Acute kidney injury risk prediction score for critically-ill surgical patients

Impact of Operative Approach on Acute Kidney Injury Risk Prediction Models for Colectomy

INTRODUCTION

Acute kidney injury (AKI) is a serious postoperative complication associated with increased morbidity and mortality. Identifying patients at risk for AKI is important for risk stratification and management. This study aimed to develop an AKI risk prediction model for colectomy and determine if the operative approach (laparoscopic versus open) alters the influence of predictive factors through an interaction term analysis.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program database was analyzed from 2005 to 2019. Patients undergoing laparoscopic and open colectomy were identified and propensity score matched. Multivariable logistic regression identified significant preoperative demographic, comorbidity, and laboratory value predictors of AKI. The predictive ability of a baseline model consisting of these variables was compared to a proposed model incorporating interaction terms between operative approach and predictor variables using the likelihood ratio test, c-statistic, and Brier score. Shapley Additive Explanations values assessed relative importance of significant predictors.

RESULTS

252,372 patients were included in the analysis. Significant AKI predictors were hypertension, age, sex, race, body mass index, smoking, diabetes, preoperative sepsis, Congestive heart failure, preoperative creatinine, preoperative albumin, and operative approach (P < 0.001). The proposed model with interaction terms had improved predictive ability per the likelihood ratio test (P < 0.05) but had no statistically significant interaction terms. C-statistic and Brier scores did not improve. Shapley Additive Explanations analysis showed hypertension had the highest importance. The importance of age and diabetes showed some variation between operative approaches.

CONCLUSIONS

While the inclusion of interaction terms collectively improved AKI prediction, no individual operative approach interaction terms were significant. Including operative approach interactions may enhance predictive ability of AKI risk models for colectomy.

Trends in perioperative practices of high-risk surgical patients over a 10-year interval

INTRODUCTION

In Brazil, data show an important decrease in morbi-mortality of high-risk surgical patients over a 10-year high. The objective of this post-hoc study was to evaluate the mechanism explaining this trend in high-risk surgical patients admitted to Brazilian ICUs in two large Brazilian multicenter cohort studies performed 10 years apart.

METHODS

The patients included in the 2 cohorts studies published in 2008 and 2018 were compared after a (1:1) propensity score matching. Patients included were adults who underwent surgeries and admitted to the ICU afterwards.

RESULTS

After matching, 704 patients were analyzed. Compared to the 2018 cohort, 2008 cohort had more postoperative infections (OR 13.4; 95%CI 6.1-29.3) and cardiovascular complications (OR 1.5; 95%CI 1.0-2.2), as well as a lower survival ICU stay (HR = 2.39, 95% CI: 1.36-4.20) and hospital stay (HR = 1.64, 95% CI: 1.03-2.62). In addition, by verifying factors strongly associated with hospital mortality, it was found that the risk of death correlated with higher intraoperative fluid balance (OR = 1.03, 95% CI 1.01-1.06), higher creatinine (OR = 1.31, 95% CI 1.1-1.56), and intraoperative blood transfusion (OR = 2.32, 95% CI 1.35-4.0). By increasing the mean arterial pressure, according to the limits of sample values from 43 mmHg to 118 mmHg, the risk of death decreased (OR = 0.97, 95% CI 0.95-0.98). The 2008 cohort had higher fluid balance, postoperative creatinine, and volume of intraoperative blood transfused and lower mean blood pressure at ICU admission and temperature at the end of surgery.

CONCLUSION

In this sample of ICUs in Brazil, high-risk surgical patients still have a high rate of complications, but with improvement over a period of 10 years. There were changes in the management of these patients over time.

Predictive model of acute kidney injury after spontaneous intracerebral hemorrhage: A multicenter retrospective study

BACKGROUND AND OBJECTIVES

Acute kidney injury is a common comorbidity in patients with intracerebral hemorrhage. Although there are predictive models to determine risk of AKI in patients in critical care or post-surgical scenarios or in general medical floors, there are no models that specifically determine the risk of AKI in patients with ICH.

METHODS

Clinical features and laboratory tests were selected by previous studies and LASSO (least absolute shrinkage and selection operator) regression. We used multivariable logistic regression with a bidirectional stepwise method to construct ICH-AKIM (intracerebral hemorrhage-associated acute kidney injury model). The accuracy of ICH-AKIM was measured by the area under the receiver operating characteristic curve. The outcome was AKI development during hospitalization, defined as KDIGO (Kidney Disease: Improving Global Outcomes) Guidelines.

RESULTS

From four independent medical centers, a total of 9649 patients with ICH were available. Overall, five clinical features (sex, systolic blood pressure, diabetes, Glasgow coma scale, mannitol infusion) and four laboratory tests at admission (serum creatinine, albumin, uric acid, neutrophils-to-lymphocyte ratio) were predictive factors and were included in the ICH-AKIM construction. The AUC of ICH-AKIM in the derivation, internal validation, and three external validation cohorts were 0.815, 0.816, 0.776, 0.780, and 0.821, respectively. Compared to the univariate forecast and pre-existing AKI models, ICH-AKIM led to significant improvements in discrimination and reclassification for predicting the incidence of AKI in all cohorts. An online interface of ICH-AKIM is freely available for use.

CONCLUSION

ICH-AKIM exhibited good discriminative capabilities for the prediction of AKI after ICH and outperforms existing predictive models.

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.

Development and validation of AKI prediction model in postoperative critically ill patients: a multicenter cohort study

BACKGROUND

Acute kidney injury (AKI) is a common complication, especially among postoperative critically ill patients. Early identification of AKI is essential for reducing mortality.

METHODS

Multicenter data were used to develop an AKI prediction model for critically ill postoperative patients. A total of 1731 patients admitted to intensive care units (ICUs) were divided into a development set (n=1196) and a validation set (n=535) according to the principle of 7:3 randomization. Multivariate logistic regression analysis was performed on the predictors identified by univariate analysis, and a nomogram was created based on the predictors. The area under the receiver operating characteristic curve (AUROC) was used to assess the discrimination of the model. Calibration curves were generated, and the Hosmer-Lemeshow (HL) goodness of fit test was carried out. Decision curve analysis (DCA) was performed to assess the net clinical benefit.

RESULTS

The final model included 7 predictors: age, emergency surgery, abnormal basal creatinine level (BCr), chronic kidney disease (CKD), use of nephrotoxic drugs, diuretic use, and the Sequential Organ Failure Assessment (SOFA) score. A nomogram was drawn based on the predictors. The AUROC of the model in the development set was 0.725 (95% confidence interval (CI): 0.696-0.754). In the validation set, the AUROC was 0.706 (95% CI: 0.656-0.744). The model showed good discrimination (>70%) in both sets, and the HL test indicated that the model fit was good (P>0.05). DCA showed that our model is clinically useful.

CONCLUSION

The novel prediction model can be used to identify high-risk postoperative patients and provide a scientific and effective basis for clinicians to identify AKI early with a nomogram.

Development and validation of a clinical prediction model of acute kidney injury in intensive care unit patients at a rural tertiary teaching hospital in South Africa: a study protocol

INTRODUCTION

Acute kidney injury (AKI) is a decline in renal function lasting hours to days. The rising global incidence of AKI, and associated costs of renal replacement therapy, is a public health priority. With the only therapeutic option being supportive therapy, prevention and early diagnosis will facilitate timely interventions to prevent progression to chronic kidney disease. While many factors have been identified as predictive of AKI, none have shown adequate sensitivity or specificity on their own. Many tools have been developed in developed-country cohorts with higher rates of non-communicable disease, and few have been validated and practically implemented. The development and validation of a predictive tool incorporating clinical, biochemical and imaging parameters, as well as quantification of their impact on the development of AKI, should make timely and improved prediction of AKI possible. This study is positioned to develop and validate an AKI prediction tool in critically ill patients at a rural tertiary hospital in South Africa.

METHOD AND ANALYSIS

Critically ill patients will be followed from admission until discharge or death. Risk factors for AKI will be identified and their impact quantified using statistical modelling. Internal validation of the developed model will be done on separate patients admitted at a different time. Furthermore, patients developing AKI will be monitored for 3 months to assess renal recovery and quality of life. The study will also explore the utility of endothelial monitoring using the biomarker Syndecan-1 and capillary leak measurements in predicting persistent AKI.

ETHICS AND DISSEMINATION

The study has been approved by the Walter Sisulu University Faculty of Health Science Research Ethics and Biosafety Committee (WSU No. 005/2021), and the Eastern Cape Department of Health Research Ethics (approval number: EC 202103006). The findings will be shared with facility management, and presented at relevant conferences and seminars.

State of the Art of Machine Learning-Enabled Clinical Decision Support in Intensive Care Units: Literature Review

Background

Modern clinical care in intensive care units is full of rich data, and machine learning has great potential to support clinical decision-making. The development of intelligent machine learning–based clinical decision support systems is facing great opportunities and challenges. Clinical decision support systems may directly help clinicians accurately diagnose, predict outcomes, identify risk events, or decide treatments at the point of care.

Objective

We aimed to review the research and application of machine learning–enabled clinical decision support studies in intensive care units to help clinicians, researchers, developers, and policy makers better understand the advantages and limitations of machine learning–supported diagnosis, outcome prediction, risk event identification, and intensive care unit point-of-care recommendations.

Methods

We searched papers published in the PubMed database between January 1980 and October 2020. We defined selection criteria to identify papers that focused on machine learning–enabled clinical decision support studies in intensive care units and reviewed the following aspects: research topics, study cohorts, machine learning models, analysis variables, and evaluation metrics.

Results

A total of 643 papers were collected, and using our selection criteria, 97 studies were found. Studies were categorized into 4 topics—monitoring, detection, and diagnosis (13/97, 13.4%), early identification of clinical events (32/97, 33.0%), outcome prediction and prognosis assessment (46/97, 47.6%), and treatment decision (6/97, 6.2%). Of the 97 papers, 82 (84.5%) studies used data from adult patients, 9 (9.3%) studies used data from pediatric patients, and 6 (6.2%) studies used data from neonates. We found that 65 (67.0%) studies used data from a single center, and 32 (33.0%) studies used a multicenter data set; 88 (90.7%) studies used supervised learning, 3 (3.1%) studies used unsupervised learning, and 6 (6.2%) studies used reinforcement learning. Clinical variable categories, starting with the most frequently used, were demographic (n=74), laboratory values (n=59), vital signs (n=55), scores (n=48), ventilation parameters (n=43), comorbidities (n=27), medications (n=18), outcome (n=14), fluid balance (n=13), nonmedicine therapy (n=10), symptoms (n=7), and medical history (n=4). The most frequently adopted evaluation metrics for clinical data modeling studies included area under the receiver operating characteristic curve (n=61), sensitivity (n=51), specificity (n=41), accuracy (n=29), and positive predictive value (n=23).

Conclusions

Early identification of clinical and outcome prediction and prognosis assessment contributed to approximately 80% of studies included in this review. Using new algorithms to solve intensive care unit clinical problems by developing reinforcement learning, active learning, and time-series analysis methods for clinical decision support will be greater development prospects in the future.

Application of Machine Learning Algorithms to Predict Acute Kidney Injury in Elderly Orthopedic Postoperative Patients

Objective

There has been a worldwide increment in acute kidney injury (AKI) incidence among elderly orthopedic operative patients. The AKI prediction model provides patients’ early detection a possibility at risk of AKI; most of the AKI prediction models derive, however, from the cardiothoracic operation. The purpose of this study is to predict the risk of AKI in elderly patients after orthopedic surgery based on machine learning algorithm models.

Methods

We organized a retrospective study being comprised of 1000 patients with postoperative AKI undergoing orthopedic surgery from September 2016, to June, 2021. They were divided into training (80%;n=799) and test (20%;n=201) sets.We utilized nine machine learning (ML) algorithms and used intraoperative information and preoperative clinical features to acquire models to predict AKI. The performance of the model was evaluated according to the area under the receiver operating characteristic (AUC), sensitivity, specificity and accuracy. Select the optimal model and establish the nomogram to make the prediction model visualization. The concordance statistic (C-statistic) and calibration curve were used to discriminate and calibrate the nomogram respectively.

Results

In predicting AKI, nine ML algorithms posted AUC of 0.656–1.000 in the training cohort, with the randomforest standing out and AUC of 0.674–0.821 in the test cohort, with the logistic regression model standing out. Thus, we applied the logistic regression model to establish nomogram. The nomogram was comprised of ten variables: age, body mass index, American Society of Anesthesiologists, hypoproteinemia, hypertension, diabetes, anemia, duration of low mean arterial pressure, mean arterial pressure, transfusion.The calibration curves showed good agreement between prediction and observation in both the training and test sets.

Conclusion

By including intraoperative and preoperative risk factors, ML algorithm can predict AKI and logistic regression model performing the best. Our prediction model and nomogram that are based on this ML algorithm can help lead decision-making for strategies to inhibit AKI over the perioperative duration.

Advances in artificial intelligence and deep learning systems in ICU-related acute kidney injury

PURPOSE OF REVIEW

Acute kidney injury (AKI) affects nearly 60% of all patients admitted to ICUs. Large volumes of clinical, monitoring and laboratory data produced in ICUs allow the application of artificial intelligence analytics. The purpose of this article is to assimilate and critically evaluate recently published literature regarding artificial intelligence applications for predicting, diagnosing and subphenotyping AKI among critically ill patients.

RECENT FINDINGS

Among recent studies regarding artificial intelligence implementations for predicting, diagnosing and subphenotyping AKI among critically ill patients, there are many promising models, but few had external validation, clinical interpretability and high predictive performance. Deep learning techniques leveraging multimodal clinical data show great potential to provide continuous, accurate, early predictions of AKI risk, which could be implemented clinically to optimize preventive and early therapeutic management strategies.

SUMMARY

Use of consensus criteria, standard definitions and common data models could facilitate access to machine learning-ready data sets for external validation. The lack of interpretability, explainability, fairness and transparency of artificial intelligence models hinder their entrustment and clinical implementation; compliance with standardized reporting guidelines can mitigate these challenges.

Assessment of Detectable Serum Tobramycin Concentrations in Patients Receiving Inhaled Tobramycin for Ventilator-Associated Pneumonia

BACKGROUND

Inhaled tobramycin can be used for empiric or definitive therapy of ventilator-associated pneumonia (VAP) in mechanically ventilated patients. This is believed to minimize systemic exposure and potential adverse drug toxicities including acute kidney injury (AKI). However, detectable serum tobramycin concentrations have been reported after inhaled tobramycin therapy with AKI.

METHODS

This retrospective, observational study evaluated mechanically ventilated adult subjects admitted to ICUs at a large, urban academic medical center that received empiric inhaled tobramycin for VAP. Subjects were separated into detectable (ie, ≥ 0.6 mg/L) or undetectable serum tobramycin concentration groups, and characteristics were compared. Independent predictors for detectable serum tobramycin concentration and new onset AKI during or within 48 h of therapy discontinuation were assessed.

RESULTS

Fifty-nine inhaled tobramycin courses in 53 subjects were included in the analysis, of which 39 (66.1%) courses administered to 35 (66.0%) subjects had detectable serum tobramycin concentrations. Subjects with detectable serum tobramycin concentrations were older (57.1 y ± 11.4 vs 45.9 ±15.0, P = .004), had higher PEEP (9.2 cm H₂O [7.0-11.0] vs 8.0 [5.6-8.9], P = .049), chronic kidney disease stage ≥ 2 (10 [29.4%] vs 0 [0%], P = .009), and higher serum creatinine before inhaled tobramycin therapy (1.26 mg/dL [0.84-2.18] vs 0.76 [0.47-1.28], P = .004). Age (odds ratio 1.09 [95% CI 1.02-1.16], P = .009) and PEEP (odds ratio 1.47 [95% CI 1.08-2.0], P =.01) were independent predictors for detectable serum tobramycin concentration. Thirty-seven subjects had no previous renal disease or injury, of which 9 (24.3%) developed an AKI. Sequential Organ Failure Assessment score (odds ratio 1.72 [95% CI 1.07-2.76], P = .03) was the only independent predictor for AKI.

CONCLUSIONS

Detectable serum tobramycin concentrations were frequently observed in critically ill, mechanically ventilated subjects receiving empiric inhaled tobramycin for VAP. Subject age and PEEP were independent predictors for detectable serum tobramycin concentration. Serum monitoring and empiric dose reductions should be considered in older patients and those requiring higher PEEP.

A Data Augmentation Method for War Trauma Using the War Trauma Severity Score and Deep Neural Networks

The demand for large-scale analysis and research of data on trauma from modern warfare is increasing day by day, but the amount of existing data is not sufficient to meet such demand. In this study, an integrated modeling approach incorporating a war trauma severity scoring algorithm (WTSS) and deep neural networks (DNN) is proposed. First, the proposed WTSS, which uses multiple non-linear regression based on the characteristics of war trauma data and the medical evaluation by an expert panel, performed a standardized assessment of an injury and predicts its trauma consequences. Second, to generate virtual injury, based on the probability of occurrence, the injured parts, injury types, and complications were randomly sampled and combined, and then WTSS was used to assess the consequences of the virtual injury. Third, to evaluate the accuracy of the predicted injury consequences, we built a DNN classifier and then trained it with the generated data and tested it with real data. Finally, we used the Delphi method to filter out unreasonable injuries and improve data rationality. The experimental results verified that the proposed approach surpassed the traditional artificial generation methods, achieved a prediction accuracy of 84.43%, and realized large-scale and credible war trauma data augmentation.

Lowered Risk of Nephrotoxicity through Intervention against the Combined Use of Vancomycin and Tazobactam/Piperacillin: A Retrospective Cohort Study

The combined use of vancomycin (VCM) and tazobactam/piperacillin (TAZ/PIPC) is a major risk factor for nephrotoxicity. We sought to evaluate interventions against the combined use of VCM and TAZ/PIPC. This retrospective cohort study involved patients who considered the combined use of VCM and TAZ/PIPC as a treatment. Patients that had either or both antimicrobials replaced were assigned to the intervention group, whereas those who were continued on combination therapy were assigned to the comparison group. The primary endpoint was the incidence of acute kidney injury (AKI). The survival rate of patients on day 30 was evaluated as the secondary endpoint. The comparison and intervention groups were composed of 65 and 68 patients, respectively, and the incidence rates of AKI were 44.6% and 17.6%, respectively. Cox proportional hazard analysis identified the intervention as the only independent factor against AKI development, with a hazard ratio of 0.282 (95% confidence interval [CI], 0.141 to 0.565). For the incidence of AKI of grade greater than 1, the hazard ratio was 0.114 (95% CI, 0.025 to 0.497). The survival rates on day 30 in the comparison and intervention groups were 92.3% and 91.2%, respectively, with a relative risk of 0.988 (95% CI, 0.892 to 1.094). The trough VCM concentration was not associated with the incidence of AKI in patients receiving the combination therapy. This study demonstrated that intervention against the combined use of VCM and TAZ/PIPC can lower the risk of nephrotoxicity. IMPORTANCE The combined use of vancomycin (VCM) and tazobactam/piperacillin (TAZ/PIPC) is a major risk factor for nephrotoxicity. We retrospectively evaluated interventions against the combined use of VCM and TAZ/PIPC. Patients for whom either or both antimicrobials were replaced were assigned to the intervention group (65 patients), whereas those who were continued on combination therapy were assigned to the comparison group (68 patients). The primary endpoint was the incidence of acute kidney injury (AKI). The incidence rates of AKI in the intervention and comparison groups were 44.6% and 17.6%, respectively. Cox proportional hazard analysis identified intervention as the only independent factor against AKI development, with a hazard ratio of 0.282 (95% confidence interval [CI], 0.141 to 0.565). In conclusion, this study demonstrated that intervention against the combined use of VCM and TAZ/PIPC can lower the risk of nephrotoxicity.

Incidence, risk factors and outcome of acute kidney injury (AKI) in patients with COVID-19

Background

Acute kidney injury (AKI) is a severe complication of coronavirus disease-2019 (COVID-19). This study aims to evaluate incidence, risk factors and case-fatality rate of AKI in patients with COVID-19.

Methods

We reviewed the health medical records of 307 consecutive patients with COVID-19 hospitalized at the University Hospital of Modena, Italy.

Results

AKI was diagnosed in 69 out of 307 (22.4%) COVID-19 patients. Stages 1, 2, or 3 AKI accounted for 57.9%, 24.6% and 17.3%, respectively. AKI patients had a mean age of 74.7 ± 9.9 years. These patients showed higher serum levels of the main markers of inflammation and higher rate of severe pneumonia than non-AKI patients. Kidney injury was associated with a higher rate of urinary abnormalities including proteinuria (0.44 ± 0.85 vs 0.18 ± 0.29 mg/mg; P =  < 0.0001) and microscopic hematuria (P = 0.032) compared to non-AKI patients. Hemodialysis was performed in 7.2% of the subjects and 33.3% of the survivors did not recover kidney function after AKI. Risk factors for kidney injury were age, male sex, CKD and higher non-renal SOFA score. Patients with AKI had a mortality rate of 56.5%. Adjusted Cox regression analysis revealed that COVID-19-associated AKI was independently associated with in-hospital death (hazard ratio [HR] = 4.82; CI 95%, 1.36–17.08) compared to non-AKI patients.

Conclusion

AKI was a common and harmful consequence of COVID-19. It manifested with urinary abnormalities (proteinuria, microscopic hematuria) and conferred an increased risk for death. Given the well-known short-term sequelae of AKI, prevention of kidney injury is imperative in this vulnerable cohort of patients.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10157-021-02092-x.

External Validation of the Acute Kidney Injury Risk Prediction Score for Critically Ill Surgical Patients Who Underwent Major Non-Cardiothoracic Surgery

Background: Acute kidney injury (AKI) is a common complication encountered in an intensive care unit (ICU). In 2020, the AKI prediction score was developed specifically for critically ill surgical patients who underwent major non-cardiothoracic surgeries. This study aimed to externally validate the AKI prediction score in terms of performance and clinical utility. Methods: External validation was carried out in a prospective cohort of patients admitted to the ICU of the Faculty of Medicine Vajira Hospital between September 2014 and September 2015. The endpoint was AKI within seven days following ICU admission. Discriminative ability was based on the area under the receiver operating characteristic curves (AuROC). Calibration and clinical usefulness were evaluated. Results: A total of 201 patients were included in the analysis. AKI occurred in 37 (18.4%) patients. The discriminative ability dropped from good in the derivation cohort, to acceptable in the validation cohort (0.839 (95%CI 0.825–0.852) vs. 0.745 (95%CI 0.652–0.838)). No evidence of lack-of-fit was identified (p = 0.754). The score had potential clinical usefulness across the range of threshold probability from 10 to 50%. Conclusions: The AKI prediction score showed an acceptable discriminative performance and calibration with potential clinical usefulness for predicting AKI risk in surgical patients who underwent major non-cardiothoracic surgery.