Development and Validation of a Prediction Model for Survival in Diabetic Patients With Acute Kidney Injury

Vitamin D deficiency may increase the risk of acute kidney injury in patients with diabetes and predict a poorer outcome in patients with acute kidney injury

BACKGOUND

People with diabetes are much more likely to develop acute kidney injury (AKI) than people without diabetes. Low 25-hydroxy-vitamin D [25(OH)D] concentrations increased the risk of AKI in specific populations. Few studies have explored the relationship between the 25(OH)D level and AKI in patients with diabetes. We conducted this study to investigate the relationship between the plasma level of 25(OH)D and the risk of AKI in patients with diabetes, and to evaluate whether the 25(OH)D level could be a good prognostic marker for AKI progression.

METHODS

A total of 347 patients with diabetes were retrospectively reviewed. The primary endpoint was the first event of AKI. The secondary endpoint is need-of-dialysis. AKI patients were further followed up for 6 months with the composite endpoint of end-stage renal disease (ESRD) or all-cause death. Kaplan-Meier survival analysis and Cox proportional hazards models were used.

RESULTS

During a median follow-up of 12 weeks (12.3 ± 6.7), 105 incident AKI were identified. The middle and high tertiles of baseline 25(OH)D levels were associated with a significantly decreased risk of AKI and dialysis compared to the low tertile group (HR = 0.25, 95% CI 0.14-0.46; HR = 0.24, 95% CI 0.13-0.44, respectively, for AKI; HR = 0.15; 95% CI 0.05-0.46; HR = 0.12; 95% CI 0.03-0.42, respectively, for dialysis). Sensitivity analysis revealed similar trends after excluding participants without history of CKD. Furthermore, AKI patients with 25(OH)D deficiency were associated with a higher risk for ESRD or all-cause death (HR, 4.24; 95% CI, 1.80 to 9.97, P < 0.001).

CONCLUSION

A low 25 (OH) vitamin D is associated with a higher risk of AKI and dialysis in patients with diabetes. AKI patients with 25(OH)D deficiency were associated with a higher risk for ESRD or all-cause death.

A dynamic model to predict early occurrence of acute kidney injury in ICU hospitalized cirrhotic patients: a MIMIC database analysis

BACKGROUND

This study aimed to develop a tool for predicting the early occurrence of acute kidney injury (AKI) in ICU hospitalized cirrhotic patients.

METHODS

Eligible patients with cirrhosis were identified from the Medical Information Mart for Intensive Care database. Demographic data, laboratory examinations, and interventions were obtained. After splitting the population into training and validation cohorts, the least absolute shrinkage and selection operator regression model was used to select factors and construct the dynamic online nomogram. Calibration and discrimination were used to assess nomogram performance, and clinical utility was evaluated by decision curve analysis (DCA).

RESULTS

A total of 1254 patients were included in the analysis, and 745 developed AKI. The mean arterial pressure, white blood cell count, total bilirubin level, Glasgow Coma Score, creatinine, heart rate, platelet count and albumin level were identified as predictors of AKI. The developed model had a good ability to differentiate AKI from non-AKI, with AUCs of 0.797 and 0.750 in the training and validation cohorts, respectively. Moreover, the nomogram model showed good calibration. DCA showed that the nomogram had a superior overall net benefit within wide and practical ranges of threshold probabilities.

CONCLUSIONS

The dynamic online nomogram can be an easy-to-use tool for predicting the early occurrence of AKI in critically ill patients with cirrhosis.

Development and validation of a nomogram of all-cause mortality in adult Americans with diabetes

This study aimed to develop and validate a predictive model of all-cause mortality risk in American adults aged ≥ 18 years with diabetes. 7918 participants with diabetes were enrolled from the National Health and Nutrition Examination Survey (NHANES) 1999-2016 and followed for a median of 96 months. The primary study endpoint was the all-cause mortality. Predictors of all-cause mortality included age, Monocytes, Erythrocyte, creatinine, Nutrition Risk Index (NRI), neutrophils/lymphocytes (NLR), smoking habits, alcohol consumption, cardiovascular disease (CVD), urinary albumin excretion rate (UAE), and insulin use. The c-index was 0.790 (95% CI 0.779-0.801, P < 0.001) and 0.792 (95% CI: 0.776-0.808, P < 0.001) for the training and validation sets, respectively. The area under the ROC curve was 0.815, 0.814, 0.827 and 0.812, 0.818 and 0.829 for the training and validation sets at 3, 5, and 10 years of follow-up, respectively. Both calibration plots and DCA curves performed well. The model provides accurate predictions of the risk of death for American persons with diabetes and its scores can effectively determine the risk of death in outpatients, providing guidance for clinical decision-making and predicting prognosis for patients.

Development and validation of short-term renal prognosis prediction model in diabetic patients with acute kidney injury

OBJECTIVE

Diabetes is a major cause of the progression of acute kidney injury (AKI). Few prediction models have been developed to predict the renal prognosis in diabetic patients with AKI so far. The aim of this study was to develop and validate a predictive model to identify high-risk individuals with non-recovery of renal function at 90 days in diabetic patients with AKI.

METHODS

Demographic data and related laboratory indicators of diabetic patients with AKI in the First Affiliated Hospital of Guangxi Medical University from January 31, 2012 to January 31, 2022 were retrospectively analysed, and patients were followed up to 90 days after AKI diagnosis. Based on the results of Logistic regression, a model predicting the risk of non-recovery of renal function at 90 days in diabetic patients with AKI was developed and internal validated. Consistency index (C-index), calibration curve, and decision curve analysis were used to evaluate the differentiation, accuracy, and clinical utility of the prediction model, respectively.

RESULTS

A total of 916 diabetic patients with AKI were enrolled, with a male to female ratio of 2.14:1. The rate of non-recovery of renal function at 90 days was 66.8% (612/916). There were 641 in development cohort and 275 in validation cohort (ration of 7:3). In the development cohort, a prediction model was developed based on the results of Logistic regression analysis. The variables included in the model were: diabetes duration (OR = 1.022, 95% CI  1.012-1.032), hypertension (OR = 1.574, 95% CI 1.043-2.377), chronic kidney disease (OR = 2.241, 95% CI 1.399-3.591), platelet (OR = 0.997, 95% CI 0.995-1.000), 25-hydroxyvitamin D3 (OR = 0.966, 95% CI  0.956-0.976), postprandial blood glucose (OR = 1.104, 95% CI 1.032-1.181), discharged serum creatinine (OR = 1.003, 95% CI 1.001-1.005). The C-indices of the prediction model were 0.807 (95% CI 0.738-0.875) and 0.803 (95% CI 0.713-0.893) in the development and validation cohorts, respectively. The calibration curves were all close to the straight line with slope 1. The decision curve analysis showed that in a wide range of threshold probabilities.

CONCLUSION

A prediction model was developed to help predict short-term renal prognosis of diabetic patients with AKI, which has been verified to have good differentiation, calibration degree and clinical practicability.

Application of interpretable machine learning for early prediction of prognosis in acute kidney injury

Background

This study aimed to develop an algorithm using the explainable artificial intelligence (XAI) approaches for the early prediction of mortality in intensive care unit (ICU) patients with acute kidney injury (AKI).

Methods

This study gathered clinical data with AKI patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) in the US between 2008 and 2019. All the data were further randomly divided into a training cohort and a validation cohort. Seven machine learning methods were used to develop the models for assessing in-hospital mortality. The optimal model was selected based on its accuracy and area under the curve (AUC). The SHapley Additive exPlanation (SHAP) values and Local Interpretable Model-Agnostic Explanations (LIME) algorithm were utilized to interpret the optimal model.

Results

A total of 22,360 patients with AKI were finally enrolled in this study (median age, 69.5 years; female, 42.8%). They were randomly split into a training cohort (16770, 75%) and a validation cohort (5590, 25%). The eXtreme Gradient Boosting (XGBoost) model achieved the best performance with an AUC of 0.890. The SHAP values showed that Glasgow Coma Scale (GCS), blood urea nitrogen, cumulative urine output on Day 1 and age were the top 4 most important variables contributing to the XGBoost model. The LIME algorithm was used to explain the individualized predictions.

Conclusions

Machine-learning models based on clinical features were developed and validated with great performance for the early prediction of a high risk of death in patients with AKI.

Influence of Red Blood Cell Distribution Width on All-Cause Death in Critical Diabetic Patients with Acute Kidney Injury

OBJECTIVE

To explore the relationship between red blood cell distribution width (RDW) and all-cause death in critical diabetic patients with acute kidney injury (AKI).

METHODS

The clinical data of critical diabetic patients with AKI in MIMIC-III database were analyzed retrospectively. According to the survival status of 28-day after AKI and levels of RDW, patients were divided into survival and death groups, high RDW (RDW > 15.3%) and low RDW groups (RDW ≤ 15.3%). Kaplan-Meier curves were used to compare the survival rates of diabetic patients with AKI in different RDW and AKI stages, and Cox regression analysis was used to evaluate the risk factors of 28-day all-cause death in critical diabetic patients with AKI.

RESULTS

A total of 5200 patients with critical diabetic patients with AKI were included in this study with the male to female ratio of 1.53:1. The mean follow-up time was 24.97 ± 7.14 days, and the 28-day all-cause mortality was 17.9% (931/5200). Age, RDW, blood urea nitrogen, serum creatinine, lactic acid, proportion of AKI stage, sepsis and respiratory failure in the death group were higher than those in the survival group, while mean arterial pressure (MAP) and red blood cell count were lower than those in the survival group. Kaplan-Meier analysis showed that the 28-day survival rate of the high RDW group was significantly lower than that of the low RDW group (log-rank χ ² = 9.970, P = 0.002). Multivariate Cox regression analysis showed that advanced age (HR = 1.042, 95% CI = 1.021-1.063), decreased MAP (HR = 0.984, 95% CI = 0.969-0.998), stage 3 AKI (HR = 3.318, 95% CI = 1.598-6.890) and increased RDW (HR = 1.255, 95% CI = 1.123-1.403) were independent risk factors of 28-day all-cause death in critical diabetic patients with AKI (P < 0.05).

CONCLUSION

High level of RDW is an important risk factor of all-cause death in critical diabetic patients with AKI, and it may be used as a valuable index to classify the mortality.