A Predictive Model Based on Inflammatory and Coagulation Indicators for Sepsis-Induced Acute Kidney Injury

Development and external validation of a nomogram for the early prediction of acute kidney injury in septic patients: a multicenter retrospective clinical study

Background and purpose: Acute kidney injury (AKI) is a common serious complication in sepsis patients with a high mortality rate. This study aimed to develop and validate a predictive model for sepsis associated acute kidney injury (SA-AKI). Methods: In our study, we retrospectively constructed a development cohort comprising 733 septic patients admitted to eight Grade-A tertiary hospitals in Shanghai from January 2021 to October 2022. Additionally, we established an external validation cohort consisting of 336 septic patients admitted to our hospital from January 2017 to December 2019. Risk predictors were selected by LASSO regression, and a corresponding nomogram was constructed. We evaluated the model's discrimination, precision and clinical benefit through receiver operating characteristic (ROC) curves, calibration plots, decision curve analysis (DCA) and clinical impact curves (CIC) in both internal and external validation. Results: AKI incidence was 53.2% in the development cohort and 48.2% in the external validation cohort. The model included five independent indicators: chronic kidney disease stages 1 to 3, blood urea nitrogen, procalcitonin, D-dimer and creatine kinase isoenzyme. The AUC of the model in the development and validation cohorts was 0.914 (95% CI, 0.894-0.934) and 0.923 (95% CI, 0.895-0.952), respectively. The calibration plot, DCA, and CIC demonstrated the model's favorable clinical applicability. Conclusion: We developed and validated a robust nomogram model, which might identify patients at risk of SA-AKI and promising for clinical applications.

Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury

OBJECTIVES

This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms.

METHODS

Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation (n = 2440) and development (n = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP).

RESULTS

A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774-0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis.

CONCLUSIONS

The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction.

Development and validation of an early acute kidney injury risk prediction model for patients with sepsis in emergency departments

In this study, we aimed to develop and validate a nomogram to predicting the risk of sepsis-associated acute kidney injury (SA-AKI) in patients admitted to emergency departments (EDs). We randomly divided a retrospective dataset of 391 patients with sepsis into a 294-person training cohort and a 97-person validation cohort, and developed three predictive models using multivariate logistic regression analysis and clinical insight. No difference was observed between the three models using the DeLong test and Model 3 was selected as the risk prediction model based on the principle of least inclusion indicators. The use of vasopressor drugs, patient age, platelet count, procalcitonin, and D-dimer levels were included. The training and validation cohorts had a consistency index of 0.832 and 0.866, respectively, indicating high accuracy and stability in predicting SA-AKI risk. The area under the receiver operating characteristic curve was 0.832, showing excellent discrimination. The calibration curves for the training and validation cohorts showed excellent calibration. The decision curve and clinical impact curve analyses showed that the net clinical benefit of using the nomogram was greatest over a probability threshold of 0.05-0.90. In addition, the model showed moderate validity in predicting the 30-day survival and the incidence of major adverse renal events within 30 days. The nomogram developed for SA-AKI risk assessment in patients in EDs showed good discriminability and clinical utility. It can provide a theoretical basis for emergency physicians to prevent SA-AKI.

A promising application of kidney-specific cell-free DNA methylation markers in real-time monitoring sepsis-induced acute kidney injury

Sepsis-induced acute kidney injury (SI-AKI) is a common clinical syndrome that is associated with high mortality and morbidity. Effective timely detection may improve the outcome of SI-AKI. Kidney-derived cell-free DNA (cfDNA) may provide new insight into understanding and identifying SI-AKI. Plasma cfDNA from 82 healthy individuals, 7 patients with sepsis non-acute kidney injury (SN-AKI), and 9 patients with SI-AKI was subjected to genomic methylation sequencing. We deconstructed the relative contribution of cfDNA from different cell types based on cell-specific methylation markers and focused on exploring the association between kidney-derived cfDNA and SI-AKI.Based on the deconvolution of the cfDNA methylome: SI-AKI patients displayed the elevated cfDNA concentrations with an increased contribution of kidney epithelial cells (kidney-Ep) DNA; kidney-Ep derived cfDNA achieved high accuracy in distinguishing SI-AKI from SN-AKI (AUC = 0.92, 95% CI 0.7801-1); the higher kidney-ep cfDNA concentrations tended to correlate with more advanced stages of SI-AKI; strikingly, SN-AKI patients with potential kidney damage unmet by SI-AKI criteria showed higher levels of kidney-Ep derived cfDNA than healthy individuals. The autonomous screening of kidney-Ep (n = 24) and kidney endothelial (kidney-Endo, n = 12) specific methylation markers indicated the unique identity of kidney-Ep/kidney-Endo compared with other cell types, and its targeted assessment reproduced the main findings of the deconvolution of the cfDNA methylome. Our study first demonstrates that kidney-Ep- and kidney-Endo-specific methylation markers can serve as a novel marker for SI-AKI emergence, supporting further exploration of the utility of kidney-specific cfDNA methylation markers in the study of SI-AKI.

Heterogeneity in the definition of major adverse kidney events: a scoping review

Acute kidney injury (AKI) is associated with persistent renal dysfunction, the receipt of dialysis, dialysis dependence, and mortality. Accordingly, the concept of major adverse kidney events (MAKE) has been adopted as an endpoint for assessing the impact of AKI. However, applied criteria or observation periods for operationalizing MAKE appear to vary across studies. To evaluate this heterogeneity for MAKE evaluation, we performed a systematic scoping review of studies that employed MAKE as an AKI endpoint. Four major academic databases were searched, and we identified 122 studies with increasing numbers over time. We found marked heterogeneity in applied criteria and observation periods for MAKE across these studies, with some even lacking a description of criteria. Moreover, 13 different observation periods were employed, with 30 days and 90 days as the most common. Persistent renal dysfunction was evaluated by estimated glomerular filtration rate (34%) or serum creatinine concentration (48%); however, 37 different definitions for this component were employed in terms of parameters, cut-off criteria, and assessment periods. The definition for the dialysis component also showed significant heterogeneity regarding assessment periods and duration of dialysis requirement (chronic vs temporary). Finally, MAKE rates could vary by 7% [interquartile range: 1.7-16.7%] with different observation periods or by 36.4% with different dialysis component definitions. Our findings revealed marked heterogeneity in MAKE definitions, particularly regarding component assessment and observation periods. Dedicated discussion is needed to establish uniform and acceptable standards to operationalize MAKE in terms of selection and applied criteria of components, observation period, and reporting criteria for future trials on AKI and related conditions.

Artificial intelligence and machine learning's role in sepsis-associated acute kidney injury

Sepsis-associated acute kidney injury (SA-AKI) is a serious complication in critically ill patients, resulting in higher mortality, morbidity, and cost. The intricate pathophysiology of SA-AKI requires vigilant clinical monitoring and appropriate, prompt intervention. While traditional statistical analyses have identified severe risk factors for SA-AKI, the results have been inconsistent across studies. This has led to growing interest in leveraging artificial intelligence (AI) and machine learning (ML) to predict SA-AKI better. ML can uncover complex patterns beyond human discernment by analyzing vast datasets. Supervised learning models like XGBoost and RNN-LSTM have proven remarkably accurate at predicting SA-AKI onset and subsequent mortality, often surpassing traditional risk scores. Meanwhile, unsupervised learning reveals clinically relevant sub-phenotypes among diverse SA-AKI patients, enabling more tailored care. In addition, it potentially optimizes sepsis treatment to prevent SA-AKI through continual refinement based on patient outcomes. However, utilizing AI/ML presents ethical and practical challenges regarding data privacy, algorithmic biases, and regulatory compliance. AI/ML allows early risk detection, personalized management, optimal treatment strategies, and collaborative learning for SA-AKI management. Future directions include real-time patient monitoring, simulated data generation, and predictive algorithms for timely interventions. However, a smooth transition to clinical practice demands continuous model enhancements and rigorous regulatory oversight. In this article, we outlined the conventional methods used to address SA-AKI and explore how AI and ML can be applied to diagnose and manage SA-AKI, highlighting their potential to revolutionize SA-AKI care.

The role of thromboinflammation in acute kidney injury among patients with septic coagulopathy

Inflammation and coagulation are critical self-defense mechanisms for mitigating infection that can nonetheless induce tissue injury and organ dysfunction. In severe cases, like sepsis, a dysregulated thromboinflammatory response may result in multiorgan dysfunction. Sepsis-associated acute kidney injury (AKI) is a significant contributor to patient morbidity and mortality. The connection between AKI and thromboinflammation is largely due to unique aspects of the renal vasculature. Specifically, the interaction between blood cells with the endothelial, glomerular, and peritubular capillary systems during thromboinflammation reduces oxygen supply to tubular epithelial cells. Previous studies have focused on tubular epithelial cell damage due to hypoxia, oxidative stress, and nephrotoxins. Although these factors are pivotal in acute tubular injury or necrosis, recent studies have demonstrated that AKI in sepsis encompasses a mixture of tubular and glomerular damage subtypes. In cases of sepsis-induced coagulopathy, thromboinflammation within the glomerulus and peritubular capillaries is an important pathogenic mechanism for AKI. Unfortunately, and despite the use of renal replacement therapy, the development of AKI in sepsis continues to be associated with high morbidity, mortality, and clinical challenges requiring alternative approaches. This review introduces the important role of thromboinflammation in AKI pathogenesis and details innovative vascular-targeting therapeutic strategies.

Impact of early heparin therapy on mortality in critically ill patients with sepsis associated acute kidney injury: a retrospective study from the MIMIC-IV database

Background: Inflammatory-coagulation dysfunction plays an increasingly important role in sepsis associated acute kidney injury (SAKI). This study aimed to investigate whether early heparin therapy improves survival in patients with SAKI. Methods: Patients with SAKI were identified from the Medical Information Mart for Intensive Care-IV database. The patients were divided into two groups: those who received heparin subcutaneously within 48 h after intensive care unit (ICU) admission and the control group, who received no heparin. The primary endpoint was ICU mortality, the secondary outcomes were 7-day, 14-day, 28-day, and hospital mortality. Propensity score matching (PSM), marginal structural Cox model (MSCM), and E-value analyses were performed. Results: The study included 5623 individuals with SAKI, 2410 of whom received heparin and 3213 of whom did not. There were significant effects on ICU and 28-day mortality in the overall population with PSM. MSCM further reinforces the efficacy of heparin administration reduces ICU mortality in the general population. Stratification analysis with MSCM showed that heparin administration was associated with decreased ICU mortality at various AKI stages. Heparin use was also associated with reduced 28-day mortality in patients with only female, age >60 years, and AKI stage 3, with HRs of 0.79, 0.77, and 0.60, respectively (p < 0.05). E-value analysis suggests robustness to unmeasured confounding. Conclusion: Early heparin therapy for patients with SAKI decreased ICU mortality. Further analysis demonstrated that heparin therapy was associated with reduced 28-day mortality rate in patients only among female, age > 60 years and AKI stage 3.

Relationship between serum sodium level and sepsis-induced coagulopathy

Purpose

A discussion about the correlation between the level of serum sodium and sepsis-induced coagulopathy (SIC).

Materials and methods

A retrospective analysis was conducted on sepsis patients who were admitted to the Intensive Care Unit (ICU) of Nanjing Drum Tower Hospital from January 2021 to December 2022. Based on the presence of coagulation disorders, the patients were divided into two groups: sepsis-induced coagulopathy (SIC) and non-sepsis-induced coagulopathy (non-SIC) groups. We recorded demographic characteristics and laboratory indicators at the time of ICU admission, and analyzed relationship between serum sodium level and SIC.

Results

One hundred and twenty-five patients with sepsis were enrolled, among which, the SIC and the non-SIC groups included 62 and 63 patients, respectively. Compared to patients in the non-SIC group, the level of serum sodium of those in the SIC was significantly higher (p < 0.001). Multi-factor logistic regression showed serum sodium level was independently associated with SIC (or = 1.127, p = 0.001). Pearson's correlation analysis indicated that the higher the serum sodium level, the significantly higher the SIC score was (r = 0.373, p < 0.001). Additionally, the mortality rate of patients with sepsis in the ICU were significantly correlated with increased serum sodium levels (p = 0.014).

Conclusion

An increase in serum sodium level was independently associated with an increased occurrence of SIC and also associated with the poor prognosis for patients with sepsis.

Development of a nomogram model for the early prediction of sepsis-associated acute kidney injury in critically ill patients

Sepsis-associated acute kidney injury is a common complication of sepsis, but it is difficult to predict sepsis-associated acute kidney injury. In this retrospective observational study, adult septic patients were recruited from the MIMIC-III database as the training cohort (n = 4764) and from Xiangya Hospital (n = 1568) and Zhang's database as validation cohorts. We identified eleven predictors with seven independent risk predictors of sepsis-associated acute kidney injury [fluid input_day1 ≥ 3390 ml (HR hazard ratio 1.42), fluid input_day2 ≥ 2734 ml (HR 1.64), platelet_min_day5 ≤ 224.2 × 109/l (HR 0.86), length of ICU stay ≥ 2.5 days (HR 1.24), length of hospital stay ≥ 5.8 days (HR 1.18), Bun_max_day1 ≥ 20 mmol/l (HR 1.20), and mechanical ventilation time ≥ 96 h (HR 1.11)] by multivariate Cox regression analysis, and the eleven predictors were entered into the nomogram. The nomogram model showed a discriminative ability for estimating sepsis-associated acute kidney injury. These results indicated that clinical parameters such as excess input fluid on the first and second days after admission and longer mechanical ventilation time could increase the risk of developing sepsis-associated acute kidney injury. With our study, we built a real-time prediction model for potentially forecasting acute kidney injury in septic patients that can help clinicians make decisions as early as possible to avoid sepsis-associated acute kidney injury.