Development of a novel score to predict the risk of acute kidney injury in patient with acute myocardial infarction

Predictive Value of the Naples Prognostic Score for Acute Kidney Injury in ST-Elevation Myocardial Infarction Patients Undergoing Primary Percutaneous Coronary Intervention

The purpose of this investigation was to investigate whether there was an association between the Naples prognostic score and the development of acute kidney injury (AKI) in ST-elevation myocardial infarction (STEMI) patients following primary percutaneous coronary intervention (pPCI). The study comprised 2901 consecutive STEMI patients who had pPCI. For each patient, the Naples prognostic score was determined. To evaluate the predictive performance of the Naples score (which included either continuous and categorical variables), we developed a Nested model and a nested model combined with the Naples score. The Naples prognostic score was the most significant predictor of AKI occurrence after admission creatinine, age, and contrast volume. The continuous Naples prognostic score model provided the best prediction performance and discriminative ability. The C-index of the Nested and full models with continuous Naples prognostic score were significantly higher than that of the Nested model. The decision curve analysis found that the overall model had a higher full range of probability of clinical net benefit than the baseline model, with a 10% AKI likelihood. The present study found that the Naples prognostic score may be useful to predict the risk of AKI in STEMI patients undergoing pPCI.

Development and Validation of a Risk Model for Predicting Contrast-Associated Acute Kidney Injury in Patients With Cancer: Evaluation in Over 46,000 CT Examinations

BACKGROUND. Patients with cancer undergo frequent CT examinations with iodinated contrast media and may be uniquely predisposed to contrast-associated acute kidney injury (CA-AKI). OBJECTIVE. The purpose of this study was to develop and validate a model for predicting the risk of CA-AKI after contrast-enhanced CT in patients with cancer. METHODS. This retrospective study included 25,184 adult patients (12,153 men, 13,031 women; mean age, 62.3 ± 13.7 [SD] years) with cancer who underwent 46,593 contrast-enhanced CT examinations between January 1, 2016, and June 20, 2020, at one of three academic medical centers. Information was recorded regarding demographics, malignancy type, medication use, baseline laboratory values, and comorbid conditions. CA-AKI was defined as a 0.3-mg/dL or greater increase in serum creatinine level from baseline within 48 hours after CT or a 1.5-fold or greater increase in the peak measurement within 14 days after CT. Multivariable models accounting for correlated data were used to identify risk factors for CA-AKI. A risk score for predicting CA-AKI was generated in a development set (n = 30,926) and tested in a validation set (n = 15,667). RESULTS. CA-AKI occurred after 5.8% (2682/46,593) of CT examinations. The final multivariable model for predicting CA-AKI included hematologic malignancy, diuretic use, angiotensin-converting enzyme inhibitor or angiotensin receptor blocker use, chronic kidney disease (CKD) stage 3a, CKD stage 3b, CKD stage 4 or 5, serum albumin level less than 3.0 g/dL, platelet count less than 150 × 103/μL, 1+ or greater proteinuria on baseline urinalysis, diabetes mellitus, heart failure, and contrast medium volume 100 mL or greater. A risk score (range, 0-53 points) was generated with these variables. The most points (13) were for CKD stage 4 or 5 and for albumin level less than 3 g/dL. The frequency of CA-AKI progressively increased in higher risk categories. For example, in the validation set, CA-AKI occurred after 2.2% of CT examinations in the lowest risk category (score ≤ 4) and after 32.7% of CT examinations in the highest risk category (score ≥ 30). The Hosmer-Lemeshow test result indicated that the risk score was a good fit (p = .40). CONCLUSION. A risk model in which readily available clinical data are used to predict the likelihood of CA-AKI after contrast-enhanced CT in patients with cancer was developed and validated. CLINICAL IMPACT. The model may help facilitate appropriate implementation of preventive measures in the care of patients at high risk of CA-AKI.

Characterization of Risk Prediction Models for Acute Kidney Injury: A Systematic Review and Meta-analysis

Importance

Despite the expansion of published prediction models for acute kidney injury (AKI), there is little evidence of uptake of these models beyond their local derivation nor data on their association with patient outcomes.

Objective

To systematically review published AKI prediction models across all clinical subsettings.

Data Sources

MEDLINE via PubMed (January 1946 to April 2021) and Embase (January 1947 to April 2021) were searched using medical subject headings and text words related to AKI and prediction models.

Study Selection

All studies that developed a prediction model for AKI, defined as a statistical model with at least 2 predictive variables to estimate future occurrence of AKI, were eligible for inclusion. There was no limitation on study populations or methodological designs.

Data Extraction and Synthesis

Two authors independently searched the literature, screened the studies, and extracted and analyzed the data following the Preferred Reporting Items for Systematic Review and Meta-analyses guideline. The data were pooled using a random-effects model, with subgroups defined by 4 clinical settings. Between-study heterogeneity was explored using multiple methods, and funnel plot analysis was used to identify publication bias.

Main Outcomes and Measures

C statistic was used to measure the discrimination of prediction models.

Results

Of the 6955 studies initially identified through literature searching, 150 studies, with 14.4 million participants, met the inclusion criteria. The study characteristics differed widely in design, population, AKI definition, and model performance assessments. The overall pooled C statistic was 0.80 (95% CI, 0.79-0.81), with pooled C statistics in different clinical subsettings ranging from 0.78 (95% CI, 0.75-0.80) to 0.82 (95% CI, 0.78-0.86). Between-study heterogeneity was high overall and in the different clinical settings (eg, contrast medium-associated AKI: I2 = 99.9%; P < .001), and multiple methods did not identify any clear sources. A high proportion of models had a high risk of bias (126 [84.4%]) according to the Prediction Model Risk Of Bias Assessment Tool.

Conclusions and Relevance

In this study, the discrimination of the published AKI prediction models was good, reflected by high C statistics; however, the wide variation in the clinical settings, populations, and predictive variables likely drives the highly heterogenous findings that limit clinical utility. Standardized procedures for development and validation of prediction models are urgently needed.

A prediction model for acute kidney injury in adult patients with hemophagocytic lymphohistiocytosis

Background and aims

Hemophagocytic lymphohistiocytosis is a clinical syndrome resulting from abnormally active immune cells and a cytokine storm, with the accompanying phagocytosis of blood cells. Patients with hemophagocytic lymphohistiocytosis often suffer acute kidney injury during hospitalization, which usually signifies poor prognosis. We would like to establish a prediction model for the occurrence of acute kidney injury in adult patients with hemophagocytic lymphohistiocytosis for risk stratification.

Method

We extracted the electronic medical records of patients diagnosed with hemophagocytic lymphohistiocytosis during hospitalization from January 2009 to July 2019. The observation indicator is the occurrence of acute kidney injury within 28 days of hospitalization. LASSO regression was used to screen variables and modeling was performed by COX regression.

Results

In the present study, 136 (22.7%) patients suffered from acute kidney injury within 28 days of hospitalization. The prediction model consisted of 11 variables, including vasopressor, mechanical ventilation, disseminated intravascular coagulation, admission heart rate, hemoglobin, baseline cystatin C, phosphorus, total bilirubin, lactic dehydrogenase, prothrombin time, and procalcitonin. The risk of acute kidney injury can be assessed by the sum of the scores of each parameter on the nomogram. For the development and validation groups, the area under the receiver operating characteristic curve was 0.760 and 0.820, and the C-index was 0.743 and 0.810, respectively.

Conclusion

We performed a risk prediction model for the development of acute kidney injury in patients with hemophagocytic lymphohistiocytosis, which may help physicians to evaluate the risk of acute kidney injury and prevent its occurrence.

Identifying patients with heart failure in susceptible to de novo acute kidney injury: a machine learning approach (Preprint)

Background

Studies have shown that more than half of patients with heart failure (HF) with acute kidney injury (AKI) have newonset AKI, and renal function evaluation markers such as estimated glomerular filtration rate are usually not repeatedly tested during the hospitalization. As an independent risk factor, delayed AKI recognition has been shown to be associated with the adverse events of patients with HF, such as chronic kidney disease and death.

Objective

The aim of this study is to develop and assess of an unsupervised machine learning model that identifies patients with HF and normal renal function but who are susceptible to de novo AKI.

Methods

We analyzed an electronic health record data set that included 5075 patients admitted for HF with normal renal function, from which 2 phenogroups were categorized using an unsupervised machine learning algorithm called K-means clustering. We then determined whether the inferred phenogroup index had the potential to be an essential risk indicator by conducting survival analysis, AKI prediction, and the hazard ratio test.

Results

The AKI incidence rate in the generated phenogroup 2 was significantly higher than that in phenogroup 1 (group 1: 106/2823, 3.75%; group 2: 259/2252, 11.50%; P<.001). The survival rate of phenogroup 2 was consistently lower than that of phenogroup 1 (P<.005). According to logistic regression, the univariate model using the phenogroup index achieved promising performance in AKI prediction (sensitivity 0.710). The generated phenogroup index was also significant in serving as a risk indicator for AKI (hazard ratio 3.20, 95% CI 2.55-4.01). Consistent results were yielded by applying the proposed model on an external validation data set extracted from Medical Information Mart for Intensive Care (MIMIC) III pertaining to 1006 patients with HF and normal renal function.

Conclusions

According to a machine learning analysis on electronic health record data, patients with HF who had normal renal function were clustered into separate phenogroups associated with different risk levels of de novo AKI. Our investigation suggests that using machine learning can facilitate patient phengrouping and stratification in clinical settings where the identification of high-risk patients has been challenging.

Acute Kidney Injury Following Admission with Acute Coronary Syndrome: The Role of Diabetes Mellitus

Purpose: To evaluate the role of diabetes mellitus in the incidence, risk factors, and outcomes of AKI (acute kidney injury) in patients admitted with ACS (acute coronary syndrome). Methods: We performed a comparative evaluation of ACS patients with vs. without DM who developed AKI enrolled in the biennial ACS Israeli Surveys (ACSIS) between 2000 and 2018. AKI was defined as an absolute increase in serum creatinine (≥0.5 mg/dL) or above 1.5 mg/dL or new renal replacement therapy upon admission with ACS. Outcomes included 30-day major adverse cardiovascular events (MACE) and 1-year all-cause mortality. Results: The current study included a total of 16,879 patients, median age 64 (IQR 54–74), 77% males, 36% with DM. The incidence of AKI was significantly higher among patients with vs. without DM (8.4% vs. 4.7%, p < 0.001). The rates of 30-day MACE (40.8% vs. 13.4%, p < 0.001) and 1-year mortality (43.7% vs. 10%, p < 0.001) were significantly greater among diabetic patients who developed vs. those who did not develop AKI respectively, yet very similar among patients that developed AKI with vs. without DM (30-day MACE 40.8% vs. 40.3%, p = 0.9 1-year mortality 43.7 vs. 44.8%, p = 0.8, respectively). Multivariate analyses adjusted to potential confounders, showed similar independent predictors of AKI among patients with and without DM, comprising; older age, chronic kidney disease, congestive heart failure, and peripheral arterial disease. Conclusions: Although patients with DM are at much greater risk for AKI when admitted with ACS, the independent predictors of AKI and the worse patient outcomes when AKI occurs, are similar irrespective to DM status.

Clinical Scoring for Prediction of Acute Kidney Injury in Patients with Acute ST-Segment Elevation Myocardial Infarction after Emergency Primary Percutaneous Coronary Intervention

Acute kidney injury (AKI) after a coronary intervention is common in patients with ST-segment elevation myocardial infarction (STEMI) and is associated with significant morbidity and mortality. Several scores have been developed to predict post-procedural AKI over the years. However, the AKI definitions have also evolved, which causes the definitions used in the past to be obsolete. We aimed to develop a prediction score for AKI in patients with STEMI requiring emergency primary percutaneous coronary intervention (pPCI). This study was based on a retrospective cohort of Thai patients with STEMI who underwent pPCI at the Central Chest Institute of Thailand from December 2014 to September 2019. AKI was defined as an increase in serum creatinine of at least 0.3 mg/dL from baseline within 48 h after pPCI. Logistic regression was used for modeling. A total of 1617 patients were included. Of these, 195 patients had AKI (12.1%). Eight significant predictors were identified: age, baseline creatinine, left ventricular ejection fraction (LVEF) < 40%, multi-vessel pPCI, treated with thrombus aspiration, inserted intra-aortic balloon pump (IABP), pre- and intra-procedural cardiogenic shock, and congestive heart failure. The score showed an area under the receiver operating characteristic curve of 0.78 (95% CI 0.75, 0.82) and was well-calibrated. The pPCI-AKI score showed an acceptable predictive performance and was potentially useful to help interventionists stratify the patients and provide optimal preventive management.

Predictive value of stress hyperglycemia ratio for the occurrence of acute kidney injury in acute myocardial infarction patients with diabetes

Background

Acute hyperglycemia has been recognized as a robust predictor for occurrence of acute kidney injury (AKI) in nondiabetic patients with acute myocardial infarction (AMI), however, its discriminatory ability for AKI is unclear in diabetic patients after an AMI. Here, we investigated whether stress hyperglycemia ratio (SHR), a novel index with the combined evaluation of acute and chronic glycemic levels, may have a better predictive value of AKI as compared with admission glycemia alone in diabetic patients following AMI.

Methods

SHR was calculated with admission blood glucose (ABG) divided by the glycated hemoglobin-derived estimated average glucose. A total of 1215 diabetic patients with AMI were enrolled and divided according to SHR tertiles. Baseline characteristics and outcomes were compared. The primary endpoint was AKI and secondary endpoints included all-cause death and cardiogenic shock during hospitalization. The logistic regression analysis was performed to identify potential risk factors. Accuracy was defined with area under the curve (AUC) by a receiver-operating characteristic (ROC) curve analysis.

Results

In AMI patients with diabetes, the incidence of AKI (4.4%, 7.8%, 13.0%; p < 0.001), all-cause death (2.7%, 3.6%, 6.4%; p = 0.027) and cardiogenic shock (4.9%, 7.6%, 11.6%; p = 0.002) all increased with the rising tertile levels of SHR. After multivariate adjustment, elevated SHR was significantly associated with an increased risk of AKI (odds ratio 3.18, 95% confidence interval: 1.99–5.09, p < 0.001) while ABG was no longer a risk factor of AKI. The SHR was also strongly related to the AKI risk in subgroups of patients. At ROC analysis, SHR accurately predicted AKI in overall (AUC 0.64) and a risk model consisted of SHR, left ventricular ejection fraction, N-terminal B-type natriuretic peptide, and estimated glomerular filtration rate (eGFR) yielded a superior predictive value (AUC 0.83) for AKI.

Conclusion

The novel index SHR is a better predictor of AKI and in-hospital mortality and morbidity than admission glycemia in AMI patients with diabetes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12872-021-01962-2.

In-hospital outcome of primary PCI for patients with acute myocardial infarction and prior coronary artery bypass grafting

BACKGROUND

This study aims to analyze the in-hospital outcome of primary percutaneous coronary intervention (PCI) for patients with acute myocardial infarction (AMI) and prior coronary artery bypass grafting (CABG).

METHODS

This was a retrospective study. From January 2011 to December 2018, the data of 78 consecutive patients (study group) with prior CABG, who received primary coronary angiography in the setting of ST-elevation myocardial infarction (STEMI) or non-ST-elevation myocardial infarction (NSTEMI), were screened. The study group was compared with another well-matched 78 patients without a history of CABG (control group). The information of the coronary angiograms and clinical data of both groups were analyzed. Multivariate conditional logistic regression models were constructed to test the association between PCI success rate and the prior CABG at age ≥65 and <65 years, respectively.

RESULTS

The results revealed that the primary PCI success rate in the study group was significantly lower than in the control group (67.9% vs. 92.3%, P<0.001) and in-hospital mortality was significantly higher than in control group (11.5% vs. 2.5%, P=0.03). The multivariate logistic regression analysis indicated that the primary PCI success rate was significantly associated with the history of prior CABG both in young patients [age <65 years; odds ratio (OR) =5.26, 95% confidence interval (CI): 1.69-16.47] and elderly (age ≥65 years; OR =13.76, 95% CI: 2.72-69.75).

CONCLUSIONS

The patients who receive primary PCI with AMI and prior CABG have poor in-hospital outcomes, with low PCI success rates and high mortality.

Potassium levels as a marker of imminent acute kidney injury among patients admitted with acute myocardial infarction. Soroka Acute Myocardial Infarction II (SAMI-II) Project

BACKGROUND

Acute kidney injury (AKI) is a common complication following acute myocardial infarction (AMI) and associated with worse outcomes. Serum Potassium levels (K, mEq/L), which are regulated by the kidneys, are related with poor prognosis in patients with AMI.

OBJECTIV

To evaluate whether K levels predict imminent AKI in patients with AMI.

METHODS

This retrospective nested case-control study was based on medical records of hospitalized AMI patients, 2002-2012. The cases (AKI group) were defined as an increase of ≥1.5-fold in serum creatinine level or a decrease of ≥25% in the estimated glomerular filtration rate (eGFR) during the hospitalization. The control group comprised of matched randomly selected patients that did not develop AKI. For both groups, all creatinine and K levels were obtained for up-to 72 h prior to the AKI diagnosis (index time).

RESULTS

A total of 12,498/17,678 admissions met the inclusion criteria. The AKI and the control groups consisted of 430 and 1345 matched admission respectively. K levels, prior AKI diagnosis seemed to be higher in the AKI group. Multivariate analysis showed that K ≥ 4.5 within 36-56 h prior to the index time was an independent predictor of the subsequent AKI, OR = 2.3, p < .001. The c-statistic of the model was 0.859, p < .001. Predictivity of K for AKI was stronger among ST-elevation (STEMI) vs. Non-ST-elevation AMI (NSTEMI) patients (OR = 4, p < .001 vs. 1.7, p = .025 respectively; p-for-interaction = 0.038).

CONCLUSIONS

K ≥ 4.5 is an independent and incremental marker of imminent AKI in patients with AMI, predictivity is stronger in patients with STEMI than NSTEMI.

The Association of Fractional Pulse Pressure with Acute Kidney Injury in Patients Undergoing Coronary Intervention due to ST-Segment Elevated Myocardial Infarction

OBJECTIVE

Acute kidney injury (AKI), which is prevalent in ST-segment elevated myocardial infarction (STEMI) patients who have undergone primary percutaneous coronary intervention (PCI), is associated with poor cardiovascular outcomes. As high pulse pressure (PP) is associated with adverse cardiovascular events, the present study's aim was to evaluate the relationship between fractional PP (PPf) and AKI in patients with STEMI who underwent primary PCI.

SUBJECTS AND METHODS

All laboratory findings as well as echocardiographic and angiographic data of 1,170 consecutive STEMI patients were retrospectively screened. PPf was calculated from the pressures invasively measured after sheath insertion and before performing coronary angiography.

RESULTS

From 1,170 eligible STEMI patients (mean age 56 years, 18.2% female), AKI developed in 143 (12.2%) patients. The PPf and pulsatility index were significantly higher in patients with AKI than those without (0.53 ± 0.10 vs. 0.61 ± 0.10, p < 0.001, and 0.80 ± 0.03 vs. 0.82 ± 0.03, p < 0.001, respectively). PPf was also found to be associated with AKI in univariable (OR 2.183, 95% CI 1.823-2.614, p< 0.001) and multivariable (OR 1.874, 95% CI 1.513-2.322, p < 0.001) analysis. In-hospital mortality was higher in patients with AKI than those without.

CONCLUSION

Invasively measured PPf, which can be easily measured and has no additional cost in STEMI patients undergoing coronary intervention, is an independent predictor of AKI. In addition, PPf is superior to other blood pressure values and derivatives in AKI prediction.

Preventing acute kidney injury and improving outcome in critically ill patients utilizing risk prediction score (PRAIOC-RISKS) study. A prospective controlled trial of AKI prevention

BACKGROUND

Acute kidney injury (AKI) has significant impact on mortality and morbidity in critically ill patients.

METHODS

A prospective controlled interventional pilot study composed of observation and intervention arms was run at two different Intensive care unit (ICU) sites. A recently validated risk prediction score was used to predict the AKI in critically ill patients at high risk of developing AKI. All patients with established AKI at the time of recruitment were excluded from the study. A package of early preventive measures, including an early nephrology review was applied to high risk patients in the intervention arm to prevent AKI development.

RESULTS

We have recruited 108 patients at the intervention site and 98 patients at the observation site. The primary outcome measure was the AKI incidence. AKI incidence was significantly lower in the intervention arm than its incidence in the observation arm (11% vs 26%, p = 0.002). The median Time till recovery of AKI episodes was significantly lower in the intervention arm (3(1) vs. 5(2) days, p = 0.014) 0.30 day mortality was lower in the intervention arm, however, not statistically significant.

CONCLUSION

Our pilot study showed that it was feasible to apply a simple risk score to implement early preventive measures to high risk patients, consequently, mitigating the risk of AKI development and reducing the time till recovery of AKI episodes. Multicentre studies are needed to confirm this favourable effect.

Complete blood count in acute kidney injury prediction: a narrative review

Acute kidney injury (AKI) is a complex syndrome defined by a decrease in renal function. The incidence of AKI has raised in the past decades, and it is associated with negative impact in patient outcomes in the short and long term. Considering the impact of AKI on patient prognosis, research has focused on methods to assess patients at risk for developing AKI, diagnose subclinical AKI, and on prevention and treatment strategies, for which it is crucial an understanding of pathophysiology the of AKI. In this review, we discuss the use of easily available parameters found in a complete blood count to detect patients at risk for developing AKI, to provide an early diagnosis of AKI, and to predict associated patient outcomes.

Clinical efficacy and safety of percutaneous coronary intervention for acute myocardial infarction complicated with chronic renal insufficiency: A protocol of systematic review and meta-analysis

BACKGROUND

The aim of this research is to further evaluate the efficacy and safety of percutaneous coronary intervention (PCI) in patients with acute myocardial infarction (AMI) complicated with chronic renal insufficiency (CRI) by meta-analysis, to provide scientific and effective medical evidence for PCI in patients with AMI complicated with CRI, and to support the clinical application of PCI.

METHODS

Electronic databases will be searched, including PubMed, Cochrane Library, Embase, CNKI, CBM, VIP, and Wanfang Data. Patients with AMI complicated by renal insufficiency treated with PCI will be included. The retrieval time is from inception to January 2019. The inclusion and exclusion criteria are formulated to search only the relevant literature. Endnote software management for literature will be adopted. The literature will be independently screened by 2 researchers. Excel 2016 will be applied to extract literature data with the "Research Information Registration Form." The final selected literature will be assessed for bias risk. Stata 12.0 software will be used for the meta-analysis.

RESULTS

The systematic evaluation and meta-analysis will be carried out strictly in accordance with the requirements of the Cochrane System Evaluator Manual 5.3 on meta-analyses, which will provide a high-quality evaluation of the clinical efficacy and safety of PCI in patients with AMI and CRI.

ETHICS AND DISSEMINATION

This study belongs to the category of systematic reviews, not clinical trials. Therefore, it does not require ethical approval. The results of this study will be published in influential international academic journals related to this topic.

CONCLUSION

PCI is an effective and safe treatment for patients with AMI and CRI. This study will provide a definite evidence-based medical conclusion and provide a scientific basis for the clinical treatment of patients with AMI and CRI.

PROSPERO REGISTRATION NUMBER

CRD42019131367.

Derivation and validation of a prediction score for acute kidney injury secondary to acute myocardial infarction in Chinese patients

Background

Acute kidney injury (AKI) is a major complication of acute myocardial infarction(AMI), which can significantly increase mortality. This study is to analyze the related risk factors and establish a prediction score of acute kidney injury in order to take early measurement for prevention.

Methods

The medical records of 6014 hospitalized patients with AMI in Beijing Anzhen Hospital from January 2010 to December 2016 were retrospectively analyzed. These patients were randomly assigned into two cohorts: one was for the derivation of prediction score (n = 4252) and another for validation (n = 1762). The criterion for AKI was defined as an increase in serum creatinine of ≥ 0.3 mg/dL or ≥ 50% from baseline within 48 h. On the basis of odds ratio obtained from multivariate logistic regression analysis, a prediction score of acute kidney injury after AMI was built up.

Results

In this prediction score, risk score 1 point included hypertension history, heart rate > 100 bpm on admission, peak serum troponin I ≥ 100 μg/L, and time from admission to coronary reperfusion > 120 min; risks score 2 points included Killip classification ≥ class 3 on admission; and maximum dosage of intravenous furosemide ≥ 60 mg/d; risks score 3 points only included shock during hospitalization. In addition, when baseline estimated glomerular filtration rate (eGFR) was less than 90 ml/min·1.73 m², every 10 ml/min·1.73 m² reduction of eGFR increased risk score 1 point. Youden index showed that the best cut-off value for prediction of AKI was 3 points with a sensitivity of 71.1% and specificity 74.2%. The datasets of derivation and validation both displayed adequate discrimination (an area under the ROC curve, 0.79 and 0.81, respectively) and satisfactory calibration (Hosmer–Lemeshow statistic test, P = 0.63 and P = 0.60, respectively).

Conclusions

In conclusion, a prediction score for AKI secondary to AMI in Chinese patients was established, which may help to prevent AKI early.