• Acute kidney injury
• Intracerebral hemorrhage
• Pulse pressure

• Humans
• Male
• Acute Kidney Injury/etiology
• Acute Kidney Injury/physiopathology
• Acute Kidney Injury/epidemiology
• Female
• Aged
• Blood Pressure/physiology
• Cerebral Hemorrhage/complications
• Cerebral Hemorrhage/physiopathology
• Middle Aged
• Risk Factors
• Aged, 80 and over
• Japan/epidemiology
• Incidence

• Intra-operative variables
• cardiac surgery
• model validation
• morbidity
• mortality
• risk model

• Humans
• Cardiac Surgical Procedures/methods

• acute kidney injury
• cardiac valve surgery
• cardiovascular surgery
• external validation
• prediction model
• risk factors

• National Natural Science Foundation of China

• Cardiac surgery
• antifibrinolytic drugs
• aprotinin
• bleeding
• cardiopulmonary bypass
• mortality

• Adult
• Humans
• Aprotinin/adverse effects
• Blood Loss, Surgical/prevention & control
• Cardiac Surgical Procedures/adverse effects
• Cardiac Surgical Procedures/methods
• Endocarditis
• Aortic Dissection
• Hemostatics/adverse effects

• Correlation coefficient
• Dense multi scale entropy
• Eigen-entropy
• Eigenvalue
• Multivariate time series classification
• Time series signatures

• 2122901 National Science Foundation (NSF) - Partnership for Innovation - "Avoiding Kidney Injuries"

• acute kidney injury
• cardiopulmonary bypass
• reduction of creatinine

• cardiac surgery
• ischemia-reperfusion
• microvasculature
• organ damage
• vasomotor tone

• R01 HL046716 NHLBI NIH HHS
• F32 HL160063 NHLBI NIH HHS
• T32 GM065085 NIGMS NIH HHS
• R01 HL128831 NHLBI NIH HHS
• R01 HL136347 NHLBI NIH HHS
• R01 HL127072 NHLBI NIH HHS
• National Heart, Lung, and Blood Institute
• National Institute of General Medical Sciences

• acute kidney injury
• cardiac surgery
• lasso logistics regression
• machine learning
• prediction

• National Natural Science Foundation of China

• acute kidney injury
• cardiac surgery
• cardiopulmonary bypass
• perioperative risk stratification
• renal replacement therapy

• Acute kidney injury
• Cardiopulmonary bypass
• Oxygen delivery index
• Pulse pressure

• AKI
• acute kidney injury
• artificial intelligence
• cardiac surgery
• cardiac surgery-associated acute kidney injury
• individualized medicine
• machine learning
• personalized medicine
• preoperative

• 21-004248 Mayo Clinic and nference AI Challenge Award

A clinical prediction model for postoperative combined Acute kidney injury (AKI) in patients with Type A acute aortic dissection (TAAAD) and Type B acute aortic dissection (TBAAD) was constructed by using Machine Learning (ML).

Baseline data was collected from Acute aortic division (AAD) patients admitted to First Affiliated Hospital of Xinjiang Medical University between January 1, 2019 and December 31, 2021. (1) We identified baseline Serum creatinine (SCR) estimation methods and used them as a basis for diagnosis of AKI. (2) Divide their total datasets randomly into Training set (70%) and Test set (30%), Bootstrap modeling and validation of features using multiple ML methods in the training set, and select models corresponding to the largest Area Under Curve (AUC) for follow-up studies. (3) Screening of the best ML model variables through the model visualization tools Shapley Addictive Explanations (SHAP) and Recursive feature reduction (REF). (4) Finally, the pre-screened prediction models were evaluated using test set data from three aspects: discrimination, Calibration, and clinical benefit.

The final incidence of AKI was 69.4% (120/173) in 173 patients with TAAAD and 28.6% (81/283) in 283 patients with TBAAD. For TAAAD-AKI, the Random Forest (RF) model showed the best prediction performance in the training set (AUC = 0.760, 95% CI:0.630–0.881); while for TBAAD-AKI, the Light Gradient Boosting Machine (LightGBM) model worked best (AUC = 0.734, 95% CI:0.623–0.847). Screening of the characteristic variables revealed that the common predictors among the two final prediction models for postoperative AKI due to AAD were baseline SCR, Blood urea nitrogen (BUN) and Uric acid (UA) at admission, Mechanical ventilation time (MVT). The specific predictors in the TAAAD-AKI model are: White blood cell (WBC), Platelet (PLT) and D dimer at admission, Plasma The specific predictors in the TBAAD-AKI model were N-terminal pro B-type natriuretic peptide (BNP), Serum kalium, Activated partial thromboplastin time (APTT) and Systolic blood pressure (SBP) at admission, Combined renal arteriography in surgery. Finally, we used in terms of Discrimination, the ROC value of the RF model for TAAAD was 0.81 and the ROC value of the LightGBM model for TBAAD was 0.74, both with good accuracy. In terms of calibration, the calibration curve of TAAAD-AKI's RF fits the ideal curve the best and has the lowest and smallest Brier score (0.16). Similarly, the calibration curve of TBAAD-AKI's LightGBM model fits the ideal curve the best and has the smallest Brier score (0.15). In terms of Clinical benefit, the best ML models for both types of AAD have good Net benefit as shown by Decision Curve Analysis (DCA).

We successfully constructed and validated clinical prediction models for the occurrence of AKI after surgery in TAAAD and TBAAD patients using different ML algorithms. The main predictors of the two types of AAD-AKI are somewhat different, and the strategies for early prevention and control of AKI are also different and need more external data for validation.

• Acute kidney injury
• Artificial intelligence
• Machine learning
• Renal replacement therapy
• Risk prediction

• Acute Kidney Injury/diagnosis
• Acute Kidney Injury/therapy
• Artificial Intelligence
• Hospitalization
• Humans
• Nephrology
• Risk Assessment

• R01 DK126933 NIDDK NIH HHS

Diagnosis of cardiac surgery-associated acute kidney injury (CSA-AKI), a syndrome of sudden renal dysfunction occurring in the immediate post-operative period, is still sub-optimal. Standard CSA-AKI diagnosis is performed according to the international criteria for AKI diagnosis, afflicted with insufficient sensitivity, specificity, and prognostic capacity. In this article, we describe the limitations of current diagnostic procedures and of the so-called injury biomarkers and analyze new strategies under development for a conceptually enhanced diagnosis of CSA-AKI. Specifically, early pathophysiological diagnosis and patient stratification based on the underlying mechanisms of disease are presented as ongoing developments. This new approach should be underpinned by process-specific biomarkers including, but not limited to, glomerular filtration rate (GFR) to other functions of renal excretion causing GFR-independent hydro-electrolytic and acid-based disorders. In addition, biomarker-based strategies for the assessment of AKI evolution and prognosis are also discussed. Finally, special focus is devoted to the novel concept of pre-emptive diagnosis of acquired risk of AKI, a premorbid condition of renal frailty providing interesting prophylactic opportunities to prevent disease through diagnosis-guided personalized patient handling. Indeed, a new strategy of risk assessment complementing the traditional scores based on the computing of risk factors is advanced. The new strategy pinpoints the assessment of the status of the primary mechanisms of renal function regulation on which the impact of risk factors converges, namely renal hemodynamics and tubular competence, to generate a composite and personalized estimation of individual risk.

• biomarkers
• cardiac surgery-associated AKI
• diagnosis

• Aprotinin/adverse effects
• Blood Loss, Surgical/prevention & control
• Cardiac Surgical Procedures/adverse effects
• Cardiac Surgical Procedures/methods
• Coronary Artery Bypass/adverse effects
• Hemostatics/adverse effects
• Hospital Mortality
• Humans
• Male
• Thoracic Surgery

• MTHFR
• impaired renal function
• preeclampsia
• pregnancy hypertension
• risk factor

The association of lactate and contrast-induced acute kidney injury (CI-AKI) has not been well established. This prospective study was planned to identify the effects of lactate level on the occurrence of CI-AKI and long-term prognosis with acute myocardial infarction (AMI) patients undergoing emergency percutaneous coronary intervention (PCI).

A total of 280 patients with AMI who underwent emergency PCI were selected from March 2018 to March 2019. A receiver operating characteristic (ROC) curve was used to analyze the optimal cut-off value of lactate on predicting CI-AKI after PCI. A multivariable logistic regression model was used to explore the significant predictors that might affect the occurrence of CI-AKI after univariate analysis. The primary endpoints were clinical outcomes including events: a combined endpoint of major adverse cardiovascular events, re-hospitalization due to heart failure, and worsening renal function. The Cox regression model was further used to analyze the predictors of the long-term prognosis after PCI.

Among the 280 patients, 64 patients (22.9%) developed CI-AKI after emergency PCI procedure. Multivariable logistic regression analysis revealed that baseline lactate level was the independent risk factor for the development of CI-AKI (OR, 3.657; 95% CI, 2.237–5.978; p<0.001). The area under the ROC curve for predicting CI-AKI of lactate was 0.786, and the optimum cut-off point of lactate was 3.02 mmol/L, with sensitivity of 65.6% and specificity of 85.2%. The incidence of primary endpoints in the high lactate group (lactate ≥3.02mmol/L) was significantly increased compared with the control group [26.3% (42/160) vs 15.8% (19/120), χ²=4.430, p=0.035]. Cox regression analysis also confirmed high lactate was an independent predictor for primary endpoint outcomes at 1-year follow-up (HR, 1.916; 95% CI, 1.118–3.285; p=0.018).

Our study demonstrates that baseline high lactate levels may be associated with an increased risk of CI-AKI and are the important predictors of long-term poor cardiorenal outcomes in AMI patients undergoing emergency PCI.

• acute kidney injury
• contrast media
• lactate
• myocardial infarction
• percutaneous coronary intervention
• prognosis

• Acute kidney injury
• Cardiac surgery
• NGAL score
• Neutrophil gelatinase-associated lipocalin

Rhabdomyolysis-induced acute kidney injury (AKI) is one of the most common complications of catastrophic incidents, especially earthquakes. Early detection of AKI can reduce the burden of the disease. In this paper, data collected from the Bam earthquake was used to find a suitable model that can be used in prediction of AKI in the early stages of the disaster.

Models used in this paper utilized many inputs, which were extracted from the previously published dataset, but depending on the employed method, other inputs have also been considered. This work has been done in two parts. In the first part, the models were constructed from a smaller set of records, which included all of the required fields and in the second part; the main purpose was to find a way to replace the missing data, as data are mostly incomplete in catastrophic events. The data used belonged to the victims of the Bam earthquake, who were admitted to different hospitals. These data were collected on the first day of the incident via questionnaires that were provided by the Iranian Society of Nephrology, in collaboration with the International Society of Nephrology (ISN).

Overall, neural networks have more robust results and given that they can be trained on more data to gain better accuracy, and gain more generalization, they show promising results. Overall, the best specificity that was achieved on testing almost all of the records was 99.24% and the best sensitivity that was achieved in testing almost all of the records was 94.44%.

We introduced several machine learning-based methods for predicting rhabdomyolysis-induced AKI on the third day after a catastrophic incident. The introduced models show higher accuracy compared to previous works performed on the Bam earthquake dataset.

• Acute Kidney Injury
• Clinical Decision Rules
• Computer
• Decision Making
• Machine Learning
• Neural Networks

Recent studies have recognized several risk factors for cardiopulmonary bypass- (CPB-) associated acute kidney injury (AKI). However, the lack of early biomarkers for AKI prevents practitioners from intervening in a timely manner. We reviewed the literature with the aim of improving our understanding of the risk factors for CPB-associated AKI, which may increase our ability to prevent or improve this condition. Some novel early biomarkers for AKI have been introduced. In particular, a combinational use of these biomarkers would be helpful to improve clinical outcomes. Furthermore, we discuss several interventions that are aimed at managing CPB-associated AKI, may increase the effect of renal replacement therapy (RRT), and may contribute to preventing CPB-associated AKI. Collectively, the conclusions of this paper are limited by the availability of clinical trial evidence and conflicting definitions of AKI. A guideline is urgently needed for CPB-associated AKI.

• Acute kidney injury
• Artificial intelligence
• Decision support tool
• Machine learning
• Risk assessment

• Aged
• Blood Pressure
• Coronary Artery Bypass/adverse effects
• Female
• Heart Injuries/epidemiology
• Heart Injuries/etiology
• Hospital Mortality
• Humans
• Hypertension/complications
• Hypertension/diagnosis
• Male
• Middle Aged
• Postoperative Complications/epidemiology
• Predictive Value of Tests
• Preoperative Period
• Retrospective Studies
• Treatment Outcome
• Troponin T/blood

• Diagnosis
• Preventive medicine

• BIH Charité Clinician Scientist Program funded by the Charité – Universitätsmedizin Berlin and the Berlin Institute of Health
• Swiss National Science Foundation (SNSF) Ambizione Program under grant agreement no. 174025

Cardiac surgery–associated acute kidney injury (CSA-AKI) is a major complication that results in increased morbidity and mortality after cardiac surgery. Most established prediction models are limited to the analysis of nonlinear relationships and fail to fully consider intraoperative variables, which represent the acute response to surgery. Therefore, this study utilized an artificial intelligence–based machine learning approach thorough perioperative data-driven learning to predict CSA-AKI.

A total of 671 patients undergoing cardiac surgery from August 2016 to August 2018 were enrolled. AKI following cardiac surgery was defined according to criteria from Kidney Disease: Improving Global Outcomes (KDIGO). The variables used for analysis included demographic characteristics, clinical condition, preoperative biochemistry data, preoperative medication, and intraoperative variables such as time-series hemodynamic changes. The machine learning methods used included logistic regression, support vector machine (SVM), random forest (RF), extreme gradient boosting (XGboost), and ensemble (RF + XGboost). The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). We also utilized SHapley Additive exPlanation (SHAP) values to explain the prediction model.

Development of CSA-AKI was noted in 163 patients (24.3%) during the first postoperative week. Regarding the efficacy of the single model that most accurately predicted the outcome, RF exhibited the greatest AUC (0.839, 95% confidence interval [CI] 0.772–0.898), whereas the AUC (0.843, 95% CI 0.778–0.899) of ensemble model (RF + XGboost) was even greater than that of the RF model alone. The top 3 most influential features in the RF importance matrix plot were intraoperative urine output, units of packed red blood cells (pRBCs) transfused during surgery, and preoperative hemoglobin level. The SHAP summary plot was used to illustrate the positive or negative effects of the top 20 features attributed to the RF. We also used the SHAP dependence plot to explain how a single feature affects the output of the RF prediction model.

In this study, machine learning methods were successfully established to predict CSA-AKI, which determines risks following cardiac surgery, enabling the optimization of postoperative treatment strategies to minimize the postoperative complications following cardiac surgeries.

• Acute kidney injury
• Cardiac surgery
• Machine learning
• Prediction

Improving recognition of patients at increased risk of acute kidney injury (AKI) in the community may facilitate earlier detection and implementation of proactive prevention measures that mitigate the impact of AKI. The aim of this study was to develop and externally validate a practical risk score to predict the risk of AKI in either hospital or community settings using routinely collected data.

Routinely collected linked datasets from Tayside, Scotland, were used to develop the risk score and datasets from Kent in the UK and Alberta in Canada were used to externally validate it. AKI was defined using the Kidney Disease: Improving Global Outcomes serum creatinine–based criteria. Multivariable logistic regression analysis was performed with occurrence of AKI within 1 year as the dependent variable. Model performance was determined by assessing discrimination (C-statistic) and calibration.

The risk score was developed in 273 450 patients from the Tayside region of Scotland and externally validated into two populations: 218 091 individuals from Kent, UK and 1 173 607 individuals from Alberta, Canada. Four variables were independent predictors for AKI by logistic regression: older age, lower baseline estimated glomerular filtration rate, diabetes and heart failure. A risk score including these four variables had good predictive performance, with a C-statistic of 0.80 [95% confidence interval (CI) 0.80–0.81] in the development cohort and 0.71 (95% CI 0.70–0.72) in the Kent, UK external validation cohort and 0.76 (95% CI 0.75–0.76) in the Canadian validation cohort.

We have devised and externally validated a simple risk score from routinely collected data that can aid both primary and secondary care physicians in identifying patients at high risk of AKI.

• acute kidney
• epidemiology
• injury
• risk score

• AKI
• acute kidney injury
• artificial intelligence
• cardiac surgery
• machine learning
• nephrology

• Perioperative
• acute kidney injury
• nephrotoxicity
• surgery

• mortality
• pulse pressure
• renal dysfunction
• stroke
• surgery

• vascular stiffness
• pulse pressure hypertension
• cerebral blood flow autoregulation
• perioperative stroke

• Acute Kidney Injury/physiopathology
• Acute Kidney Injury/prevention & control
• Blood Pressure
• Cardiac Surgical Procedures/adverse effects
• Emergence Delirium/physiopathology
• Emergence Delirium/prevention & control
• Humans
• Monitoring, Physiologic/methods
• Perioperative Period
• Pulse Wave Analysis/methods
• Stroke/physiopathology
• Stroke/prevention & control
• Vascular Stiffness/physiology

• R01 HL092259 NHLBI NIH HHS

• acute renal failure
• cardiac surgery
• cardiopulmonary bypass

• acute kidney injury (AKI)
• big data and analytics
• electronic health record (EHR)
• outcomes
• pediatrics

• acute kidney injury
• cardiac surgery
• perioperative complications
• prediction

Machine learning approaches were introduced for better or comparable predictive ability than statistical analysis to predict postoperative outcomes. We sought to compare the performance of machine learning approaches with that of logistic regression analysis to predict acute kidney injury after cardiac surgery. We retrospectively reviewed 2010 patients who underwent open heart surgery and thoracic aortic surgery. Baseline medical condition, intraoperative anesthesia, and surgery-related data were obtained. The primary outcome was postoperative acute kidney injury (AKI) defined according to the Kidney Disease Improving Global Outcomes criteria. The following machine learning techniques were used: decision tree, random forest, extreme gradient boosting, support vector machine, neural network classifier, and deep learning. The performance of these techniques was compared with that of logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUC). During the first postoperative week, AKI occurred in 770 patients (38.3%). The best performance regarding AUC was achieved by the gradient boosting machine to predict the AKI of all stages (0.78, 95% confidence interval (CI) 0.75–0.80) or stage 2 or 3 AKI. The AUC of logistic regression analysis was 0.69 (95% CI 0.66–0.72). Decision tree, random forest, and support vector machine showed similar performance to logistic regression. In our comprehensive comparison of machine learning approaches with logistic regression analysis, gradient boosting technique showed the best performance with the highest AUC and lower error rate. We developed an Internet–based risk estimator which could be used for real-time processing of patient data to estimate the risk of AKI at the end of surgery.

• acute kidney injury
• cardiovascular surgery
• machine learning