variables included the diagnosis of sepsis (HR, 2.03; 95% CI, 1.23-3.37), Quick Sequential Organ Failure Assessment score (HR, 1.52; 95% CI, 1.32-3.76). And Systemic Inflammatory Response Syndrome criteria (HR. 1.41; 95% CI, 1.24-1.26). After we used these clinically significant variables and applied various machine learning models to the data, we found out that our proposed DNN outperformed all the other methods with test set accuracy of 92.25%, sensitivity of 79.13%, and specificity of 94.16%; positive predictive value, 66.42%; negative predictive value, 96.87%; and area under the curve of the receiver-operator curve of 0.91 (1.45-1.29).

CONCLUSION

Our novel Deep-FLAIM model outperformed all other machine learning models. The model is easy to implement, user friendly and with high accuracy.

LEVEL OF EVIDENCE

Prognostic study, level II.

Outcomes of early and reversible renal impairment in patients with ST segment elevation myocardial infarction undergoing percutaneous coronary intervention

Objective:

Acute kidney injury (AKI) is a frequent complication in patients with ST segment elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention (PCI). While AKI occurring post-PCI has been well studied, the incidence and clinical significance of early renal impairment evident on hospital admission prior to PCI and which resolves towards discharge has not been investigated.

Methods:

We retrospectively studied 2339 STEMI patients treated with primary PCI. The incidence of renal impairment and in-hospital complications as well as short and long-term mortality were compared between patients who did not develop renal impairment, patients who developed post-PCI AKI and those who presented with renal impairment on admission but improved their renal function during hospitalization (improved renal function). Improved renal function was defined as continuous and gradual decrease of ⩾ 0.3 mg/dL in serum creatinine levels obtained at hospital admission.

Results:

One hundred and nineteen patients (5%) had improved renal function and 230 patients (10%) developed post-PCI AKI. When compared with patients with no renal impairment, improved renal function and post-PCI AKI were associated with more complications and adverse events during hospitalization as well as higher 30-day mortality. Long-term mortality was significantly higher among those with post-PCI AKI (63/230, 27%) following STEMI than those without renal impairment (104/1990, 5%; p&lt;0.001), but there was no significant difference in long term mortality between patients with no renal impairment and those with improved renal function (5% vs. 7.5%, p=0.17).

Conclusion:

In STEMI patients undergoing primary PCI, the presence of renal impairment prior to PCI which resolves towards discharge is not uncommon and is associated with adverse short-term outcomes but better long-term outcomes compared with post-PCI AKI.

Should we pay more attention to low creatinine levels?

A review is made of the basic aspects of creatine/creatinine metabolism and the close relationship between creatinine and muscle mass, which makes the former a biochemical marker of the latter. Emphasis is placed on the current prognostic value of both the low urinary excretion of creatinine and low serum creatinine levels in different clinical settings in which sarcopenia probably plays a significant role in morbidity and mortality.

Serum creatinine trajectories in real-world hospitalized patients: clinical context and short-term mortality

Fluctuations in serum creatinine (SCr) during hospitalization may provide additional prognostic value beyond baseline renal function. This study aimed to identify groups of patients with distinct creatinine trajectories over hospital stay and assess them in terms of clinical characteristics and short-term mortality. This retrospective study included 35 853 unique adult admissions to a tertiary referral center between January 2012 and January 2016 with at least three SCr measurements within the first 9 days of stay. Individual SCr courses were determined using linear regression or linear-splines model and grouped into clusters. SCr trajectories were described as median SCr courses within clusters. Almost half of the patients presented with changing, mainly declining SCr concentration during hospitalization. In comparison to patients with an increase in SCr, those with a significant decline were younger, more often admitted via the emergency department, more often required a higher level of care, had fewer comorbidities and the more pronounced the fall in SCr, the greater the observed difference. Regardless of baseline renal function, an increase in SCr was related to the highest in-hospital mortality risk among compared clusters. Also, patients with normal renal function at admission followed by decreasing SCr were at higher risk of inpatient death, but lower 90-day postdischarge mortality than patients with a stable SCr. Acute changes in inpatient SCr convey important prognostic information and can only be interpreted by looking at their evolution over time. Recognizing underlying causes and providing adequate care is crucial for improving adverse prognosis.

Delayed Antibiotic Therapy and Organ Dysfunction in Critically Ill Septic Patients in the Emergency Department

Background: We investigated the effect of antibiotic timing on outcomes based on changes in surrogate markers of organ failure, including platelet, serum bilirubin, serum creatinine levels, and the PaO₂/FiO₂ (P/F) ratio. Methods: This was a single-center, retrospective observational study of critically ill septic patients who presented to the emergency department (ED). The study period extended from August 2008 to September 2016. The primary outcomes included changes in platelet, serum bilirubin, serum creatinine levels, and the P/F ratio (δ-platelet, δ-serum bilirubin, δ-serum creatinine, and δ-P/F ratio were calculated as values measured on Day 3; values measured at ED enrollment). A multivariable linear regression model was developed to assess variables related to outcomes (δ-platelet, δ-serum bilirubin, δ-serum creatinine, and δ-P/F ratio). Results: We analyzed 1784 patients who met the inclusion criteria. The overall 28-day mortality was 14% (n = 256/1784). On multivariable linear regression analysis, the hourly delay in antibiotic therapy was significantly associated with a decrease in δ-platelet count (coefficient, −1.741; standard error, 0.740; p = 0.019), and an increase in δ-serum bilirubin (coefficient, 0.054; standard error, 0.021; p = 0.009). In contrast, it was not associated with δ-creatinine (coefficient, 0.008; standard error, 0.010; p = 0.434) or the δ-P/F ratio (coefficient, −0.797; standard error, 1.858; p = 0.668). Conclusion: The hourly delay of antibiotic therapy was associated with decreased platelet count and increased serum bilirubin concentration in critically ill septic patients during the first three days of ED admission.