Automated Continuous Acute Kidney Injury Prediction and Surveillance: A Random Forest Model

A risk prediction model based on machine learning algorithm for parastomal hernia after permanent colostomy

OBJECTIVE

To develop a machine learning-based risk prediction model for postoperative parastomal hernia (PSH) in colorectal cancer patients undergoing permanent colostomy, assisting nurses in identifying high-risk groups and devising preventive care strategies.

METHODS

A case-control study was conducted on 495 colorectal cancer patients who underwent permanent colostomy at the Second Affiliated Hospital of Anhui Medical University from June 2017 to June 2023, with a 1-year follow-up period. Patients were categorized into PSH and non-PSH groups based on PSH occurrence within 1-year post-operation. Data were split into training (70%) and testing (30%) sets. Variable selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, and binary classification prediction models were established using Logistic Regression (LR), Support Vector Classification (SVC), K Nearest Neighbor (KNN), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XgBoost). The binary classification label denoted 1 for PSH occurrence and 0 for no PSH occurrence. Parameters were optimized via 5-fold cross-validation. Model performance was evaluated using Area Under Curve (AUC), specificity, sensitivity, accuracy, positive predictive value, negative predictive value, and F1-score. Clinical utility was evaluated using decision curve analysis (DCA), model explanation was enhanced using shapley additive explanation (SHAP), and model visualization was achieved using a nomogram.

RESULTS

The incidence of PSH within 1 year was 29.1% (144 patients). Among the models tested, the RF model demonstrated the highest discrimination capability with an AUC of 0.888 (95% CI: 0.881-0.935), along with superior specificity, accuracy, sensitivity, and F1 score. It also showed the highest clinical net benefit on the DCA curve. SHAP analysis identified the top 10 influential variables associated with PSH risk: body mass index (BMI), operation duration, history and status of chronic obstructive pulmonary disease (COPD), prealbumin, tumor node metastasis (TNM) staging, stoma site, thickness of rectus abdominis muscle (TRAM), C-reactive protein CRP, american society of anesthesiologists physical status classification (ASA), and stoma diameter. These insights from SHAP plots illustrated how these factors influence individual PSH outcomes. The nomogram was used for model visualization.

CONCLUSION

The Random Forest model demonstrated robust predictive performance and clinical relevance in forecasting colonic PSH. This model aids in early identification of high-risk patients and guides preventive care.

Forecasting acute kidney injury and resource utilization in ICU patients using longitudinal, multimodal models

BACKGROUND

Advances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive.

OBJECTIVE

This study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database.

METHODS

We conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT.

RESULTS

Our multimodal model achieved a lead time of at least 12 h ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT.

CONCLUSION

Our study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.

Interpretable machine learning model for predicting acute kidney injury in critically ill patients

BACKGROUND

This study aimed to create a method for promptly predicting acute kidney injury (AKI) in intensive care patients by applying interpretable, explainable artificial intelligence techniques.

METHODS

Population data regarding intensive care patients were derived from the Medical Information Mart for Intensive Care IV database from 2008 to 2019. Machine learning (ML) techniques with six methods were created to construct the predicted models for AKI. The performance of each ML model was evaluated by comparing the areas under the curve (AUC). Local Interpretable Model-Agnostic Explanations (LIME) method and Shapley Additive exPlanation values were used to decipher the best model.

RESULTS

According to inclusion and exclusion criteria, 53,150 severely sick individuals were included in the present study, of which 42,520 (80%) were assigned to the training group, and 10,630 (20%) were allocated to the validation group. Compared to the other five ML models, the eXtreme Gradient Boosting (XGBoost) model greatly predicted AKI following ICU admission, with an AUC of 0.816. The top four contributing variables of the XGBoost model were SOFA score, weight, mechanical ventilation, and the Simplified Acute Physiology Score II. An AKI and Non-AKI cases were predicted separately using the LIME algorithm.

CONCLUSION

Overall, the constructed clinical feature-based ML models are excellent in predicting AKI in intensive care patients. It would be constructive for physicians to provide early support and timely intervention measures to intensive care patients at risk of AKI.

Forecasting Acute Kidney Injury and Resource Utilization in ICU patients using longitudinal, multimodal models

Background

Advances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive.

Objective

This study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database.

Methods

We conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT.

Results

Our multimodal model achieved a lead time of at least 12 hours ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT.

Conclusion

Our study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.

A Machine Learning Algorithm Predicting Acute Kidney Injury in Intensive Care Unit Patients (NAVOY Acute Kidney Injury): Proof-of-Concept Study

BACKGROUND

Acute kidney injury (AKI) represents a significant global health challenge, leading to increased patient distress and financial health care burdens. The development of AKI in intensive care unit (ICU) settings is linked to prolonged ICU stays, a heightened risk of long-term renal dysfunction, and elevated short- and long-term mortality rates. The current diagnostic approach for AKI is based on late indicators, such as elevated serum creatinine and decreased urine output, which can only detect AKI after renal injury has transpired. There are no treatments to reverse or restore renal function once AKI has developed, other than supportive care. Early prediction of AKI enables proactive management and may improve patient outcomes.

OBJECTIVE

The primary aim was to develop a machine learning algorithm, NAVOY Acute Kidney Injury, capable of predicting the onset of AKI in ICU patients using data routinely collected in ICU electronic health records. The ultimate goal was to create a clinical decision support tool that empowers ICU clinicians to proactively manage AKI and, consequently, enhance patient outcomes.

METHODS

We developed the NAVOY Acute Kidney Injury algorithm using a hybrid ensemble model, which combines the strengths of both a Random Forest (Leo Breiman and Adele Cutler) and an XGBoost model (Tianqi Chen). To ensure the accuracy of predictions, the algorithm used 22 clinical variables for hourly predictions of AKI as defined by the Kidney Disease: Improving Global Outcomes guidelines. Data for algorithm development were sourced from the Massachusetts Institute of Technology Lab for Computational Physiology Medical Information Mart for Intensive Care IV clinical database, focusing on ICU patients aged 18 years or older.

RESULTS

The developed algorithm, NAVOY Acute Kidney Injury, uses 4 hours of input and can, with high accuracy, predict patients with a high risk of developing AKI 12 hours before onset. The prediction performance compares well with previously published prediction algorithms designed to predict AKI onset in accordance with Kidney Disease: Improving Global Outcomes diagnosis criteria, with an impressive area under the receiver operating characteristics curve (AUROC) of 0.91 and an area under the precision-recall curve (AUPRC) of 0.75. The algorithm's predictive performance was externally validated on an independent hold-out test data set, confirming its ability to predict AKI with exceptional accuracy.

CONCLUSIONS

NAVOY Acute Kidney Injury is an important development in the field of critical care medicine. It offers the ability to predict the onset of AKI with high accuracy using only 4 hours of data routinely collected in ICU electronic health records. This early detection capability has the potential to strengthen patient monitoring and management, ultimately leading to improved patient outcomes. Furthermore, NAVOY Acute Kidney Injury has been granted Conformite Europeenne (CE)-marking, marking a significant milestone as the first CE-marked AKI prediction algorithm for commercial use in European ICUs.

Federated machine learning for predicting acute kidney injury in critically ill patients: a multicenter study in Taiwan

Purpose

To address the contentious data sharing across hospitals, this study adopted a novel approach, federated learning (FL), to establish an aggregate model for acute kidney injury (AKI) prediction in critically ill patients in Taiwan.

Methods

This study used data from the Critical Care Database of Taichung Veterans General Hospital (TCVGH) from 2015 to 2020 and electrical medical records of the intensive care units (ICUs) between 2018 and 2020 of four referral centers in different areas across Taiwan. AKI prediction models were trained and validated thereupon. An FL-based prediction model across hospitals was then established.

Results

The study included 16,732 ICU admissions from the TCVGH and 38,424 ICU admissions from the other four hospitals. The complete model with 60 features and the parsimonious model with 21 features demonstrated comparable accuracies using extreme gradient boosting, neural network (NN), and random forest, with an area under the receiver-operating characteristic (AUROC) curve of approximately 0.90. The Shapley Additive Explanations plot demonstrated that the selected features were the key clinical components of AKI for critically ill patients. The AUROC curve of the established parsimonious model for external validation at the four hospitals ranged from 0.760 to 0.865. NN-based FL slightly improved the model performance at the four centers.

Conclusion

A reliable prediction model for AKI in ICU patients was developed with a lead time of 24 h, and it performed better when the novel FL platform across hospitals was implemented.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13755-023-00248-5.

Digital health and acute kidney injury: consensus report of the 27th Acute Disease Quality Initiative workgroup

Acute kidney injury (AKI), which is a common complication of acute illnesses, affects the health of individuals in community, acute care and post-acute care settings. Although the recognition, prevention and management of AKI has advanced over the past decades, its incidence and related morbidity, mortality and health care burden remain overwhelming. The rapid growth of digital technologies has provided a new platform to improve patient care, and reports show demonstrable benefits in care processes and, in some instances, in patient outcomes. However, despite great progress, the potential benefits of using digital technology to manage AKI has not yet been fully explored or implemented in clinical practice. Digital health studies in AKI have shown variable evidence of benefits, and the digital divide means that access to digital technologies is not equitable. Upstream research and development costs, limited stakeholder participation and acceptance, and poor scalability of digital health solutions have hindered their widespread implementation and use. Here, we provide recommendations from the Acute Disease Quality Initiative consensus meeting, which involved experts in adult and paediatric nephrology, critical care, pharmacy and data science, at which the use of digital health for risk prediction, prevention, identification and management of AKI and its consequences was discussed.

Exploring the Potential of Chatbots in Critical Care Nephrology

The exponential growth of artificial intelligence (AI) has allowed for its integration into multiple sectors, including, notably, healthcare. Chatbots have emerged as a pivotal resource for improving patient outcomes and assisting healthcare practitioners through various AI-based technologies. In critical care, kidney-related conditions play a significant role in determining patient outcomes. This article examines the potential for integrating chatbots into the workflows of critical care nephrology to optimize patient care. We detail their specific applications in critical care nephrology, such as managing acute kidney injury, alert systems, and continuous renal replacement therapy (CRRT); facilitating discussions around palliative care; and bolstering collaboration within a multidisciplinary team. Chatbots have the potential to augment real-time data availability, evaluate renal health, identify potential risk factors, build predictive models, and monitor patient progress. Moreover, they provide a platform for enhancing communication and education for both patients and healthcare providers, paving the way for enriched knowledge and honed professional skills. However, it is vital to recognize the inherent challenges and limitations when using chatbots in this domain. Here, we provide an in-depth exploration of the concerns tied to chatbots' accuracy, dependability, data protection and security, transparency, potential algorithmic biases, and ethical implications in critical care nephrology. While human discernment and intervention are indispensable, especially in complex medical scenarios or intricate situations, the sustained advancements in AI signal that the integration of precision-engineered chatbot algorithms within critical care nephrology has considerable potential to elevate patient care and pivotal outcome metrics in the future.

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.

A deep learning-based dynamic model for predicting acute kidney injury risk severity in postoperative patients

BACKGROUND

Acute kidney injury is a common postoperative complication affecting between 10% and 30% of surgical patients. Acute kidney injury is associated with increased resource usage and chronic kidney disease development, with more severe acute kidney injury suggesting more aggressive deterioration in clinical outcomes and mortality.

METHODS

We considered 42,906 surgical patients admitted to University of Florida Health (n = 51,806) between 2014 and 2021. Acute kidney injury stages were determined using the Kidney Disease Improving Global Outcomes serum creatinine criteria. We developed a recurrent neural network-based model to continuously predict acute kidney injury risk and state in the following 24 hours and compared it with logistic regression, random forest, and multi-layer perceptron models. We used medications, laboratory and vital measurements, and derived features from past one-year records as inputs. We analyzed the proposed model with integrated gradients for enhanced explainability.

RESULTS

Postoperative acute kidney injury at any stage developed in 20% (10,664) of the cohort. The recurrent neural network model was more accurate in predicting nearly all categories of next-day acute kidney injury stages (including the no acute kidney injury group). The area under the receiver operating curve and 95% confidence intervals for recurrent neural network and logistic regression models were for no acute kidney injury (0.98 [0.98-0.98] vs 0.93 [0.93-0.93]), stage 1 (0.95 [0.95-0.95] vs. 0.81 [0.80-0.82]), stage 2/3 (0.99 [0.99-0.99] vs 0.96 [0.96-0.97]), and stage 3 with renal replacement therapy (1.0 [1.0-1.0] vs 1.0 [1.0-1.0].

CONCLUSION

The proposed model demonstrates that temporal processing of patient information can lead to more granular and dynamic modeling of acute kidney injury status and result in more continuous and accurate acute kidney injury prediction. We showcase the integrated gradients framework's utility as a mechanism for enhancing model explainability, potentially facilitating clinical trust for future implementation.

Serological Biomarker-Based Machine Learning Models for Predicting the Relapse of Ulcerative Colitis

Purpose

To explore whether machine learning models using serological markers can predict the relapse of Ulcerative colitis (UC).

Patients and Methods

This clinical cohort study included 292 UC patients, and serological markers were obtained when patients were discharged from the hospital. Subsequently, four machine learning models including the random forest (RF) model, the logistic regression model, the decision tree, and the neural network were compared to predict the relapse of UC. A nomogram was constructed, and the performance of these models was evaluated by accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).

Results

Based on the patients' characteristics and serological markers, we selected the relevant variables associated with relapse and developed a LR model. The novel model including gender, white blood cell count, percentage of leukomonocyte, percentage of monocyte, absolute value of neutrophilic granulocyte, and erythrocyte sedimentation rate was established for predicting the relapse. In addition, the average AUC of the four machine learning models was 0.828, of which the RF model was the best. The AUC of the test group was 0.889, the accuracy was 76.4%, the sensitivity was 78.5%, and the specificity was 76.4%. There were 45 variables in the RF models, and the relative weight coefficients of these variables were determined. Age has the greatest impact on classification results, followed by hemoglobin concentration, white blood cell count, and platelet distribution width.

Conclusion

Machine learning models based on serological markers had high accuracy in predicting the relapse of UC. The model can be used to noninvasively predict patient outcomes and can be an effective tool for determining personalized treatment plans.

Construction and validation of prognostic models in critically Ill patients with sepsis-associated acute kidney injury: interpretable machine learning approach

BACKGROUND

Acute kidney injury (AKI) is a common complication in critically ill patients with sepsis and is often associated with a poor prognosis. We aimed to construct and validate an interpretable prognostic prediction model for patients with sepsis-associated AKI (S-AKI) using machine learning (ML) methods.

METHODS

Data on the training cohort were collected from the Medical Information Mart for Intensive Care IV database version 2.2 to build the model, and data of patients were extracted from Hangzhou First People's Hospital Affiliated to Zhejiang University School of Medicine for external validation of model. Predictors of mortality were identified using Recursive Feature Elimination (RFE). Then, random forest, extreme gradient boosting (XGBoost), multilayer perceptron classifier, support vector classifier, and logistic regression were used to establish a prognosis prediction model for 7, 14, and 28 days after intensive care unit (ICU) admission, respectively. Prediction performance was assessed using the receiver operating characteristic (ROC) curve and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) were used to interpret the ML models.

RESULTS

In total, 2599 patients with S-AKI were included in the analysis. Forty variables were selected for the model development. According to the areas under the ROC curve (AUC) and DCA results for the training cohort, XGBoost model exhibited excellent performance with F1 Score of 0.847, 0.715, 0.765 and AUC (95% CI) of 0.91 (0.90, 0.92), 0.78 (0.76, 0.80), and 0.83 (0.81, 0.85) in 7 days, 14 days and 28 days group, respectively. It also demonstrated excellent discrimination in the external validation cohort. Its AUC (95% CI) was 0.81 (0.79, 0.83), 0.75 (0.73, 0.77), 0.79 (0.77, 0.81) in 7 days, 14 days and 28 days group, respectively. SHAP-based summary plot and force plot were used to interpret the XGBoost model globally and locally.

CONCLUSIONS

ML is a reliable tool for predicting the prognosis of patients with S-AKI. SHAP methods were used to explain intrinsic information of the XGBoost model, which may prove clinically useful and help clinicians tailor precise management.

Accurate and interpretable prediction of ICU-acquired AKI

PURPOSE

We developed and validated two parsimonious algorithms to predict the time of diagnosis of any stage of acute kidney injury (any-AKI) or moderate-to-severe AKI in clinically actionable prediction windows.

MATERIALS AND METHODS

In this retrospective single-center cohort of adult ICU admissions, we trained two gradient-boosting models: 1) any-AKI model, predicting the risk of any-AKI at least 6 h before diagnosis (50,342 admissions), and 2) moderate-to-severe AKI model, predicting the risk of moderate-to-severe AKI at least 12 h before diagnosis (39,087 admissions). Performance was assessed before disease diagnosis and validated prospectively.

RESULTS

The models achieved an area under the receiver operating characteristic curve (AUROC) of 0.756 at six hours (any-AKI) and 0.721 at 12 h (moderate-to-severe AKI) prior. Prospectively, both models had high positive predictive values (0.796 and 0.546 for any-AKI and moderate-to-severe AKI models, respectively) and triggered more in patients who developed AKI vs. those who did not (median of 1.82 [IQR 0-4.71] vs. 0 [IQR 0-0.73] and 2.35 [IQR 0.14-4.96] vs. 0 [IQR 0-0.8] triggers per 8 h for any-AKI and moderate-to-severe AKI models, respectively).

CONCLUSIONS

The two AKI prediction models have good discriminative performance using common features, which can aid in accurately and informatively monitoring AKI risk in ICU patients.

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.

Artificial Intelligence Applications in Clinical Chemistry

Artificial intelligence (AI) applications are an area of active investigation in clinical chemistry. Numerous publications have demonstrated the promise of AI across all phases of testing including preanalytic, analytic, and postanalytic phases; this includes novel methods for detecting common specimen collection errors, predicting laboratory results and diagnoses, and enhancing autoverification workflows. Although AI applications pose several ethical and operational challenges, these technologies are expected to transform the practice of the clinical chemistry laboratory in the near future.

MACHINE LEARNING MODELS FOR PREDICTING ACUTE KIDNEY INJURY IN PATIENTS WITH SEPSIS-ASSOCIATED ACUTE RESPIRATORY DISTRESS SYNDROME

ABSTRACT

Background: Acute kidney injury (AKI) is a prevalent and serious complication among patients with sepsis-associated acute respiratory distress syndrome (ARDS). Prompt and accurate prediction of AKI has an important role in timely intervention, ultimately improving the patients' survival rate. This study aimed to establish machine learning models to predict AKI via thorough analysis of data derived from electronic medical records. Method: The data of eligible patients were retrospectively collected from the Medical Information Mart for Intensive Care III database from 2001 to 2012. The primary outcome was the development of AKI within 48 hours after intensive care unit admission. Four different machine learning models were established based on logistic regression, support vector machine, random forest, and extreme gradient boosting (XGBoost). The performance of all predictive models was evaluated using the area under receiver operating characteristic curve, precision-recall curve, confusion matrix, and calibration plot. Moreover, the discrimination ability of the machine learning models was compared with that of the Sequential Organ Failure Assessment (SOFA) model. Results; Among 1,085 sepsis-associated ARDS patients included in this research, 375 patients (34.6%) developed AKI within 48 hours after intensive care unit admission. Twelve predictive variables were selected and further used to establish the machine learning models. The XGBoost model yielded the most accurate predictions with the highest area under receiver operating characteristic curve (0.86) and accuracy (0.81). In addition, a novel shiny application based on the XGBoost model was established to predict the probability of developing AKI among patients with sepsis-associated ARDS. Conclusions: Machine learning models could be used for predicting AKI in patients with sepsis-associated ARDS. Accordingly, a user-friendly shiny application based on the XGBoost model with reliable predictive performance was released online to predict the probability of developing AKI among patients with sepsis-associated ARDS.

Development and validation of clinical prediction models for acute kidney injury recovery at hospital discharge in critically ill adults

PURPOSE

Acute kidney injury (AKI) recovery prediction remains challenging. The purpose of the present study is to develop and validate prediction models for AKI recovery at hospital discharge in critically ill patients with ICU-acquired AKI stage 3 (AKI-3).

METHODS

Models were developed and validated in a development cohort (n = 229) and a matched validation cohort (n = 244) from the multicenter EPaNIC database to create prediction models with the least absolute shrinkage and selection operator (Lasso) machine-learning algorithm. We evaluated the discrimination and calibration of the models and compared their performance with plasma neutrophil gelatinase-associated lipocalin (NGAL) measured on first AKI-3 day (NGAL_AKI3) and reference model that only based on age.

RESULTS

Complete recovery and complete or partial recovery occurred in 33.20% and 51.23% of the validation cohort patients respectively. The prediction model for complete recovery based on age, need for renal replacement therapy (RRT), diagnostic group (cardiac/surgical/trauma/others), and sepsis on admission had an area under the receiver operating characteristics curve (AUROC) of 0.53. The prediction model for complete or partial recovery based on age, need for RRT, platelet count, urea, and white blood cell count had an AUROC of 0.61. NGAL_AKI3 showed AUROCs of 0.55 and 0.53 respectively. In cardiac patients, the models had higher AUROCs of 0.60 and 0.71 than NGAL_AKI3's AUROCs of 0.52 and 0.54. The developed models demonstrated a better performance over the reference models (only based on age) for cardiac surgery patients, but not for patients with sepsis and for a general ICU population.

CONCLUSION

Models to predict AKI recovery upon hospital discharge in critically ill patients with AKI-3 showed poor performance in the general ICU population, similar to the biomarker NGAL. In cardiac surgery patients, discrimination was acceptable, and better than NGAL. These findings demonstrate the difficulty of predicting non-reversible AKI early.

Machine learning models for predicting acute kidney injury: a systematic review and critical appraisal

BACKGROUND

The number of studies applying machine learning (ML) to predict acute kidney injury (AKI) has grown steadily over the past decade. We assess and critically appraise the state of the art in ML models for AKI prediction, considering performance, methodological soundness, and applicability.

METHODS

We searched PubMed and ArXiv, extracted data, and critically appraised studies based on the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), and Prediction Model Risk of Bias Assessment Tool (PROBAST) guidelines.

RESULTS

Forty-six studies from 3166 titles were included. Thirty-eight studies developed a model, five developed and externally validated one, and three studies externally validated one. Flexible ML methods were used more often than deep learning, although the latter was common with temporal variables and text as predictors. Predictive performance showed an area under receiver operating curves ranging from 0.49 to 0.99. Our critical appraisal identified a high risk of bias in 39 studies. Some studies lacked internal validation, whereas external validation and interpretability of results were rarely considered. Fifteen studies focused on AKI prediction in the intensive care setting, and the US-derived Medical Information Mart for Intensive Care (MIMIC) data set was commonly used. Reproducibility was limited as data and code were usually unavailable.

CONCLUSIONS

Flexible ML methods are popular for the prediction of AKI, although more complex models based on deep learning are emerging. Our critical appraisal identified a high risk of bias in most models: Studies should use calibration measures and external validation more often, improve model interpretability, and share data and code to improve reproducibility.

Challenges in translational machine learning

Machine learning (ML) algorithms are increasingly being used to help implement clinical decision support systems. In this new field, we define as "translational machine learning", joint efforts and strong communication between data scientists and clinicians help to span the gap between ML and its adoption in the clinic. These collaborations also improve interpretability and trust in translational ML methods and ultimately aim to result in generalizable and reproducible models. To help clinicians and bioinformaticians refine their translational ML pipelines, we review the steps from model building to the use of ML in the clinic. We discuss experimental setup, computational analysis, interpretability and reproducibility, and emphasize the challenges involved. We highly advise collaboration and data sharing between consortia and institutes to build multi-centric cohorts that facilitate ML methodologies that generalize across centers. In the end, we hope that this review provides a way to streamline translational ML and helps to tackle the challenges that come with it.

Artificial intelligence-enabled decision support in nephrology

Kidney pathophysiology is often complex, nonlinear and heterogeneous, which limits the utility of hypothetical-deductive reasoning and linear, statistical approaches to diagnosis and treatment. Emerging evidence suggests that artificial intelligence (AI)-enabled decision support systems - which use algorithms based on learned examples - may have an important role in nephrology. Contemporary AI applications can accurately predict the onset of acute kidney injury before notable biochemical changes occur; can identify modifiable risk factors for chronic kidney disease onset and progression; can match or exceed human accuracy in recognizing renal tumours on imaging studies; and may augment prognostication and decision-making following renal transplantation. Future AI applications have the potential to make real-time, continuous recommendations for discrete actions and yield the greatest probability of achieving optimal kidney health outcomes. Realizing the clinical integration of AI applications will require cooperative, multidisciplinary commitment to ensure algorithm fairness, overcome barriers to clinical implementation, and build an AI-competent workforce. AI-enabled decision support should preserve the pre-eminence of wisdom and augment rather than replace human decision-making. By anchoring intuition with objective predictions and classifications, this approach should favour clinician intuition when it is honed by experience.

Machine learning for the prediction of acute kidney injury in patients with sepsis

BACKGROUND

Acute kidney injury (AKI) is the most common and serious complication of sepsis, accompanied by high mortality and disease burden. The early prediction of AKI is critical for timely intervention and ultimately improves prognosis. This study aims to establish and validate predictive models based on novel machine learning (ML) algorithms for AKI in critically ill patients with sepsis.

METHODS

Data of patients with sepsis were extracted from the Medical Information Mart for Intensive Care III (MIMIC- III) database. Feature selection was performed using a Boruta algorithm. ML algorithms such as logistic regression (LR), k-nearest neighbors (KNN), support vector machine (SVM), decision tree, random forest, Extreme Gradient Boosting (XGBoost), and artificial neural network (ANN) were applied for model construction by utilizing tenfold cross-validation. The performances of these models were assessed in terms of discrimination, calibration, and clinical application. Moreover, the discrimination of ML-based models was compared with those of Sequential Organ Failure Assessment (SOFA) and the customized Simplified Acute Physiology Score (SAPS) II model.

RESULTS

A total of 3176 critically ill patients with sepsis were included for analysis, of which 2397 cases (75.5%) developed AKI during hospitalization. A total of 36 variables were selected for model construction. The models of LR, KNN, SVM, decision tree, random forest, ANN, XGBoost, SOFA and SAPS II score were established and obtained area under the receiver operating characteristic curves of 0.7365, 0.6637, 0.7353, 0.7492, 0.7787, 0.7547, 0.821, 0.6457 and 0.7015, respectively. The XGBoost model had the best predictive performance in terms of discrimination, calibration, and clinical application among all models.

CONCLUSION

The ML models can be reliable tools for predicting AKI in septic patients. The XGBoost model has the best predictive performance, which can be used to assist clinicians in identifying high-risk patients and implementing early interventions to reduce mortality.

Nouvelles approches diagnostiques de l’insuffisance rénale aiguë

L’insuffisance rénale, véritable problème de santé publique, concernerait plus de 82 000 personnes en France. On estime que 5 à 10 % de la population française souffriraient d’une maladie rénale pouvant conduire à une insuffisance rénale avec un taux de mortalité de plus de 10 % par an. À l’inverse de la maladie rénale chronique irréversible, l’insuffisance rénale aiguë est considérée comme un dysfonctionnement transitoire et réversible. Au-delà de l’intérêt de la prévention, le diagnostic précoce de l’insuffisance rénale aiguë permettrait de mettre en place des thérapeutiques adaptées et ciblées afin d’éviter l’évolution vers des lésions rénales irréversibles. Cependant, il demeure un véritable challenge pour le praticien puisque l’on présume que près de 10 % de la population française présenteraient des lésions rénales asymptomatiques. Bien que la définition de l’insuffisance rénale aiguë ait été simplifiée durant ces dernières années, il existe de nombreuses limites. En parallèle, des progrès majeurs ont été réalisés notamment en termes de diagnostic. L’objectif de cette mise au point est de faire un rappel sur l’évolution de l’insuffisance rénale aiguë, les définitions actuelles et de présenter les nouvelles approches diagnostiques en cours de développement.

Estimation of Baseline Serum Creatinine with Machine Learning

INTRODUCTION

Comparing current to baseline serum creatinine is important in detecting acute kidney injury. In this study, we report a regression-based machine learning model to predict baseline serum creatinine.

METHODS

We developed and internally validated a gradient boosting model on patients admitted in Mayo Clinic intensive care units from 2005 to 2017 to predict baseline creatinine. The model was externally validated on the Medical Information Mart for Intensive Care III (MIMIC III) cohort in all ICU admissions from 2001 to 2012. The predicted baseline creatinine from the model was compared with measured serum creatinine levels. We compared the performance of our model with that of the backcalculated estimated serum creatinine from the Modification of Diet in Renal Disease (MDRD) equation.

RESULTS

Following ascertainment of eligibility criteria, 44,370 patients from the Mayo Clinic and 6,112 individuals from the MIMIC III cohort were enrolled. Our model used 6 features from the Mayo Clinic and MIMIC III datasets, including the presence of chronic kidney disease, weight, height, and age. Our model had significantly lower error than the MDRD backcalculation (mean absolute error [MAE] of 0.248 vs. 0.374 in the Mayo Clinic test data; MAE of 0.387 vs. 0.465 in the MIMIC III cohort) and higher correlation (intraclass correlation coefficient [ICC] of 0.559 vs. 0.050 in the Mayo Clinic test data; ICC of 0.357 vs. 0.030 in the MIMIC III cohort).

DISCUSSION/CONCLUSION

Using machine learning models, baseline serum creatinine could be estimated with higher accuracy than the backcalculated estimated serum creatinine level.

Postoperative complications of endovascular blunt thoracic aortic injury repair

Background

Thoracic endovascular aortic repair (TEVAR) has become the standard of care for thoracic aortic aneurysms and increasingly for blunt thoracic aortic injury (BTAI). Postoperative complications, including spinal cord ischemia and paraplegia, have been shown to be less common with elective TEVAR than with open thoracic or thoracoabdominal repair. Although small cohort studies exist, the postoperative complications of endovascular repair of traumatic aortic injury have not been described through large data set analysis.

Methods

A retrospective cohort analysis was performed of the American College of Surgeons Trauma Quality Improvement Program registry spanning from 2007 to 2017. All patients with BTAI who underwent TEVAR, as indicated by the Abbreviated Injury Scale or the International Classification of Diseases (ICD-9 or ICD-10), were included. Categorical data were presented as proportions and continuous data as mean and SD. OR was calculated for each postoperative complication.

Results

2990 patients were identified as having undergone TEVAR for BTAI. The postoperative incidence of stroke was 2.8% (83), and 4.7% (140) of patients suffered acute kidney injury or renal failure. The incidence of spinal cord ischemia was 1.9% (58), whereas 0.2% (7) of patients suffered complete paraplegia. Renal events and stroke were found to occur significantly more frequently in those undergoing TEVAR (OR 1.758, 1.449–2.134 and OR 2.489, 1.917–3.232, respectively). Notably, there was no difference between TEVAR and non-operative BTAI incidences of spinal cord ischemia or paraplegia (OR 1.061, 0.799–1.409 and OR 1.698, 0.728–3.961, respectively).

Discussion

Postoperative intensive care unit care of patients after BTAI has historically focused on awareness of spinal cord ischemia. Our analysis suggests that after endovascular repair of blunt aortic trauma, care should involve vigilance primarily against postoperative cerebrovascular and renal events. Further study is warranted to develop guidelines for the intensivist managing patients after TEVAR for BTAI.

Level of evidence

Level III.

Acute kidney injury in the critically ill: an updated review on pathophysiology and management

Acute kidney injury (AKI) is now recognized as a heterogeneous syndrome that not only affects acute morbidity and mortality, but also a patient’s long-term prognosis. In this narrative review, an update on various aspects of AKI in critically ill patients will be provided. Focus will be on prediction and early detection of AKI (e.g., the role of biomarkers to identify high-risk patients and the use of machine learning to predict AKI), aspects of pathophysiology and progress in the recognition of different phenotypes of AKI, as well as an update on nephrotoxicity and organ cross-talk. In addition, prevention of AKI (focusing on fluid management, kidney perfusion pressure, and the choice of vasopressor) and supportive treatment of AKI is discussed. Finally, post-AKI risk of long-term sequelae including incident or progression of chronic kidney disease, cardiovascular events and mortality, will be addressed.

Applications of machine learning in the chemical pathology laboratory

Machine learning (ML) is an area of artificial intelligence that provides computer programmes with the capacity to autodidact and learn new skills from experience, without continued human programming. ML algorithms can analyse large data sets quickly and accurately, by supervised and unsupervised learning techniques, to provide classification and prediction value outputs. The application of ML to chemical pathology can potentially enhance efficiency at all phases of the laboratory's total testing process. Our review will broadly discuss the theoretical foundation of ML in laboratory medicine. Furthermore, we will explore the current applications of ML to diverse chemical pathology laboratory processes, for example, clinical decision support, error detection in the preanalytical phase, and ML applications in gel-based image analysis and biomarker discovery. ML currently demonstrates exploratory applications in chemical pathology with promising advancements, which have the potential to improve all phases of the chemical pathology total testing pathway.

Application of machine learning models for predicting acute kidney injury following donation after cardiac death liver transplantation

BACKGROUND

Acute kidney injury (AKI) is a common complication after liver transplantation (LT) and is an indicator of poor prognosis. The establishment of a more accurate preoperative prediction model of AKI could help to improve the prognosis of LT. Machine learning algorithms provide a potentially effective approach.

METHODS

A total of 493 patients with donation after cardiac death LT (DCDLT) were enrolled. AKI was defined according to the clinical practice guidelines of kidney disease: improving global outcomes (KDIGO). The clinical data of patients with AKI (AKI group) and without AKI (non-AKI group) were compared. With logistic regression analysis as a conventional model, four predictive machine learning models were developed using the following algorithms: random forest, support vector machine, classical decision tree, and conditional inference tree. The predictive power of these models was then evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

The incidence of AKI was 35.7% (176/493) during the follow-up period. Compared with the non-AKI group, the AKI group showed a remarkably lower survival rate (P < 0.001). The random forest model demonstrated the highest prediction accuracy of 0.79 with AUC of 0.850 [95% confidence interval (CI): 0.794-0.905], which was significantly higher than the AUCs of the other machine learning algorithms and logistic regression models (P < 0.001).

CONCLUSIONS

The random forest model based on machine learning algorithms for predicting AKI occurring after DCDLT demonstrated stronger predictive power than other models in our study. This suggests that machine learning methods may provide feasible tools for forecasting AKI after DCDLT.

The importance of the urinary output criterion for the detection and prognostic meaning of AKI

Most reports on AKI claim to use KDIGO guidelines but fail to include the urinary output (UO) criterion in their definition of AKI. We postulated that ignoring UO alters the incidence of AKI, may delay diagnosis of AKI, and leads to underestimation of the association between AKI and ICU mortality. Using routinely collected data of adult patients admitted to an intensive care unit (ICU), we retrospectively classified patients according to whether and when they would be diagnosed with KDIGO AKI stage ≥ 2 based on baseline serum creatinine (Screa) and/or urinary output (UO) criterion. As outcomes, we assessed incidence of AKI and association with ICU mortality. In 13,403 ICU admissions (62.2% male, 60.8 ± 16.8 years, SOFA 7.0 ± 4.1), incidence of KDIGO AKI stage ≥ 2 was 13.2% when based only the SCrea criterion, 34.3% when based only the UO criterion, and 38.7% when based on both criteria. By ignoring the UO criterion, 66% of AKI cases were missed and 13% had a delayed diagnosis. The cause-specific hazard ratios of ICU mortality associated with KDIGO AKI stage ≥ 2 diagnosis based on only the SCrea criterion, only the UO criterion and based on both criteria were 2.11 (95% CI 1.85–2.42), 3.21 (2.79–3.69) and 2.85 (95% CI 2.43–3.34), respectively. Ignoring UO in the diagnosis of KDIGO AKI stage ≥ 2 decreases sensitivity, may lead to delayed diagnosis and results in underestimation of KDIGO AKI stage ≥ 2 associated mortality.

Comparison of machine learning and logistic regression models in predicting acute kidney injury: A systematic review and meta-analysis

INTRODUCTION

We aimed to assess whether machine learning models are superior at predicting acute kidney injury (AKI) compared to logistic regression (LR), a conventional prediction model.

METHODS

Eligible studies were identified using PubMed and Embase. A total of 24 studies consisting of 84 prediction models met inclusion criteria. Independent samples t-test was performed to detect mean differences in area under the curve (AUC) between ML and LR models. One-way ANOVA and post-hoc t-tests were performed to assess mean differences in AUC between ML methods.

RESULTS

AUC data were similar between ML (0.736 ± 0.116) and LR (0.748 ± 0.057) models (p = 0.538). However, specific ML models, such as gradient boosting (0.838 ± 0.077), exhibited superior performance at predicting AKI as compared to other ML models in the literature (p < 0.05). Creatinine and urine output, standard variables assessed for AKI staging, were classified as significant predictors across multiple ML models, although the majority of significant predictors were unique and study specific.

CONCLUSIONS

These data suggest that ML models perform equally to that of LR, however ML models exhibit variable performance with some ML models displaying exceptional performance. The variability in ML prediction of AKI can be attributed, in part, to the specific ML model utilized, variable selection and processing, study and subject characteristics, and the steps associated with model training, validation, testing, and calibration.

Convolutional Neural Network Model for Intensive Care Unit Acute Kidney Injury Prediction

INTRODUCTION

Acute kidney injury (AKI) is common among hospitalized patients and has a significant impact on morbidity and mortality. Although early prediction of AKI has the potential to reduce adverse patient outcomes, it remains a difficult condition to predict and diagnose. The purpose of this study was to evaluate the ability of a machine learning algorithm to predict for AKI as defined by Kidney Disease: Improving Global Outcomes (KDIGO) stage 2 or 3 up to 48 hours in advance of onset using convolutional neural networks (CNNs) and patient electronic health record (EHR) data.

METHODS

A CNN prediction system was developed to use EHR data gathered during patients' stays to predict AKI up to 48 hours before onset. A total of 12,347 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) database. An XGBoost AKI prediction model and the sequential organ failure assessment (SOFA) scoring system were used as comparators. The outcome was AKI onset. The model was trained on routinely collected patient EHR data. Measurements included area under the receiver operating characteristic (AUROC) curve, positive predictive value (PPV), and a battery of additional performance metrics for advance prediction of AKI onset.

RESULTS

On a hold-out test set, the algorithm attained an AUROC of 0.86 and PPV of 0.24, relative to a cohort AKI prevalence of 7.62%, for long-horizon AKI prediction at a 48-hour window before onset.

CONCLUSION

A CNN machine learning-based AKI prediction model outperforms XGBoost and the SOFA scoring system, revealing superior performance in predicting AKI 48 hours before onset, without reliance on serum creatinine (SCr) measurements.

Real-Time Clinical Decision Support Based on Recurrent Neural Networks for In-Hospital Acute Kidney Injury: External Validation and Model Interpretation

Background

Acute kidney injury (AKI) is commonly encountered in clinical practice and is associated with poor patient outcomes and increased health care costs. Despite it posing significant challenges for clinicians, effective measures for AKI prediction and prevention are lacking. Previously published AKI prediction models mostly have a simple design without external validation. Furthermore, little is known about the process of linking model output and clinical decisions due to the black-box nature of neural network models.

Objective

We aimed to present an externally validated recurrent neural network (RNN)–based continuous prediction model for in-hospital AKI and show applicable model interpretations in relation to clinical decision support.

Methods

Study populations were all patients aged 18 years or older who were hospitalized for more than 48 hours between 2013 and 2017 in 2 tertiary hospitals in Korea (Seoul National University Bundang Hospital and Seoul National University Hospital). All demographic data, laboratory values, vital signs, and clinical conditions of patients were obtained from electronic health records of each hospital. We developed 2-stage hierarchical prediction models (model 1 and model 2) using RNN algorithms. The outcome variable for model 1 was the occurrence of AKI within 7 days from the present. Model 2 predicted the future trajectory of creatinine values up to 72 hours. The performance of each developed model was evaluated using the internal and external validation data sets. For the explainability of our models, different model-agnostic interpretation methods were used, including Shapley Additive Explanations, partial dependence plots, individual conditional expectation, and accumulated local effects plots.

Results

We included 69,081 patients in the training, 7675 in the internal validation, and 72,352 in the external validation cohorts for model development after excluding cases with missing data and those with an estimated glomerular filtration rate less than 15 mL/min/1.73 m2 or end-stage kidney disease. Model 1 predicted any AKI development with an area under the receiver operating characteristic curve (AUC) of 0.88 (internal validation) and 0.84 (external validation), and stage 2 or higher AKI development with an AUC of 0.93 (internal validation) and 0.90 (external validation). Model 2 predicted the future creatinine values within 3 days with mean-squared errors of 0.04-0.09 for patients with higher risks of AKI and 0.03-0.08 for those with lower risks. Based on the developed models, we showed AKI probability according to feature values in total patients and each individual with partial dependence, accumulated local effects, and individual conditional expectation plots. We also estimated the effects of feature modifications such as nephrotoxic drug discontinuation on future creatinine levels.

Conclusions

We developed and externally validated a continuous AKI prediction model using RNN algorithms. Our model could provide real-time assessment of future AKI occurrences and individualized risk factors for AKI in general inpatient cohorts; thus, we suggest approaches to support clinical decisions based on prediction models for in-hospital AKI.

Including urinary output to define AKI enhances the performance of machine learning models to predict AKI at admission

PURPOSE

Acute kidney injury (AKI) is a prevalent and detrimental condition in intensive care unit patients. Most AKI predictive models only predict creatinine-triggered AKI (AKI_Cr) and might underperform when predicting urine-output-triggered AKI (AKI_UO). We aimed to describe how admission AKI_Cr prediction models perform in all AKI patients.

MATERIALS AND METHODS

Three types of models were trained: 1) pAKI_any, predicting AKI based on creatinine or urine output, 2) pAKI_UO, predicting AKI based only on urine output, and 3) pAKI_Cr, predicting AKI based only on creatinine. We compared model performance and predictive features.

RESULTS

The pAKI_any models had the best overall performance (AUROC 0.673-0.716) and the most consistent performance across three patient cohorts grouped by type of AKI trigger (min AUROC of 0.636). The pAKI_Cr models had fair performance in predicting AKI_Cr (AUROCs 0.702-0.748) but poor performance predicting AKI_UO (AUROCs 0.581-0.695). The predictive features for the pAKI_Cr models and pAKI_UO models were distinct, while top features for the pAKI_any models were consistently a combination of those for the pAKI_Cr and pAKI_UO models.

CONCLUSION

Ignoring urine output in the outcome during model training resulted in models that are unlikely to predict AKI_UO adequately and may miss a substantial proportion of patients in practice.

Artificial intelligence to guide management of acute kidney injury in the ICU: a narrative review

PURPOSE OF REVIEW

Acute kidney injury (AKI) frequently complicates hospital admission, especially in the ICU or after major surgery, and is associated with high morbidity and mortality. The risk of developing AKI depends on the presence of preexisting comorbidities and the cause of the current disease. Besides, many other parameters affect the kidney function, such as the state of other vital organs, the host response, and the initiated treatment. Advancements in the field of informatics have led to the opportunity to store and utilize the patient-related data to train and validate models to detect specific patterns and, as such, predict disease states or outcomes.

RECENT FINDINGS

Machine-learning techniques have also been applied to predict AKI, as well as the patients' outcomes related to their AKI, such as mortality or the need for kidney replacement therapy. Several models have recently been developed, but only a few of them have been validated in external cohorts.

SUMMARY

In this article, we provide an overview of the machine-learning prediction models for AKI and its outcomes in critically ill patients and individuals undergoing major surgery. We also discuss the pitfalls and the opportunities related to the implementation of these models in clinical practices.

Biomarkers and predicting acute kidney injury

AIM

How can we convert biomarkers into reliable, validated laboratory tests? Glomerular filtration rate (GFR) estimators exist for more than a century. The first utilitarian biomarkers were endogenously produced urea and creatinine. Clinicians then developed simple tests to determine whether or not renal tubular function was maintained. Are there faster and better tests that reflect decreased renal function and increased acute kidney injury (AKI) risk?

METHODS

We inspect earlier, and recently propagated biomarkers. Cystatin C reflects GFR and is not confounded by muscle mass. Direct GFR and plasma volume can now be measured acutely within 3 hours. Better yet would be tests that give information before GFR decreases and prior to urea, creatinine, and cystatin C increases. Prospective tests identifying those persons likely to develop AKI would be helpful. Even more utilitarian would be a test that also suggests a therapeutic avenue.

RESULTS

A number of highly provocative biomarkers have recently been proposed. Moreover the application of big data from huge electronic medical records promise new directions in identifying and dealing with AKI.

CONCLUSIONS

Pipedreams are in the pipeline; the novel findings require immediate testing, verification, and perhaps application. Future research promises to make such dreams come true.

AKI!Now Initiative: Recommendations for Awareness, Recognition, and Management of AKI

The American Society of Nephrology has established a new initiative, AKI!Now, with the goal of promoting excellence in the prevention and treatment of AKI by building a foundational program that transforms education and delivery of AKI care, aiming to reduce morbidity and associated mortality and to improve long-term outcomes. In this article, we describe our current efforts to improve early recognition and management involving inclusive interdisciplinary collaboration between providers, patients, and their families; discuss the ongoing need to change some of our current AKI paradigms and diagnostic methods; and provide specific recommendations to improve AKI recognition and care. In the hospital and the community, AKI is a common and increasingly frequent condition that generates risks of adverse events and high costs. Unfortunately, patients with AKI may frequently have received less than optimal quality of care. New classifications have facilitated understanding of AKI incidence and its impact on outcomes, but they are not always well aligned with AKI pathophysiology. Despite ongoing research efforts, treatments to promote or hasten kidney recovery remain ineffective. To avoid progression, the current approach to AKI emphasizes the promotion of early recognition and timely response. However, a lack of awareness of the importance of early recognition and treatment among health care team members and the heterogeneity of approaches within the health care teams assessing the patient remains a major challenge. Early identification is further complicated by differences in settings where AKI occurs (the community or the hospital), and by differences in patient populations and cultures between the intensive care unit and ward environments. To address these obstacles, we discuss the need to improve education at all levels of care and to generate specific guidance on AKI evaluation and management, including the development of a widely applicable education and an AKI management toolkit, engaging hospital administrators to incorporate AKI as a quality initiative, and raising awareness of AKI as a complication of other disease processes.

Clinical adoption of Nephrocheck® in the early detection of acute kidney injury

Acute kidney injury is a common complication of acute illnesses and is associated with increased morbidity and mortality. Over the past years several acute kidney injury biomarkers for diagnostication, decision-making processes, and prognosis of acute kidney injury and its outcomes have been developed and validated. Among these biomarkers, tissue inhibitor of metalloproteinase-2 (TIMP-2) and insulin-like growth factor-binding protein 7 (IGFBP7), the so-called cell cycle arrest biomarkers, showed a superior profile of accuracy and stability even in patients with substantial comorbidities. Therefore, in 2014, the US Food and Drug Administration approved the use of the product of TIMP-2 and IGFBP7 ([TIMP-2] × [IGFBP7]), known as cell cycle arrest biomarkers, to aid critical care physicians and nephrologists in the early prediction of acute kidney injury in the critical care setting. To date, Nephrocheck® is the only commercially available test for [TIMP-2] × [IGFBP7]. In this narrative review, we describe the growing clinical and investigational momentum of biomarkers, focusing on [TIMP-2] × [IGFBP7], as one of the most promising candidate biomarkers. Additionally, we review the current state of clinical implementation of Nephrocheck®.

Recommendations on Acute Kidney Injury Biomarkers From the Acute Disease Quality Initiative Consensus Conference: A Consensus Statement

IMPORTANCE

In the last decade, new biomarkers for acute kidney injury (AKI) have been identified and studied in clinical trials. Guidance is needed regarding how best to incorporate them into clinical practice.

OBJECTIVE

To develop recommendations on AKI biomarkers based on existing data and expert consensus for practicing clinicians and researchers.

EVIDENCE REVIEW

At the 23rd Acute Disease Quality Initiative meeting, a meeting of 23 international experts in critical care, nephrology, and related specialties, the panel focused on 4 broad areas, as follows: (1) AKI risk assessment; (2) AKI prediction and prevention; (3) AKI diagnosis, etiology, and management; and (4) AKI progression and kidney recovery. A literature search revealed more than 65 000 articles published between 1965 and May 2019. In a modified Delphi process, recommendations and consensus statements were developed based on existing data, with 90% agreement among panel members required for final adoption. Recommendations were graded using the Grading of Recommendations, Assessment, Development and Evaluations system.

FINDINGS

The panel developed 11 consensus statements for biomarker use and 14 research recommendations. The key suggestions were that a combination of damage and functional biomarkers, along with clinical information, be used to identify high-risk patient groups, improve the diagnostic accuracy of AKI, improve processes of care, and assist the management of AKI.

CONCLUSIONS AND RELEVANCE

Current evidence from clinical studies supports the use of new biomarkers in prevention and management of AKI. Substantial gaps in knowledge remain, and more research is necessary.

Predicting acute kidney injury in critically ill patients using comorbid conditions utilizing machine learning

Background

Acute kidney injury (AKI) carries a poor prognosis. Its incidence is increasing in the intensive care unit (ICU). Our purpose in this study is to develop and externally validate a model for predicting AKI in the ICU using patient data present prior to ICU admission.

Methods

We used data of 98 472 adult ICU admissions at Mayo Clinic between 1 January 2005 and 31 December 2017 and 51 801 encounters from Medical Information Mart for Intensive Care III (MIMIC-III) cohort. A gradient-boosting model was trained on 80% of the Mayo Clinic cohort using a set of features to predict AKI acquired in the ICU.

Results

AKI was identified in 39 307 (39.9%) encounters in the Mayo Clinic cohort. Patients who developed AKI in the ICU were older and had higher ICU and in-hospital mortality compared to patients without AKI. A 30-feature model yielded an area under the receiver operating curve of 0.690 [95% confidence interval (CI) 0.682–0.697] in the Mayo Clinic cohort set and 0.656 (95% CI 0.648–0.664) in the MIMIC-III cohort.

Conclusions

Using machine learning, AKI among ICU patients can be predicted using information available prior to admission. This model is independent of ICU information, making it valuable for stratifying patients at admission.

Machine Learning Model for Risk Prediction of Community-Acquired Acute Kidney Injury Hospitalization From Electronic Health Records: Development and Validation Study

BACKGROUND

Community-acquired acute kidney injury (CA-AKI)-associated hospitalizations impose significant health care needs and contribute to in-hospital mortality. However, most risk prediction models developed to date have focused on AKI in a specific group of patients during hospitalization, and there is limited knowledge on the baseline risk in the general population for preventing CA-AKI-associated hospitalization.

OBJECTIVE

To gain further insight into risk exploration, the aim of this study was to develop, validate, and establish a scoring system to facilitate health professionals in enabling early recognition and intervention of CA-AKI to prevent permanent kidney damage using different machine-learning techniques.

METHODS

A nested case-control study design was employed using electronic health records derived from a group of Chang Gung Memorial Hospitals in Taiwan from 2010 to 2017 to identify 234,867 adults with at least two measures of serum creatinine at hospital admission. Patients were classified into a derivation cohort (2010-2016) and a temporal validation cohort (2017). Patients with the first episode of CA-AKI at hospital admission were classified into the case group and those without CA-AKI were classified in the control group. A total of 47 potential candidate variables, including age, gender, prior use of nephrotoxic medications, Charlson comorbid conditions, commonly measured laboratory results, and recent use of health services, were tested to develop a CA-AKI hospitalization risk model. Permutation-based selection with both the extreme gradient boost (XGBoost) and least absolute shrinkage and selection operator (LASSO) algorithms was performed to determine the top 10 important features for scoring function development.

RESULTS

The discriminative ability of the risk model was assessed by the area under the receiver operating characteristic curve (AUC), and the predictive CA-AKI risk model derived by the logistic regression algorithm achieved an AUC of 0.767 (95% CI 0.764-0.770) on derivation and 0.761 on validation for any stage of AKI, with positive and negative predictive values of 19.2% and 96.1%, respectively. The risk model for prediction of CA-AKI stages 2 and 3 had an AUC value of 0.818 for the validation cohort with positive and negative predictive values of 13.3% and 98.4%, respectively. These metrics were evaluated at a cut-off value of 7.993, which was determined as the threshold to discriminate the risk of AKI.

CONCLUSIONS

A machine learning-generated risk score model can identify patients at risk of developing CA-AKI-related hospitalization through a routine care data-driven approach. The validated multivariate risk assessment tool could help clinicians to stratify patients in primary care, and to provide monitoring and early intervention for preventing AKI while improving the quality of AKI care in the general population.

Predicting Acute Kidney Injury after Cardiac Surgery by Machine Learning Approaches

Cardiac surgery-associated AKI (CSA-AKI) is common after cardiac surgery and has an adverse impact on short- and long-term mortality. Early identification of patients at high risk of CSA-AKI by applying risk prediction models allows clinicians to closely monitor these patients and initiate effective preventive and therapeutic approaches to lessen the incidence of AKI. Several risk prediction models and risk assessment scores have been developed for CSA-AKI. However, the definition of AKI and the variables utilized in these risk scores differ, making general utility complex. Recently, the utility of artificial intelligence coupled with machine learning, has generated much interest and many studies in clinical medicine, including CSA-AKI. In this article, we discussed the evolution of models established by machine learning approaches to predict CSA-AKI.

Real-Time Prediction of Acute Kidney Injury in Hospitalized Adults: Implementation and Proof of Concept

RATIONALE & OBJECTIVE

Acute kidney injury (AKI) is diagnosed based on changes in serum creatinine concentration, a late marker of this syndrome. Algorithms that predict elevated risk for AKI are of great interest, but no studies have incorporated such an algorithm into the electronic health record to assist with clinical care. We describe the experience of implementing such an algorithm.

STUDY DESIGN

Prospective observational cohort study.

SETTING & PARTICIPANTS

2,856 hospitalized adults in a single urban tertiary-care hospital with an algorithm-predicted risk for AKI in the next 24 hours>15%. Alerts were also used to target a convenience sample of 100 patients for measurement of 16 urine and 6 blood biomarkers.

EXPOSURE

Clinical characteristics at the time of pre-AKI alert.

OUTCOME

AKI within 24 hours of pre-AKI alert (AKI₂₄).

ANALYTICAL APPROACH

Descriptive statistics and univariable associations.

RESULTS

At enrollment, mean predicted probability of AKI₂₄ was 19.1%; 18.9% of patients went on to develop AKI₂₄. Outcomes were generally poor among this population, with 29% inpatient mortality among those who developed AKI₂₄ and 14% among those who did not (P<0.001). Systolic blood pressure<100mm Hg (28% of patients with AKI₂₄ vs 18% without), heart rate>100 beats/min (32% of patients with AKI₂₄ vs 24% without), and oxygen saturation<92% (15% of patients with AKI₂₄ vs 6% without) were all more common among those who developed AKI₂₄. Of all biomarkers measured, only hyaline casts on urine microscopy (72% of patients with AKI₂₄ vs 25% without) and fractional excretion of urea nitrogen (20% [IQR, 12%-36%] among patients with AKI₂₄ vs 34% [IQR, 25%-44%] without) differed between those who did and did not develop AKI₂₄.

LIMITATIONS

Single-center study, reliance on serum creatinine level for AKI diagnosis, small number of patients undergoing biomarker evaluation.

CONCLUSIONS

A real-time AKI risk model was successfully integrated into the EHR.

Clinical prediction models for acute kidney injury

Objective

To report on the currently available prediction models for the development of acute kidney injury in heterogeneous adult intensive care units.

Methods

A systematic review of clinical prediction models for acute kidney injury in adult intensive care unit populations was carried out. PubMed^® was searched for publications reporting on the development of a novel prediction model, validation of an established model, or impact of an existing prediction model for early acute kidney injury diagnosis in intensive care units.

Results

We screened 583 potentially relevant articles. Among the 32 remaining articles in the first selection, only 5 met the inclusion criteria. The nonstandardized adaptations that were made to define baseline serum creatinine when the preadmission value was missing led to heterogeneous definitions of the outcome. Commonly included predictors were sepsis, age, and serum creatinine level. The final models included between 5 and 19 risk factors. The areas under the Receiver Operating Characteristic curves to predict acute kidney injury development in the internal validation cohorts ranged from 0.78 to 0.88. Only two studies were externally validated.

Conclusion

Clinical prediction models for acute kidney injury can help in applying more timely preventive interventions to the right patients. However, in intensive care unit populations, few models have been externally validated. In addition, heterogeneous definitions for acute kidney injury and evaluation criteria and the lack of impact analysis hamper a thorough comparison of existing models. Future research is needed to validate the established models and to analyze their clinical impact before they can be applied in clinical practice.

Artificial intelligence-assisted prediction of preeclampsia: Development and external validation of a nationwide health insurance dataset of the BPJS Kesehatan in Indonesia

Background

We developed and validated an artificial intelligence (AI)-assisted prediction of preeclampsia applied to a nationwide health insurance dataset in Indonesia.

Methods

The BPJS Kesehatan dataset have been preprocessed using a nested case-control design into preeclampsia/eclampsia (n = 3318) and normotensive pregnant women (n = 19,883) from all women with one pregnancy. The dataset provided 95 features consisting of demographic variables and medical histories started from 24 months to event and ended by delivery as the event. Six algorithms were compared by area under the receiver operating characteristics curve (AUROC) with a subgroup analysis by time to the event. We compared our model to similar prediction models from systematically reviewed studies. In addition, we conducted a text mining analysis based on natural language processing techniques to interpret our modeling results.

Findings

The best model consisted of 17 predictors extracted by a random forest algorithm. Nine∼12 months to the event was the period that had the best AUROC in external validation by either geographical (0.88, 95% confidence interval (CI) 0.88–0.89) or temporal split (0.86, 95% CI 0.85–0.86). We compared this model to prediction models in seven studies from 869 records in PUBMED, EMBASE, and SCOPUS. This model outperformed the previous models in terms of the precision, sensitivity, and specificity in all validation sets.

Interpretation

Our low-cost model improved preliminary prediction to decide pregnant women that will be predicted by the models with high specificity and advanced predictors.

Funding

This work was supported by grant no. MOST108-2221-E-038-018 from the Ministry of Science and Technology of Taiwan.

Temporal Pattern Detection to Predict Adverse Events in Critical Care: Case Study With Acute Kidney Injury

BACKGROUND

More than 20% of patients admitted to the intensive care unit (ICU) develop an adverse event (AE). No previous study has leveraged patients' data to extract the temporal features using their structural temporal patterns, that is, trends.

OBJECTIVE

This study aimed to improve AE prediction methods by using structural temporal pattern detection that captures global and local temporal trends and to demonstrate these improvements in the detection of acute kidney injury (AKI).

METHODS

Using the Medical Information Mart for Intensive Care dataset, containing 22,542 patients, we extracted both global and local trends using structural pattern detection methods to predict AKI (ie, binary prediction). Classifiers were built on 17 input features consisting of vital signs and laboratory test results using state-of-the-art models; the optimal classifier was selected for comparisons with previous approaches. The classifier with structural pattern detection features was compared with two baseline classifiers that used different temporal feature extraction approaches commonly used in the literature: (1) symbolic temporal pattern detection, which is the most common approach for multivariate time series classification; and (2) the last recorded value before the prediction point, which is the most common approach to extract temporal data in the AKI prediction literature. Moreover, we assessed the individual contribution of global and local trends. Classifier performance was measured in terms of accuracy (primary outcome), area under the curve, and F-measure. For all experiments, we employed 20-fold cross-validation.

RESULTS

Random forest was the best classifier using structural temporal pattern detection. The accuracy of the classifier with local and global trend features was significantly higher than that while using symbolic temporal pattern detection and the last recorded value (81.3% vs 70.6% vs 58.1%; P<.001). Excluding local or global features reduced the accuracy to 74.4% or 78.1%, respectively (P<.001).

CONCLUSIONS

Classifiers using features obtained from structural temporal pattern detection significantly improved the prediction of AKI onset in ICU patients over two baselines based on common previous approaches. The proposed method is a generalizable approach to predict AEs in critical care that may be used to help clinicians intervene in a timely manner to prevent or mitigate AEs.

Effect of nephrology follow-up on long-term outcomes in patients with acute kidney injury: A systematic review and meta-analysis

AIM

Acute kidney injury (AKI) is associated with poor short-term and long-term clinical outcomes. The role of nephrology follow-up in post-AKI management remains uncertain.

METHODS

A systematic review and meta-analysis were performed examining all randomized controlled trials and observational studies assessing the effect of nephrology follow-up on patients' clinical outcomes. The primary outcome was all-cause mortality. The secondary outcomes were renal outcomes, which were defined as a composite of requirement of permanent dialysis and recurrent AKI. Pooled analysis was performed using a random-effect model.

RESULTS

We identified six studies (8972 patients, mean follow-up of 49 months). Five were retrospective cohort studies and one was a prospective cohort study. Risk of bias was a concern with all studied. Only four studies reported primary and/or secondary outcomes and were included. Compared with patients without nephrology follow-up, patients with nephrology follow-up had significantly reduced mortality by 22% (three studies, 3240 patients, relative risk [RR] = 0.78, 95% confidence interval [CI] = 0.70-0.88, I² = 0.0%). Nephrology follow-up did not improve composite renal outcomes with high heterogeneity due to significant differences in reported renal outcomes and follow-up period (two studies, 2537 patients, RR = 1.72, 95% CI = 0.49-6.05, I² = 90.1%).

CONCLUSION

Current evidence from observational studies is biased. It suggests long-term survival benefits with post-discharge nephrology follow-up in AKI patients. However, due to its low quality, such evidence is only hypothesis-generating. Nonetheless, it provides a rationale for future randomized controlled trials of nephrology follow-up in AKI patients. SUMMARY AT A GLANCE The present meta-analysis assessed the effect of nephrology follow-up on patients' clinical outcomes, and suggested long-term survival benefits in acute kidney injury (AKI) survivors. Although the study inherently comprises potential risks of bias due to paucity of available data, the results provide a rationale for future randomized controlled trials.