Prediction Model For Acute Kidney Injury Research Articles

Validation of an acute kidney injury prediction model as a clinical decision support system.

Acute kidney injury (AKI) is a critical clinical condition that requires immediate intervention. We developed an artificial intelligence (AI) model called PRIME Solution to predict AKI and evaluated its ability to enhance clinicians' predictions. The PRIME Solution was developed using convolutional neural networks with residual blocks on 183,221 inpatient admissions from a tertiary hospital (2013-2017) and externally validated with 4,501 admissions at another tertiary hospital (2020-2021). To assess its application, we conducted a prospective evaluation using retrospectively collected data from 100 patients at the latter hospital, including 15 AKI cases. AKI prediction performance was compared among specialists, physicians, and medical students, both with and without AI assistance. Without assistance, specialists demonstrated the highest accuracy (0.797), followed by medical students (0.619) and the PRIME Solution (0.568). AI assistance improved overall recall (61.0% to 74.0%) and F1 scores (38.7% to 42.0%), while reducing average review time (73.8 to 65.4 seconds, p < 0.001). However, the impact varied across expertise levels. Specialists showed the greatest improvement (recall, 32.1% to 64.3%; F1, 36.4% to 48.6%), whereas medical students' performance improved but aligned more closely with the AI model. Additionally, the effect of AI assistance varied by prediction outcome, showing greater improvement in recall for cases predicted as AKI, and better precision, F1 score, and review time reduction (73.4 to 62.1 seconds, p < 0.001) for cases predicted as non-AKI. AKI predictions were enhanced by AI assistance, but the improvements varied according to the expertise of the user.

Prediction of acute kidney injury in intensive care unit patients based on interpretable machine learning.

Acute kidney injury (AKI) poses a lethal risk in intensive care unit (ICU) patients, where early detection is challenging. This study was to establish a prediction model for AKI 24 hours in advance for ICU patients and to help clinicians monitor patients at an early stage by key features. In this study, the Medical Information Mart for Intensive Care (MIMIC) databases were used to construct a dataset of critically ill patients. Predictive models were constructed using five machine learning algorithms based on MIMIC-IV data, and the best predictive model was selected by multiple model evaluation metrics. MIMIC-III data were used for external validation. We conducted an interpretability analysis of the model using SHapley Additive exPlanations (SHAP) to clarify key features and decision-making mechanisms. A total of 18,186 patient data were included in this study. The analysis combining calibration and decision curves demonstrated that the eXtreme Gradient Boosting (XGBoost) exhibited superior performance among the five algorithms, achieving an area under the receiver operating characteristic curve of 0.88. Interpretability analysis based on the XGBoost model showed diuretic use, mechanical ventilation, vasopressor use, age, and antibiotic use as the most important decision factors of the model. The SHAP summary plot was used to illustrate the effects of the top 19 features attributed to the XGBoost. The XGBoost algorithm can predict the occurrence of AKI more accurately. Interpretative analysis of the model reveals the mechanisms of key features, and reflects the individual differences between patients, providing an important clinical reference.

Contemporary contrast media dosing during percutaneous coronary intervention in patients with pre-existing renal impairment.

Contrast volume minimization can mitigate acute kidney injury (AKI) risk following percutaneous coronary intervention (PCI), but national data regarding contemporary contrast volume dosing patterns are lacking. The authors analyzed data from the National Cardiovascular Data Registry (NCDR) CathPCI registry to assess the prevalence and outcomes of renal function-based contrast dosing during PCI in patients with pre-existing renal impairment. The authors analyzed data from 463 753 patients with an eGFR ≤ 60 mL/min/1.73 m2, and categorized patients based on contrast volume/eGFR: high (> 3), low (1-3), and ultra-low (less than 1). eGFR was calculated using the Chronic Kidney Disease Epidemiology Collaboration creatinine equation. The primary outcome was occurrence of AKI. Outcomes were adjusted based on covariates derived from a validated AKI prediction model. The majority (51.4%) of patients received high contrast volume. Compared with patients who received low contrast volume, patients with high contrast volume use had a significantly higher incidence of AKI (adjusted OR 1.36 [1.28 to 1.45]) and a higher stage of AKI (adjusted OR 1.90 [1.80 to 2.00]). The incidence of AKI was similar between low and ultra-low contrast volume use. The development of new need for dialysis was higher in patients who received high contrast volume (2.8%) compared with those who received low contrast volume (0.8%) and ultra-low contrast volume (0.8%) (P less than .001). High contrast volume during PCI is associated with worse outcomes including AKI and new need for dialysis. Our study provides further support for the use of contrast volume less than 3 times the eGFR as a target to guide contrast dosing during PCI.

Acute kidney disease in hospitalized pediatric patients: risk prediction based on an artificial intelligence approach

Background Acute kidney injury (AKI) and acute kidney disease (AKD) are prevalent among pediatric patients, both linked to increased mortality and extended hospital stays. Early detection of kidney injury is crucial for improving outcomes. This study presents a machine learning-based risk prediction model for AKI and AKD in pediatric patients, enabling personalized risk predictions. Methods Data from 2,346 hospitalized pediatric patients, collected between January 2020 and January 2023, were divided into an 85% training set and a 15% test set. Predictive models were constructed using eight machine learning algorithms and two ensemble algorithms, with the optimal model identified through AUROC. SHAP was used to interpret the model, and an online prediction tool was developed with Streamlit to predict AKI and AKD. Results The incidence of AKI and AKD were 14.90% and 16.26%, respectively. Patients with AKD combined with AKI had the highest mortality rate, at 6.94%, when analyzed by renal function trajectories. The LightGBM algorithm showed superior predictive performance for both AKI and AKD (AUROC: 0.813, 0.744). SHAP identified top predictors for AKI as serum creatinine, white blood cell count, neutrophil count, and lactate dehydrogenase, while key predictors for AKD included proton pump inhibitor, blood glucose, hemoglobin, and AKI grade. Conclusion The high incidence of AKI and AKD among hospitalized children warrants attention. Renal function trajectories are strongly associated with prognosis. Supported by a web-based tool, machine learning models can effectively predict AKI and AKD, facilitating early identification of high-risk pediatric patients and potentially improving outcomes.

A Machine Learning-Based Prediction Model for Acute Kidney Injury in Patients With Community-Acquired Pneumonia: Multicenter Validation Study.

Acute kidney injury (AKI) is common in patients with community-acquired pneumonia (CAP) and is associated with increased morbidity and mortality. This study aimed to establish and validate predictive models for AKI in hospitalized patients with CAP based on machine learning algorithms. We trained and externally validated 5 machine learning algorithms, including logistic regression, support vector machine, random forest, extreme gradient boosting, and deep forest (DF). Feature selection was conducted using the sliding window forward feature selection technique. Shapley additive explanations and local interpretable model-agnostic explanation techniques were applied to the optimal model for visual interpretation. A total of 6371 patients with CAP met the inclusion criteria. The development of CAP-associated AKI (CAP-AKI) was recognized in 1006 (15.8%) patients. The 11 selected indicators were sex, temperature, breathing rate, diastolic blood pressure, C-reactive protein, albumin, white blood cell, hemoglobin, platelet, blood urea nitrogen, and neutrophil count. The DF model achieved the best area under the receiver operating characteristic curve (AUC) and accuracy in the internal (AUC=0.89, accuracy=0.90) and external validation sets (AUC=0.87, accuracy=0.83). Furthermore, the DF model had the best calibration among all models. In addition, a web-based prediction platform was developed to predict CAP-AKI. The model described in this study is the first multicenter-validated AKI prediction model that accurately predicts CAP-AKI during hospitalization. The web-based prediction platform embedded with the DF model serves as a user-friendly tool for early identification of high-risk patients.

A genotype-guided prediction model for the incidence of persistent acute kidney injury following lung transplantation

BackgroundThis study aimed to develop a nomogram for predicting persistent renal dysfunction in acute kidney injury (AKI) following lung transplantation (LTx).MethodA total of 229 LTx patients were enrolled, and genotyping for 153 single nucleotide polymorphisms (SNPs) was performed. The cohort was randomly divided into training (n = 183) and validation (n = 46) sets in an 8:2 ratio. Statistically significant SNPs identified through pharmacogenomic analysis were combined with clinical factors to construct a comprehensive prediction model for persistent AKI using multivariate logistic regression analysis. Discrimination and calibration analyses were conducted to evaluate the performance of the model. Decision curve analysis was used to assess its clinical utility. Due to the small sample size, bootstrap internal sampling with 500 iterations was adopted for validation to prevent overfitting of the model.ResultsThe final nomogram comprised nine predictors, including body mass index, thrombin time, tacrolimus initial concentration, rs757210, rs1799884, rs6887695, rs1494558, rs2069762 and rs2275913. In the training set, the area under the receiver operating characteristic curve of the nomogram was 0.781 (95%CI: 0.715–0.846), while in the validation set it was 0.698 (95%CI: 0.542–0.855), indicating good model fit. As demonstrated by 500 Bootstrap internal sampling validations, the model has high discrimination and calibration. Additionally, decision curve analysis confirmed its clinical applicability.ConclusionThis study presents a genotype-guided nomogram that can be used to assess the risk of persistent AKI following LTx and may assist in guiding personalized prevention strategies in clinical practice.

Machine-learning based prediction model for acute kidney injury induced by multiple wasp stings

Acute kidney injury (AKI) following multiple wasp stings is a severe complication with potentially poor outcomes. Despite extensive research on AKI's risk factors, predictive models for wasp sting-related AKI are limited. This study aims to develop and validate a machine learning-based clinical prediction model for AKI in individuals with wasp stings. In this retrospective cohort study, conducted at a tertiary teaching hospital in Yichang, China, from July 2013 to April 2023, 214 patients with wasp sting injuries were analyzed. Using least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression, prognostic variables for AKI were identified. A nomogram incorporating these four variables was constructed. The model's performance was assessed through internal validation, leave-one-out cross-validation, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA). Among 214 patients affected by wasp stings, 34.6% (74/214) developed AKI. Following LASSO regression and multivariate logistic regression, the number of stings, presence of gross hematuria, systemic inflammatory response index (SIRI), and platelet count were identified as prognostic factors. A nomogram was constructed and evaluated for its predictive accuracy, showing an area under the curve (AUC) of 0.757 (95% CI 0.711 to 0.804) and a concordance index (C-index) of 0.75. Validation confirmed the model's reliability and superior discrimination ability over existing models, as demonstrated by NRI, IDI, and DCA. The developed nomogram effectively predicts AKI risk in wasp sting patients, facilitating early identification and management of those at risk.

Electronic Alert Systems for Patients With Acute Kidney Injury

The acute kidney injury (AKI) electronic alert (e-alert) system was hypothesized to improve the outcomes of AKI. However, its association with different patient outcomes and clinical practice patterns remains systematically unexplored. To assess the association of AKI e-alerts with patient outcomes (mortality, AKI progression, dialysis, and kidney recovery) and clinical practice patterns. A search of Embase and PubMed on March 18, 2024, and a search of the Cochrane Library on March 20, 2024, to identify all relevant studies. There were no limitations on language or article types. Studies evaluating the specified outcomes in adult patients with AKI comparing AKI e-alerts with standard care or no e-alerts were included. Studies were excluded if they were duplicate cohorts, had insufficient outcome data, or had no control group. Two investigators independently extracted data and assessed bias. The systematic review and meta-analysis followed the PRISMA guidelines. Random-effects model meta-analysis, with predefined subgroup analysis and trial sequential analyses, were conducted. Primary outcomes included mortality, AKI progression, dialysis, and kidney recovery. Secondary outcomes were nephrologist consultations, post-AKI exposure to nonsteroidal anti-inflammatory drugs (NSAID), post-AKI angiotensin-converting enzyme inhibitor and/or angiotensin receptor blocker (ACEI/ARB) prescription, hospital length of stay, costs, and AKI documentation. Thirteen unique studies with 41 837 unique patients were included (mean age range, 60.5-79.0 years]; 29.3%-48.5% female). The risk ratios (RRs) for the AKI e-alerts group compared with standard care were 0.96 for mortality (95% CI, 0.89-1.03), 0.91 for AKI stage progression (95% CI, 0.84-0.99), 1.16 for dialysis (95% CI, 1.05-1.28), and 1.13 for kidney recovery (95% CI, 0.86-1.49). The AKI e-alerts group had RRs of 1.45 (95% CI, 1.04-2.02) for nephrologist consultation, 0.75 (95% CI, 0.59-0.95) for post-AKI NSAID exposure. The pooled RR for post-AKI ACEI/ARB exposure in the AKI e-alerts group compared with the control group was 0.91 (95% CI, 0.78-1.06) and 1.28 (95% CI, 1.04-1.58) for AKI documentation. Use of AKI e-alerts was not associated with lower hospital length of stay (mean difference, -0.09 [95% CI, -0.47 to 0.30] days) or lower cost (mean difference, US $655.26 [95% CI, -$656.98 to $1967.5]) but was associated with greater AKI documentation (RR, 1.28 [95% CI, 1.04-1.58]). Trial sequential analysis confirmed true-positive results of AKI e-alerts on increased nephrologist consultations and reduced post-AKI NSAID exposure and its lack of association with mortality. In this systematic review and meta-analysis, AKI e-alerts were not associated with a lower risk for mortality but were associated with changes in clinical practices. They were associated with lower risk for AKI progression. Further research is needed to confirm these results and integrate early AKI markers or prediction models to improve outcomes.

Changes in urinary renal injury markers in children with Mycoplasma pneumoniae pneumonia and a prediction model for related early renal injury

BackgroundThis study aims to analyse changes in urinary kidney injury markers in children with Mycoplasma pneumoniae pneumonia (MPP), investigate the risk factors for MPP-related acute kidney injury (AKI) and establish a model to predict MPP-related AKI.MethodsNinety-five children were enrolled based on the study’s inclusion and exclusion criteria. They were divided into a severe MPP (SMPP) group and a non-SMPP group and then into an AKI group and a non-AKI group according to the presence of AKI. A univariate logistic regression analysis was performed to explore the early risk factors for AKI. Based on a multivariate logistic regression analysis and a least absolute shrinkage and selection operator regression analysis, appropriate variables were selected to establish a prediction model, and R 4.2.2 software was used to draw nomograms and generate a dynamic nomogram website.ResultsSeven urinary kidney injury markers were abnormally elevated in the SMPP group and the non-SMPP group: urinary N-acetyl-β-D-glucosaminidase (NAG), β2-microglobulin, α1-microglobulin, retinol-binding protein, urinary immunoglobulin G, urinary transferrin and urinary microalbumin. Sixteen children were identified with AKI during hospitalisation. The AKI group had higher levels of urinary NAG, α1-microglobulin, β2-microglobulin, urinary microalbumin, urinary transferrin and retinol-binding protein than the non-AKI group (P < 0.05). The MPP-related AKI prediction model consists of four indicators (serum immunoglobulin M [IgM], C-reactive protein [CRP], urine NAG and sputum plug presence) and a dynamic nomogram.ConclusionUrinary kidney injury markers are often elevated in children with MPP; urinary NAG is the marker most likely to be elevated, and it is especially evident in severe cases. The nomogram of the prediction model, comprising serum IgM, CRP, urinary NAG and sputum plug presence, can predict the probability of AKI in children with MPP.

Perioperative Changes in Plasma Nitrite and IL-6 Levels Predict Postoperative Atrial Fibrillation (POAF) and Acute Kidney Injury (AKI) after Cardiac Surgery.

Background: Postoperative atrial fibrillation (POAF) and acute kidney injury (AKI) are common yet significant complications after cardiac surgery, with incidences of up to 40% for each. Here, we assessed plasma nitrite and serum interleukin-6 (IL-6) levels before and after cardiac surgery to quantify the extent to which oxidative stress and inflammation contribute to POAF and AKI occurrence. Methods: We prospectively enrolled 206 cardiac surgical patients. Plasma nitrite and serum IL-6 levels were determined preoperatively and at 24 h, 48 h and 72 h postoperatively. The patients had continuous EKG monitoring for occurrence of POAF, while daily serum creatinine was measured for determination of stage 1 + AKI. Results: Postoperatively, 78 (38%) patients experienced AF, and 47 (23%) patients experienced stage 1 + AKI. POAF analysis: Age, ACE-inhibitor use, valve surgery and percent change in baseline plasma nitrite at 24 h postoperatively were associated with POAF in multiple logistic regression analysis. The inclusion of this new biomarker significantly improved the POAF prediction model (AUC 0.77 for clinical risk factors alone, to AUC 0.81). AKI analysis: A history of diabetes mellitus was associated with AKI in multiple logistic regression analysis, and the addition of preoperative IL-6 levels improved the prediction model for AKI occurrence (AUC 0.69 to AUC 0.74). Conclusions: We previously observed selective upregulation of NADPH oxidase isoform 4 (NOX4) in patients with AF, a critical causal role of NOX4 for AF in zebrafish and a robust inhibitory effect of nitric oxide (NO) on NOX4. Our data innovatively demonstrate that a reduction in circulating nitrite levels, likely implicative of elevated NOX4-mediated oxidative stress, independently associates with POAF and improves POAF prediction, whereas the inclusion of circulating IL-6 levels improves the prediction model for AKI. Therefore, therapeutic strategies to mitigate these pathophysiological sequalae of surgical stress may reduce the incidence of severe postoperative complications of POAF and AKI.

Diagnostic Validation of the Updated Pediatric Sepsis Biomarker Risk II for Acute Kidney Injury Prediction Model in Pediatric Septic Shock.

We previously derived the updated Pediatric Sepsis Biomarker Risk for Acute Kidney Injury (PERSEVERE-II AKI) prediction model, which had robust diagnostic test characteristics for severe AKI on day 3 (D3 severe AKI) of septic shock. We now sought to validate this model in an independent cohort of children to the one in which the model was developed. A secondary analysis of a multicenter, prospective, observational study carried out from January 2019 to December 2022. Ten PICUs in the United States. Children with septic shock 1 week to 18 years old admitted to the PICU. None. Seventy-nine of 363 patients (22%) had D3 severe AKI, defined as Kidney Disease Improving Global Outcomes stage 2 or higher. Patients were assigned a probability of D3 severe AKI using the PERSEVERE-II AKI model. The model predicted D3 severe AKI with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.85-0.93), sensitivity of 77% (95% CI, 66-86%), specificity of 88% (95% CI, 84-92%), positive predictive value of 65% (95% CI, 54-74%), and negative predictive value of 93% (95% CI, 89-96%). These data represent an increase in post-test probability of D3 severe AKI with a positive test from 22% to 65%, and a prevalence threshold of 28%. On multivariable regression, the PERSEVERE-II AKI prediction model demonstrated greater adjusted odds ratio (aOR) for D3 severe AKI (aOR, 11.2; 95% CI, 4.9-25.3) and lesser aOR for failure of D3 renal recovery from early AKI (aOR, 0.31; 95% CI, 0.13-0.69). The PERSEVERE-II AKI model demonstrates consistently robust performance for prediction of new or persistent D3 severe AKI in children with septic shock. A major limitation is that actual D3 severe AKI prevalence is below the prevalence threshold for the test, and thus future work should focus on evaluating use in enriched populations.

Artificial intelligence algorithms permits rapid acute kidney injury risk classification of patients with acute myocardial infarction

ObjectiveThis study aimed to develop and validate several artificial intelligence (AI) models to identify acute myocardial infarction (AMI) patients at an increased risk of acute kidney injury (AKI) during hospitalization. MethodsIncluded were patients diagnosed with AMI from the Medical Information Mart for Intensive Care (MIMIC) III and IV databases. Two cohorts of AMI patients from Changzhou Second People's Hospital and Xuzhou Center Hospital were used for external validation of the models. Patients' demographics, vital signs, clinical characteristics, laboratory results, and therapeutic measures were extracted. Totally, 12 AI models were developed. The area under the receiver operating characteristic curve (AUC) were calculated and compared. ResultsAKI occurred during hospitalization in 1098 (28.3 %) of the 3882 final enrolled patients, split into training (3105) and test (777) sets randomly. Among them, Random Forest (RF), C5.0 and Bagged CART models outperformed the other models in both the training and test sets. The AUCs for the test set were 0.754, 0.734 and 0.730, respectively. The incidence of AKI was 9.8 % and 9.5 % in 2202 patients in the Changzhou cohort and 807 patients in the Xuzhou cohort with AMI, respectively. The AUCs for patients in the Changzhou cohort were RF, 0.761; C5.0, 0.733; and bagged CART, 0.725, respectively, and Xuzhou cohort were RF, 0.799; C5.0, 0.808; and bagged CART, 0.784, respectively. ConclusionSeveral machines learning-based prediction models for AKI after AMI were developed and validated. The RF, C5.0 and Bagged CART model performed robustly in identifying high-risk patients earlier. Clinical trial approval statementThis Trial was registered in the Chinese clinical trials registry: ChiCTR1800014583. Registered January 22, 2018 (http://www.chictr.org.cn/searchproj.aspx).

Time Series AI Model for Acute Kidney Injury Detection Based on a Multicenter Distributed Research Network: Development and Verification Study.

Acute kidney injury (AKI) is a marker of clinical deterioration and renal toxicity. While there are many studies offering prediction models for the early detection of AKI, those predicting AKI occurrence using distributed research network (DRN)-based time series data are rare. In this study, we aimed to detect the early occurrence of AKI by applying an interpretable long short-term memory (LSTM)-based model to hospital electronic health record (EHR)-based time series data in patients who took nephrotoxic drugs using a DRN. We conducted a multi-institutional retrospective cohort study of data from 6 hospitals using a DRN. For each institution, a patient-based data set was constructed using 5 drugs for AKI, and an interpretable multivariable LSTM (IMV-LSTM) model was used for training. This study used propensity score matching to mitigate differences in demographics and clinical characteristics. Additionally, the temporal attention values of the AKI prediction model's contribution variables were demonstrated for each institution and drug, with differences in highly important feature distributions between the case and control data confirmed using 1-way ANOVA. This study analyzed 8643 and 31,012 patients with and without AKI, respectively, across 6 hospitals. When analyzing the distribution of AKI onset, vancomycin showed an earlier onset (median 12, IQR 5-25 days), and acyclovir was the slowest compared to the other drugs (median 23, IQR 10-41 days). Our temporal deep learning model for AKI prediction performed well for most drugs. Acyclovir had the highest average area under the receiver operating characteristic curve score per drug (0.94), followed by acetaminophen (0.93), vancomycin (0.92), naproxen (0.90), and celecoxib (0.89). Based on the temporal attention values of the variables in the AKI prediction model, verified lymphocytes and calcvancomycin ium had the highest attention, whereas lymphocytes, albumin, and hemoglobin tended to decrease over time, and urine pH and prothrombin time tended to increase. Early surveillance of AKI outbreaks can be achieved by applying an IMV-LSTM based on time series data through an EHR-based DRN. This approach can help identify risk factors and enable early detection of adverse drug reactions when prescribing drugs that cause renal toxicity before AKI occurs.

Machine learning-based model to predict severe acute kidney injury after total aortic arch replacement for acute type A aortic dissection

BackgroundSevere acute kidney injury (AKI) after total aortic arch replacement (TAAR) is related to adverse outcomes in patients with acute type A aortic dissection (ATAAD). However, the early prediction of severe AKI remains a challenge. This study aimed to develop a novel model to predict severe AKI after TAAR in ATAAD patients using machine learning algorithms. MethodsA total of 572 ATAAD patients undergoing TAAR were enrolled in this retrospective study, and randomly divided into a training set (70 %) and a validation set (30 %). Lasso regression, support vector machine-recursive feature elimination and random forest algorithms were used to screen indicators for severe AKI (defined as AKI stage III) in the training set, respectively. Then the intersection indicators were selected to construct models through artificial neural network (ANN) and logistic regression. The AUC-ROC curve was employed to ascertain the prediction efficacy of the ANN and logistic regression models. ResultsThe incidence of severe AKI after TAAR was 22.9 % among ATAAD patients. The intersection predictors identified by different machine learning algorithms were baseline serum creatinine and ICU admission variables, including serum cystatin C, procalcitonin, aspartate transaminase, platelet, lactic dehydrogenase, urine N-acetyl-β-d-glucosidase and Acute Physiology and Chronic Health Evaluation II score. The ANN model showed a higher AUC-ROC than logistic regression (0.938 vs 0.908, p < 0.05). Furthermore, the ANN model could predict 89.1 % of severe AKI cases beforehand. In the validation set, the superior performance of the ANN model was further confirmed in terms of discrimination ability (AUC = 0.916), calibration curve analysis and decision curve analysis. ConclusionThis study developed a novel and reliable clinical prediction model for severe AKI after TAAR in ATAAD patients using machine learning algorithms. Importantly, the ANN model showed a higher predictive ability for severe AKI than logistic regression.

Validation of a Prediction Model for Acute Kidney Injury after Cardiac Surgery in a Retrospective Asian Cohort.

Background: The incidence of postoperative acute kidney injury (AKI) is relatively high in some Asian regions. The objective of this study was to examine the performance of an AKI prediction model developed based on data from a White-dominant population in a retrospective Asian cohort of patients undergoing cardiovascular surgery. Methods: We retrospectively identified 549 patients who underwent elective major cardiovascular surgery (coronary artery bypass graft, valve surgery, and aorta surgery), and excluded those who underwent a percutaneous cardiovascular procedure. Patients with a baseline estimated glomerular filtration rate (eGFR) < 60 mL/min/1.73 m2 were also excluded. AKI was defined according to the Kidney Disease: Improving Global Outcomes (KDIGO) definition. Performance of the prediction model for AKI was expressed as area under the receiver operating characteristic curve (AUC). Results: The prediction model had a good predictive accuracy for postoperative AKI (all AUC > 0.92). The AUC of the prediction model in subgroups of age (<65 years and ≥65 years), sex (male and female), hypertension, and diabetes were all >0.85 (all p values < 0.001). Conclusions: The model could be used to predict postoperative AKI in Asian patients undergoing cardiovascular surgery with a baseline eGFR ≥ 60 mL/min/1.73 m2.

Interpretable machine learning-based individual analysis of acute kidney injury in immune checkpoint inhibitor therapy.

Acute kidney injury (AKI) is a critical complication of immune checkpoint inhibitor therapy. Since the etiology of AKI in patients undergoing cancer therapy varies, clarifying underlying causes in individual cases is critical for optimal cancer treatment. Although it is essential to individually analyze immune checkpoint inhibitor-treated patients for underlying pathologies for each AKI episode, these analyses have not been realized. Herein, we aimed to individually clarify the underlying causes of AKI in immune checkpoint inhibitor-treated patients using a new clustering approach with Shapley Additive exPlanations (SHAP). We developed a gradient-boosting decision tree-based machine learning model continuously predicting AKI within 7 days, using the medical records of 616 immune checkpoint inhibitor-treated patients. The temporal changes in individual predictive reasoning in AKI prediction models represented the key features contributing to each AKI prediction and clustered AKI patients based on the features with high predictive contribution quantified in time series by SHAP. We searched for common clinical backgrounds of AKI patients in each cluster, compared with annotation by three nephrologists. One hundred and twelve patients (18.2%) had at least one AKI episode. They were clustered per the key feature, and their SHAP value patterns, and the nephrologists assessed the clusters' clinical relevance. Receiver operating characteristic analysis revealed that the area under the curve was 0.880. Patients with AKI were categorized into four clusters with significant prognostic differences (p = 0.010). The leading causes of AKI for each cluster, such as hypovolemia, drug-related, and cancer cachexia, were all clinically interpretable, which conventional approaches cannot obtain. Our results suggest that the clustering method of individual predictive reasoning in machine learning models can be applied to infer clinically critical factors for developing each episode of AKI among patients with multiple AKI risk factors, such as immune checkpoint inhibitor-treated patients.

Development of interpretable machine learning models for prediction of acute kidney injury after noncardiac surgery: a retrospective cohort study.

Early identification of patients at high-risk of postoperative acute kidney injury (AKI) can facilitate the development of preventive approaches. This study aimed to develop prediction models for postoperative AKI in noncardiac surgery using machine learning algorithms. The authors also evaluated the predictive performance of models that included only preoperative variables or only important predictors. Adult patients undergoing noncardiac surgery were retrospectively included in the study (76457 patients in the discovery cohort and 11910 patients in the validation cohort). AKI was determined using the KDIGO criteria. The prediction model was developed using 87 variables (56 preoperative variables and 31 intraoperative variables). A variety of machine learning algorithms were employed to develop the model, including logistic regression, random forest, extreme gradient boosting, and gradient boosting decision trees. The performance of different models was compared using the area under the receiver operating characteristic curve (AUROC). Shapley Additive Explanations (SHAP) analysis was employed for model interpretation. The patients in the discovery cohort had a median age of 52 years (IQR: 42-61 years), and 1179 patients (1.5%) developed AKI after surgery. The gradient boosting decision trees algorithm showed the best predictive performance using all available variables, or only preoperative variables. The AUROCs were 0.849 (95% CI: 0.835-0.863) and 0.828 (95% CI: 0.813-0.843), respectively. The SHAP analysis showed that age, surgical duration, preoperative serum creatinine, and gamma-glutamyltransferase, as well as American Society of Anesthesiologists physical status III were the most important five features. When gradually reducing the features, the AUROCs decreased from 0.852 (including the top 40 features) to 0.839 (including the top 10 features). In the validation cohort, the authors observed a similar pattern regarding the models' predictive performance. The machine learning models the authors developed had satisfactory predictive performance for identifying high-risk postoperative AKI patients. Furthermore, the authors found that model performance was only slightly affected when only preoperative variables or only the most important predictive features were included.

Acute kidney injury prediction model utility in premature myocardial infarction

The incidence of premature myocardial infarction (PMI) has been rising and acute kidney injury (AKI) occurring in PMI patients severely impacts prognosis. This study aimed to develop and validate a prediction model for AKI specific to PMI patients. The MIMIC-Ⅲ-CV and MIMIC-Ⅳ databases were utilized for model derivation of PMI patients. Single-center data served for external validation. There were 571 and 182 AKI patients in the training set (n= 937) and external validation set (n= 292) cohorts, respectively. Finally, a 7-variable model consisting of: Sequential Organ Failure Assessment (SOFA) score, coronary artery bypass grafting (CABG), ICU stay time, loop diuretics, estimated glomerular filtration rate (eGFR) HCO3- and Albumin was developed, achieving an AUC of 0.85 (95% CI: 0.83-0.88) in the training set. External validation also confirmed model robustness. This model may assist clinicians in the early identification of patients at elevated risk for PMI. Further validation is warranted before clinical application.

Prognostic significance of preoperative nutritional status for postoperative acute kidney injury in older patients undergoing major abdominal surgery: a retrospective cohort study.

The association between malnutrition and postoperative acute kidney injury (AKI) has not been well studied. In this study, the authors examined the association between preoperative nutritional status and postoperative AKI in older patients who underwent major abdominal surgery, as well as the predictive value of malnutrition for AKI. The authors retrospectively included patients aged 65 or older who underwent major elective abdominal surgery. The nutritional status of the patient was evaluated using three objective nutritional indices, such as the geriatric nutritional risk index (GNRI), the prognostic nutritional index (PNI), and the controlling nutritional status (CONUT). AKI was determined using the KDIGO criteria. The authors performed logistic regression analysis to investigate the association between preoperative nutritional status and postoperative AKI, as well as the predictive value of nutritional scores for postoperative AKI. A total of 2775 patients were included in the study, of which 707 (25.5%), 291 (10.5%), and 517 (18.6%) had moderate to severe malnutrition according to GNRI, PNI, and CONUT calculations. After surgery, 144 (5.2%) patients developed AKI, 86.1% at stage 1, 11.1% at stage 2, and 2.8% at stage 3 as determined by KDIGO criteria. After adjustment for traditional risk factors, worse nutritional scores were associated with a higher AKI risk. In addition to traditional risk factors, these nutritional indices improved the predictive ability of AKI prediction models, as demonstrated by significant improvements in integrated discrimination and net reclassification. Poor preoperative nutritional status, as assessed by GNRI, PNI, and CONUT scores, was associated with an increased risk of postoperative AKI. Incorporating these scores into AKI prediction models improved their performance. These findings emphasize the need for screening surgical patients for malnutrition risk. Further research is needed to determine whether preoperative malnutrition assessment and intervention can reduce postoperative AKI incidence.

Construction and validation of a risk assessment model for acute kidney injury in patients with acute pancreatitis in the intensive care unit

BackgroundTo construct and validate a risk assessment model for acute kidney injury (AKI) in patients with acute pancreatitis (AP) in the intensive care unit (ICU).MethodsA total of 963 patients diagnosed with acute pancreatitis (AP) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database was included. These patients were randomly divided into training set (N = 674) and validation set (N = 289) at a ratio of 7:3. Clinical characteristics were utilized to establish a nomogram for the prediction of AKI during ICU stay. These variables were selected by the least absolute shrinkage and selection operation (LASSO) regression and included in multivariate logistic regression analysis. Variables with P-values less than 0.05 were included in the final model. A nomogram was constructed based on the final model. The predicted accuracy of the nomogram was assessed by calculating the receiver operating characteristic curve (ROC) and the area under the curve (AUC). Moreover, calibration curves and Hosmer-Lemeshow goodness-of-fit test (HL test) were performed to evaluate model performance. Decision curve analysis (DCA) evaluated the clinical net benefit of the model.ResultsA multivariable model that included 6 variables: weight, SOFA score, white blood cell count, albumin, chronic heart failure, and sepsis. The C-index of the nomogram was 0.82, and the area under the receiver operating characteristic curve (AUC) of the training set and validation set were 0.82 (95% confidence interval:0.79–0.86) and 0.76 (95% confidence interval: 0.70–0.82), respectively. Calibration plots showed good consistency between predicted and observed outcomes in both the training and validation sets. DCA confirmed the clinical value of the model and its good impact on actual decision-making.ConclusionWe identified risk factors associated with the development of AKI in patients with AP. A risk prediction model for AKI in ICU patients with AP was constructed, and improving the treatment strategy of relevant factors in the model can reduce the risk of AKI in AP patients.