Utilizing electronic health records to predict acute kidney injury risk and outcomes: workgroup statements from the 15(th) ADQI Consensus Conference

External Validation, Re-Calibration, and Extension of a Prediction Model of Early Acute Kidney Injury in Critically Ill Children using Multi-Center Data

Background

Acute kidney injury (AKI) is common among children with critical illness and is associated with high morbidity and mortality. Risk prediction models designed for clinical decision support implementation offer an opportunity to identify and proactively mitigate AKI risks. Existing models have been primarily validated on single-center data, owing partly to the lack of appropriately detailed multicenter datasets.

Objective

To determine the accuracy of a single-center model to predict new AKI at 72 hours of ICU admission across two multicenter datasets and extend this model to improve prediction accuracy while maintaining acceptable alert burden.

Derivation and Validation Cohorts

We separately derived models in two datasets: PEDSNET-VPS, created through the linkage of PEDSnet electronic health record (EHR) extraction with Virtual Pediatric Systems (VPS); and the PICU Data Collaborative dataset, created through EHR extraction and harmonization from eight participating institutions. Derivation datasets comprised temporal and location-specific spit of these datasets (80%), while the holdout test split comprised the remaining (20%).

Prediction Model

We recalibrated an existing single-center model and measured discrimination and accuracy. We then add features guided by precision and recall measures. All features were available at 12 hours of ICU admission. We measure discrimination and accuracy at multiple cut-points and identify the features contributing most to the risk score.

Results

In two datasets comprising 186,540 ICU admissions, we report an incidence of early AKI of 2.2 - 2.7%. Initial recalibration of an existing single-center model demonstrated poor discrimination (AUROC 0.60 - 0.78). Following the addition of new features, we report higher AUROC values of 0.79 - 0.80 and AUPRC values of 0.13 - 0.21 in both datasets. We report accuracy at several cutpoints as well as cross-validate between datasets.

Conclusions

In this first use of two new multicenter datasets, we report improved discrimination and accuracy in a model designed specifically for implementation, balancing sensitivity and precision to predict patients at risk for AKI development.

Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients

Early prediction of acute kidney injury (AKI) may provide a crucial opportunity for AKI prevention. To date, no prediction model targeting AKI among general hospitalized patients in developing countries has been published. Here we show a simple, real-time, interpretable AKI prediction model for general hospitalized patients developed from a large tertiary hospital in China, which has been validated across five independent, geographically distinct, different tiered hospitals. The model containing 20 readily available variables demonstrates consistent, high levels of predictive discrimination in validation cohort, with AUCs for serum creatinine-based AKI and severe AKI within 48 h ranging from 0.74-0.85 and 0.83-0.90 for transported models and from 0.81-0.90 and 0.88-0.95 for refitted models, respectively. With optimal probability cutoffs, the refitted model could predict AKI at a median of 72 (24-198) hours in advance in internal validation, and 54-90 h in advance in external validation. Broad application of the model in the future may provide an effective, convenient and cost-effective approach for AKI prevention.

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.

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

Background

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.

Objective

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.

Methods

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.

Results

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.

Conclusions

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.

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.

Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study

Background

Acute kidney injury (AKI) is a common and serious organ dysfunction in critically ill children. Early identification and prediction of AKI are of great significance. However, current AKI criteria are insufficiently sensitive and specific, and AKI heterogeneity limits the clinical value of AKI biomarkers. This study aimed to establish and validate an explainable prediction model based on the machine learning (ML) approach for AKI, and assess its prognostic implications in children admitted to the pediatric intensive care unit (PICU).

Methods

This multicenter prospective study in China was conducted on critically ill children for the derivation and validation of the prediction model. The derivation cohort, consisting of 957 children admitted to four independent PICUs from September 2020 to January 2021, was separated for training and internal validation, and an external data set of 866 children admitted from February 2021 to February 2022 was employed for external validation. AKI was defined based on serum creatinine and urine output using the Kidney Disease: Improving Global Outcome (KDIGO) criteria. With 33 medical characteristics easily obtained or evaluated during the first 24 h after PICU admission, 11 ML algorithms were used to construct prediction models. Several evaluation indexes, including the area under the receiver-operating-characteristic curve (AUC), were used to compare the predictive performance. The SHapley Additive exPlanation method was used to rank the feature importance and explain the final model. A probability threshold for the final model was identified for AKI prediction and subgrouping. Clinical outcomes were evaluated in various subgroups determined by a combination of the final model and KDIGO criteria.

Findings

The random forest (RF) model performed best in discriminative ability among the 11 ML models. After reducing features according to feature importance rank, an explainable final RF model was established with 8 features. The final model could accurately predict AKI in both internal (AUC = 0.929) and external (AUC = 0.910) validations, and has been translated into a convenient tool to facilitate its utility in clinical settings. Critically ill children with a probability exceeding or equal to the threshold in the final model had a higher risk of death and multiple organ dysfunctions, regardless of whether they met the KDIGO criteria for AKI.

Interpretation

Our explainable ML model was not only successfully developed to accurately predict AKI but was also highly relevant to adverse outcomes in individual children at an early stage of PICU admission, and it mitigated the concern of the "black-box" issue with an undirect interpretation of the ML technique.

Funding

The National Natural Science Foundation of China, Jiangsu Province Science and Technology Support Program, Key talent of women's and children's health of Jiangsu Province, and Postgraduate Research & Practice Innovation Program of Jiangsu Province.

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.

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.

Prediction differences and implications of acute kidney injury with and without urine output criteria in adult critically ill patients

BACKGROUND

Due to the convenience of serum creatinine (SCr) monitoring and the relative complexity of urine output (UO) monitoring, most studies have predicted acute kidney injury (AKI) only based on SCr criteria. This study aimed to compare the differences between SCr alone and combined UO criteria in predicting AKI.

METHODS

We applied machine learning methods to evaluate the performance of 13 prediction models composed of different feature categories on 16 risk assessment tasks (half used only SCr criteria, half used both SCr and UO criteria). The area under receiver operator characteristic curve (AUROC), the area under precision recall curve (AUPRC) and calibration were used to assess the prediction performance.

RESULTS

In the first week after ICU admission, the prevalence of any AKI was 29% under SCr criteria alone and increased to 60% when the UO criteria was combined. Adding UO to SCr criteria can significantly identify more AKI patients. The predictive importance of feature types with and without UO was different. Using only laboratory data maintained similar predictive performance to the full feature model under only SCr criteria [e.g. for AKI within the 48-h time window after 1 day of ICU admission, AUROC (95% confidence interval) 0.83 (0.82, 0.84) vs 0.84 (0.83, 0.85)], but it was not sufficient when the UO was added [corresponding AUROC (95% confidence interval) 0.75 (0.74, 0.76) vs 0.84 (0.83, 0.85)].

CONCLUSIONS

This study found that SCr and UO measures should not be regarded as equivalent criteria for AKI staging, and emphasizes the importance and necessity of UO criteria in AKI risk assessment.

Development and validation of outcome prediction models for acute kidney injury patients undergoing continuous renal replacement therapy

Object

This study aimed to develop and validate a set of practical predictive tools that reliably estimate the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy.

Methods

The clinical data of acute kidney injury patients undergoing continuous renal replacement therapy were extracted from the Medical Information Mart for Intensive Care IV database with structured query language and used as the development cohort. An all-subset regression was used for the model screening. Predictive models were constructed via a logistic regression, and external validation of the models was performed using independent external data.

Results

Clinical prediction models were developed with clinical data from 1,148 patients and validated with data from 121 patients. The predictive model based on seven predictors (age, vasopressor use, red cell volume distribution width, lactate, white blood cell count, platelet count, and phosphate) exhibited good predictive performance, as indicated by a C-index of 0.812 in the development cohort, 0.811 in the internal validation cohort and 0.768 in the external validation cohort.

Conclusions

The model reliably predicted the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy. The predictive items are readily available, and the web-based prognostic calculator (https://libo220284.shinyapps.io/DynNomapp/) can be used as an adjunctive tool to support the management of patients.

Internal and external validation of machine learning-assisted prediction models for mechanical ventilation-associated severe acute kidney injury

BACKGROUND

Currently, very few preventive or therapeutic strategies are used for mechanical ventilation (MV)-associated severe acute kidney injury (AKI).

OBJECTIVES

We developed clinical prediction models to detect the onset of severe AKI in the first week of intensive care unit (ICU) stay during the initiation of MV.

METHODS

A large ICU database Medical Information Mart for Intensive Care IV (MIMIC-IV) was analysed retrospectively. Data were collected from the clinical information recorded at the time of ICU admission and during the initial 12 h of MV. Using univariate and multivariate analyses, the predictors were selected successively. For model development, two machine learning algorithms were compared. The primary goal was to predict the development of AKI stage 2 or 3 (AKI-23) and AKI stage 3 (AKI-3) in the first week of patients' ICU stay after initial 12 h of MV. The developed models were externally validated using another multicentre ICU database (eICU Collaborative Research Database, eICU) and evaluated in various patient subpopulations.

RESULTS

Models were developed using data from the development cohort (MIMIC-IV: 2008-2016; n = 3986); the random forest algorithm outperformed the logistic regression algorithm. In the internal (MIMIC-IV: 2017-2019; n = 1210) and external (eICU; n = 1494) validation cohorts, the incidences of AKI-23 were 154 (12.7%) and 119 (8.0%), respectively, with areas under the receiver operator characteristic curve of 0.78 (95% confidence interval [CI]: 0.74-0.82) and 0.80 (95% CI: 0.76-0.84); the incidences of AKI-3 were 81 (6.7%) and 67 (4.5%), with areas under the receiver operator characteristic curve of 0.81 (95% CI: 0.76-0.87) and 0.80 (95% CI: 0.73-0.86), respectively.

CONCLUSIONS

Models driven by machine learning and based on routine clinical data may facilitate the early prediction of MV-associated severe AKI. The validated models can be found at: https://apoet.shinyapps.io/mv_aki_2021_v2/.

Federated Learning for Electronic Health Records

In data-driven medical research, multi-center studies have long been preferred over single-center ones due to a single institute sometimes not having enough data to obtain sufficient statistical power for certain hypothesis testings as well as predictive and subgroup studies. The wide adoption of electronic health records (EHRs) has made multi-institutional collaboration much more feasible. However, concerns over infrastructures, regulations, privacy and data standardization present a challenge to data sharing across healthcare institutions. Federated Learning (FL), which allows multiple sites to collaboratively train a global model without directly sharing data, has become a promising paradigm to break the data isolation. In this study, we surveyed existing works on FL applications in EHRs and evaluated the performance of current state-of-the-art FL algorithms on two EHR machine learning tasks of significant clinical importance on a real world multi-center EHR dataset.

A Novel Risk Prediction Model for Severe Acute Kidney Injury in Intensive Care Unit Patients Receiving Fluid Resuscitation

Background

To develop a risk prediction model for the occurrence of severe acute kidney injury (AKI) in intensive care unit (ICU) patients receiving fluid resuscitation.

Methods

We conducted a secondary analysis of the Crystalloid vs. Hydroxyethyl Starch Trial (CHEST) trial, a blinded randomized controlled trial that enrolled ICU patients who received intravenous fluid resuscitation. The primary outcome was the first event in a composite outcome of doubling of serum creatinine and/or treatment with renal replacement treatment (RRT) within 28 days of randomization. The final model developed using multivariable logistic regression with backwards elimination was validated internally and then translated into a predictive equation.

Results

Six thousand seven hundred twenty-seven ICU participants were studied, among whom 745 developed the study outcome. The final model having six variables, including admission diagnosis of sepsis, illness severity score, mechanical ventilation, tachycardia, baseline estimated glomerular filtration rate and emergency admission. The model had good discrimination (c-statistic = 0.72, 95% confidence interval 0.697–0.736) and calibration (Hosmer-Lemeshow test, χ² = 14.4, p = 0.07) for the composite outcome, with a c-statistic after internal bootstrapping validation of 0.72, which revealed a low degree of over-fitting. The positive predictive value and negative predictive value were 58.8 and 89.1%, respectively. The decision curve analysis indicates a net benefit in prediction of severe AKI using the model across a range of threshold probabilities between 5 and 35%.

Conclusions

Our model, using readily available clinical variables to identify ICU patients at high risk of severe AKI achieved good predictive performance in a clinically relevant population.

Early and late acute kidney injury: temporal profile in the critically ill pediatric patient

Background

Increasing AKI diagnosis precision to refine the understanding of associated epidemiology and outcomes is a focus of recent critical care nephrology research. Timing of onset of acute kidney injury (AKI) during pediatric critical illness and impact on outcomes has not been fully explored.

Methods

This was a secondary analysis of the Assessment of Worldwide Acute Kidney Injury, Renal Angina and Epidemiology (AWARE) database. AKI was defined as per Kidney Disease: Improving Global Outcomes criteria. Early AKI was defined as diagnosed at ≤48 h after intensive care unit (ICU) admission, with any diagnosis >48 h denoted as late AKI. Transient AKI was defined as return to baseline serum creatinine ≤48 h of onset, and those without recovery fell into the persistent category. A second incidence of AKI ≥48 h after recovery was denoted as recurrent. Patients were subsequently sorted into distinct phenotypes as early-transient, late-transient, early-persistent, late-persistent and recurrent. Primary outcome was major adverse kidney events (MAKE) at 28 days (MAKE28) or at study exit, with secondary outcomes including AKI-free days, ICU length of stay and inpatient renal replacement therapy.

Results

A total of 1262 patients had AKI and were included. Overall mortality rate was 6.4% (n = 81), with 34.2% (n = 432) fulfilling at least one MAKE28 criteria. The majority of patients fell in the early-transient cohort (n = 704, 55.8%). The early-persistent phenotype had the highest odds of MAKE28 (odds ratio 7.84, 95% confidence interval 5.45–11.3), and the highest mortality rate (18.8%). Oncologic and nephrologic/urologic comorbidities at AKI diagnosis were associated with MAKE28.

Conclusion

Temporal nature and trajectory of AKI during a critical care course are significantly associated with patient outcomes, with several subtypes at higher risk for poorer outcomes. Stratification of pediatric critical care-associated AKI into distinct phenotypes is possible and may become an important prognostic tool.

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.

Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care

BACKGROUND

Acute kidney injury (AKI) in pediatric critical care patients is diagnosed using elevated serum creatinine, which occurs only after kidney impairment. There are no treatments other than supportive care for AKI once it has developed, so it is important to identify patients at risk to prevent injury. This study develops a machine learning model to learn pre-disease patterns of physiological measurements and predict pediatric AKI up to 48 h earlier than the currently established diagnostic guidelines.

METHODS

EHR data from 16,863 pediatric critical care patients between 1 month to 21 years of age from three independent institutions were used to develop a single machine learning model for early prediction of creatinine-based AKI using intelligently engineered predictors, such as creatinine rate of change, to automatically assess real-time AKI risk. The primary outcome is prediction of moderate to severe AKI (Stage 2/3), and secondary outcomes are prediction of any AKI (Stage 1/2/3) and requirement of renal replacement therapy (RRT). Predictions generate alerts allowing fast assessment and reduction of AKI risk, such as: "patient has 90% risk of developing AKI in the next 48 h" along with contextual information and suggested response such as "patient on aminoglycosides, suggest check level and review dose and indication".

RESULTS

The model was successful in predicting Stage 2/3 AKI prior to detection by conventional criteria with a median lead-time of 30 h at AUROC of 0.89. The model predicted 70% of subsequent RRT episodes, 58% of Stage 2/3 episodes, and 41% of any AKI episodes. The ratio of false to true alerts of any AKI episodes was approximately one-to-one (PPV 47%). Among patients predicted, 79% received potentially nephrotoxic medication after being identified by the model but before development of AKI.

CONCLUSIONS

As the first multi-center validated AKI prediction model for all pediatric critical care patients, the machine learning model described in this study accurately predicts moderate to severe AKI up to 48 h in advance of AKI onset. The model may improve outcome of pediatric AKI by providing early alerting and actionable feedback, potentially preventing or reducing AKI by implementing early measures such as medication adjustment.

Derivation and validation of a model to predict acute kidney injury following cardiac surgery in patients with normal renal function

BACKGROUND

The study aimed to construct a clinical model based on preoperative data for predicting acute kidney injury (AKI) following cardiac surgery in patients with normal renal function.

METHODS

A total of 22,348 consecutive patients with normal renal function undergoing cardiac surgery were enrolled. Among them, 15,701 were randomly selected for the training group and the remaining for the validation group. To develop a model visualized as a nomogram for predicting AKI, logistic regression was performed with variables selected using least absolute shrinkage and selection operator regression. The discrimination, calibration, and clinical value of the model were evaluated.

RESULTS

The incidence of AKI was 25.2% in the training group. The new model consisted of nine preoperative variables, including age, male gender, left ventricular ejection fraction, hypertension, hemoglobin, uric acid, hypomagnesemia, and oral renin-angiotensin system inhibitor and non-steroidal anti-inflammatory drug within 1 week before surgery. The model had a good performance in the validation group. The discrimination was good with an area under the receiver operating characteristic curve of 0.740 (95% confidence interval, 0.726-0.753). The calibration plot indicated excellent agreement between the model prediction and actual observations. Decision curve analysis also showed that the model was clinically useful.

CONCLUSIONS

The new model was constructed based on nine easily available preoperative clinical data characteristics for predicting AKI following cardiac surgery in patients with normal kidney function, which may help treatment decision-making, and rational utilization of medical resources.

Trajectory of AKI in hospitalized pediatric patients - impact of duration and repeat events

BACKGROUND

Peak severity of acute kidney injury (AKI) is associated with mortality in hospitalized pediatric patients. Other factors associated with AKI, such as number of AKI events, severity of AKI events, and time spent in AKI may also have associations with mortality. Characterization of these events could help to evaluate patient outcomes.

METHODS

Pediatric inpatients (<19 years of age) from 2011-2019 who were not on maintenance renal replacement therapy and had least one serum creatinine (SCr) obtained during hospital admission were included. Percent change in SCr from the minimum value in the prior 7 days was used for AKI staging according to KDIGO criteria. Maximum value for age appropriate normal was used for patients with only one SCr. Repeat AKI events were classified in patients if KDIGO criteria was met more than once with at least one SCr value between episodes that did not meet KDIGO criteria.Patient demographics were summarized and incidence of AKI was determined along with associations with mortality. AKI characterizations for the admission were developed including: AKI, repeat (>1) AKI, AKI severity (maximum KDIGO stage), and total number of AKI events. AKI duration as percent admission days in a KDIGO stage and AKI percent velocity were determined. Kaplan-Meier analysis was performed for time to 30 day survival by AKI characterization. A mixed effects logistic regression model with mortality as the dependent variable and nested in patients was developed incorporating patient variables and AKI characterizations.

RESULTS

A total of 184,297 inpatient encounters met study criteria (male 51.7%, Age 7.8 years (IQR 2.5, 13.8), mortality 0.56%). Hospital length of stay was 1.9 days (IQR 0.37, 4.8 days), 15.4% had an intensive care unit admission and 12.2% underwent mechanical ventilation. AKI occurred in 5.6% (n = 10,246) of admissions (Stage I = 4.5% (n = 8,310), Stage II = 1.3% (n = 2,363), Stage III=0.77% (n = 1,423)) and repeat AKI events occurred in 1.92% (n = 3,558). AKI was associated with mortality (OR 6.0, 95% CI 4.8, 7.6, p < 0.001) and increasing severity (KDIGO maximum stage) was associated with increased mortality. Multiple AKI events were also associated with mortality (p < 0.001),. Duration of AKI was associated with mortality (p < 0.001) but AKI velocity was not (p > 0.05).

CONCLUSIONS

AKI occurs in 5.6% of the pediatric inpatient population and multiple AKI events occur in ∼30% of these patients. Maximum KDIGO stage is most strongly associated with mortality. Multiple AKI events and AKI duration should also be considered when evaluating patient outcomes.

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.

Acute Kidney Injury in Pediatric Cardiac Intensive Care Children: Not All Admissions Are Equal: A Retrospective Study

OBJECTIVES

To describe the incidence, associated characteristics, and outcomes of the maximum severity of acute kidney injury (AKI) in a heterogeneous population of critically ill children with cardiac disease.

DESIGN

Retrospective cohort study.

SETTING

Pediatric cardiac intensive care unit (PCICU).

PARTICIPANTS

Patients admitted to the PCICU.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

From January 2018 to July 2020 all patients admitted to a tertiary PCICU were included. Only the first admission was considered. Neonates ≤seven days old were excluded. Of 742 patients, 53 were medical cases, 69 catheterization laboratory cases, and 620 surgical cases (with five subgroups). The median age was 2.47 years (interquartile range [IQR], 0.38-9.85 years), with a median Society of Thoracic Surgeons-European Association for Cardio-Thoracic Surgery score of 2 (IQR, 1-3). Median PCICU length of stay was three days (IQR, 2-7 days), and 21 (2.8%) patients died. Any incidence of AKI occurred in 70% of patients, 26% of which were classified as mild (stage 1) and 43% as severe (stages 2 and 3). AKI was diagnosed by urine output criteria in 56%, serum creatinine in 28%, and both in 16% of patients. Severe AKI occurred in subgroups as follows: medical (38%), catheterization laboratory (45%), correction (35%), palliation (55%), transplantation (85%), mechanical assistance (70%), and redo surgery (58%). Severe AKI patients were significantly older (p = 0.004), had a higher Pediatric Index of Mortality 3 score (p = 0.0004), had a higher cumulative fluid balance (p < 0.0001), and had a longer cardiopulmonary bypass time (p < 0.0001). Early AKI (≤24 hours from admission) was the most frequent presentation, with a greater proportion of severe cases in the early group compared with the intermediate (>24 and ≤48 hours) and late (>48 hours) (p < 0.0001) groups. Presentation of late severe AKI had a higher mortality (odds ratio, 4.9; 95% confidence interval, 1.8-15; p = 0.001).

CONCLUSIONS

Severe AKI occurs in 43% of cardiac children and is diagnosed early, most often by urine output criteria. Severe AKI incidence varies significantly within subgroups of cardiac patients. Late AKI is associated with worse outcomes.

Impact of integrated clinical decision support systems in the management of pediatric acute kidney injury: a pilot study

BACKGROUND

Acute kidney injury (AKI) is common but not often recognized. Early recognition and management may improve patient outcomes.

METHODS

This is a prospective, nonrandomized study of clinical decision support (CDS) system [combining electronic alert and standardized care pathway (SCP)] to evaluate AKI detection and progression in hospitalized children. The study was done in three phases: pre-, intervention (CDS) and post. During CDS, text-page with AKI stage and link to SCP was sent to patient's contact provider at diagnosis of AKI using creatinine. The SCP provided guidelines on AKI management [AEIOU: Assess cause of AKI, Evaluate drug doses, Intake-Output charting, Optimize volume status, Urine dipstick].

RESULTS

In all, 239 episodes of AKI in 225 patients (97 females, 43.1%) were analyzed. Proportion of patients with decrease in the stage of AKI after onset was 71.4% for CDS vs. 64.4% for pre- and 55% for post-CDS phases (p = 0.3). Documentation of AKI was higher during CDS (74.3% CDS vs. 47.5% pre- and 57.5% post-, p < 0.001). Significantly greater proportion of patients had nephrotoxic medications adjusted, or fluid plan changed during CDS. Patients from CDS phase had higher eGFR at discharge and at follow-up.

CONCLUSIONS

AKI remains under-recognized. CDS (electronic alerts and SCP) improve recognition and allow early intervention. This may improve long-term outcomes, but larger studies are needed.

IMPACT

Acute kidney injury can cause significant morbidity and mortality. It is under-recognized in children. Clinical decision support can be used to leverage existing data in the electronic health record to improve AKI recognition. This study demonstrates the use of a novel, electronic health record-linked, clinical decision support tool to improve the recognition of AKI and guideline-adherent clinical care.

Prediction Models for AKI in ICU: A Comparative Study

PURPOSE

To assess the performance of models for early prediction of acute kidney injury (AKI) in the Intensive Care Unit (ICU) setting.

PATIENTS AND METHODS

Data were collected from the Medical Information Mart for Intensive Care (MIMIC)-III database for all patients aged ≥18 years who had their serum creatinine (SCr) level measured for 72 h following ICU admission. Those with existing conditions of kidney disease upon ICU admission were excluded from our analyses. Seventeen predictor variables comprising patient demographics and physiological indicators were selected on the basis of the Kidney Disease Improving Global Outcomes (KDIGO) and medical literature. Six models from three types of methods were tested: Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Decision Machine (LightGBM), and Convolutional Neural Network (CNN). The area under receiver operating characteristic curve (AUC), accuracy, precision, recall and F-measure (F1) were calculated for each model to evaluate performance.

RESULTS

We extracted the ICU records of 17,205 patients from MIMIC-III dataset. LightGBM had the best performance, with all evaluation indicators achieving the highest value (average AUC = 0.905, F1 = 0.897, recall = 0.836). XGBoost had the second best performance and LR, RF, SVM performed similarly (P = 0.082, 0.158 and 0.710, respectively) on AUC. The CNN model achieved the lowest score for accuracy, precision, F1 and AUC. SVM and LR had relatively low recall compared with that of the other models. The SCr level had the most significant effect on the early prediction of AKI onset in LR, RF, SVM and LightGBM.

CONCLUSION

LightGBM demonstrated the best capability for predicting AKI in the first 72 h of ICU admission. LightGBM and XGBoost showed great potential for clinical application owing to their high recall value. This study can provide references for artificial intelligence-powered clinical decision support systems for AKI early prediction in the ICU setting.

Nephrotoxin Stewardship

Drugs are the third leading cause of acute kidney injury (AKI) in critically ill patients. Nephrotoxin stewardship ensures a structured and consistent approach to safe medication use and prevention of patient harm. Comprehensive nephrotoxin stewardship requires coordinated patient care management strategies for safe medication use, ensuring kidney health, and avoiding unnecessary costs to improve the use of nephrotoxins, renally eliminated drugs, and kidney disease treatments. Implementing nephrotoxin stewardship reduces medication errors and adverse drug events, prevents or reduces severity of drug-associated AKI, prevents progression to or worsening of chronic kidney disease, and alleviates financial burden on the health care system.

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.

A Review on the Application and Limitations of Administrative Health Care Data for the Study of Acute Kidney Injury Epidemiology and Outcomes in Children

Administrative health care databases contain valuable patient information generated by health care encounters. These "big data" repositories have been increasingly used in epidemiological health research internationally in recent years as they are easily accessible and cost-efficient and cover large populations for long periods. Despite these beneficial characteristics, it is also important to consider the limitations that administrative health research presents, such as issues related to data incompleteness and the limited sensitivity of the variables. These barriers potentially lead to unwanted biases and pose threats to the validity of the research being conducted. In this review, we discuss the effectiveness of health administrative data in understanding the epidemiology of and outcomes after acute kidney injury (AKI) among adults and children. In addition, we describe various validation studies of AKI diagnostic or procedural codes among adults and children. These studies reveal challenges of AKI research using administrative data and the lack of this type of research in children and other subpopulations. Additional pediatric-specific validation studies of administrative health data are needed to promote higher volume and increased validity of this type of research in pediatric AKI, to elucidate the large-scale epidemiology and patient and health systems impacts of AKI in children, and to devise and monitor programs to improve clinical outcomes and process of care.

For Whom the Bell Tolls: Acute Kidney Injury and Electronic Alerts for the Pediatric Nephrologist

With the advent of the electronic medical record, automated alerts have allowed for improved recognition of patients with acute kidney injury (AKI). Pediatric patients have the opportunity to benefit from such alerts, as those with a diagnosis of AKI are at risk of developing long-term consequences including reduced renal function and hypertension. Despite extensive studies on the implementation of electronic alerts, their overall impact on clinical outcomes have been unclear. Understanding the results of these studies have helped define best practices in developing electronic alerts with the aim of improving their impact on patient care. As electronic alerts for AKI are applied to pediatric patients, identifying their strengths and limitations will allow for continued improvement in its use and efficacy.

Artificial Intelligence in Acute Kidney Injury: From Static to Dynamic Models

Artificial intelligence (AI) is the development of computer systems that normally require human intelligence. In the field of acute kidney injury (AKI) AI has led to an evolution of risk prediction models. In the past, static prediction models were developed using baseline (eg, preoperative) data to evaluate AKI risk. Newer models which incorporated baseline as well as evolving data collected during a hospital admission have shown improved predicative abilities. In this review, we will summarize the advances made in AKI risk prediction over the last several years, including a shift toward more dynamic, real-time, electronic medical record-based models. In addition, we will be discussing the role of electronic AKI alerts and decision support tools. Recent studies have demonstrated improved patient outcomes through the use of these tools which monitor for nephrotoxin medication exposures as well as provide kidney focused care bundles for patients at high risk for severe AKI. Finally, we will briefly discuss the pitfalls and implications of implementing these scores, alerts, and support tools.

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.

Which risk predictors are more likely to indicate severe AKI in hospitalized patients?

OBJECTIVES

Acute kidney injury (AKI) is a sudden episode of kidney failure or damage and the risk of AKI is determined by the complex interactions of patient factors. In this study, we aimed to find out which risk factors in hospitalized patients are more likely to indicate severe AKI.

METHODS

We constructed a retrospective cohort of adult patients from all inpatient units of a tertiary care academic hospital between November 2007 and December 2016. AKI predictors included demographic information, admission and discharge dates, medications, laboratory values, past medical diagnoses and admission diagnosis. We developed a machine learning-based knowledge mining model and a screening framework to analyze which risk predictors are more likely to imply severe AKI in hospitalized populations.

RESULTS

Among the final analysis cohort of 76,957 hospital admissions, AKI occurred in 7,259 (9.43 %) with 6,396 (8.31 %) at stage 1, 678 (0.88 %) at stage 2, and 185 (0.24 %) at stage 3. We compared the non-AKI (without AKI) vs any AKI (stages 1-3), and mild AKI (stage 1) vs severe AKI (stages 2 and 3), where the best cross-validated area under the receiver operator characteristic curve (AUC) were 0.81 (95 % CI, 0.79-0.82) and 0.66 (95 % CI, 0.62-0.71), respectively. Using the developed knowledge mining model and screening framework, we identified 33 risk predictors indicating that severe AKI may occur.

CONCLUSIONS

This study screened out 33 risk predictors that are more likely to indicate severe AKI in hospitalized patients, which would help strengthen the early care and prevention of patients.

Changing relative risk of clinical factors for hospital-acquired acute kidney injury across age groups: a retrospective cohort study

Background

Likelihood of developing acute kidney injury (AKI) increases with age. We aimed to explore whether the predictability of AKI varies between age groups and assess the volatility of risk factors using electronic medical records (EMR).

Methods

We constructed a retrospective cohort of adult patients from all inpatient units of a tertiary care academic hospital and stratified it into four age groups: 18–35, 36–55, 56–65, and > 65. Potential risk factors collected from EMR for the study cohort included demographics, vital signs, medications, laboratory values, past medical diagnoses, and admission diagnoses. AKI was defined based on the Kidney Disease Improving Global Outcomes (KDIGO) serum creatinine criteria. We analyzed relative importance of the risk factors in predicting AKI using Gradient Boosting Machine algorithm and explored the predictability of AKI across age groups using multiple machine learning models.

Results

In our cohort, older patients showed a significantly higher incidence of AKI than younger adults: 18–35 (7.29%), 36–55 (8.82%), 56–65 (10.53%), and > 65 (10.55%) (p < 0.001). However, the predictability of AKI decreased with age, where the best cross-validated area under the receiver operating characteristic curve (AUROC) achieved for age groups 18–35, 36–55, 56–65, and > 65 were 0.784 (95% CI, 0.769–0.800), 0.766 (95% CI, 0.754–0.777), 0.754 (95% CI, 0.741–0.768), and 0.725 (95% CI, 0.709–0.737), respectively. We also observed that the relative risk of AKI predictors fluctuated between age groups.

Conclusions

As complexity of the cases increases with age, it is more difficult to quantify AKI risk for older adults in inpatient population.

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.

A Time-Updated, Parsimonious Model to Predict AKI in Hospitalized Children

BACKGROUND

Timely prediction of AKI in children can allow for targeted interventions, but the wealth of data in the electronic health record poses unique modeling challenges.

METHODS

We retrospectively reviewed the electronic medical records of all children younger than 18 years old who had at least two creatinine values measured during a hospital admission from January 2014 through January 2018. We divided the study population into derivation, and internal and external validation cohorts, and used five feature selection techniques to select 10 of 720 potentially predictive variables from the electronic health records. Model performance was assessed by the area under the receiver operating characteristic curve in the validation cohorts. The primary outcome was development of AKI (per the Kidney Disease Improving Global Outcomes creatinine definition) within a moving 48-hour window. Secondary outcomes included severe AKI (stage 2 or 3), inpatient mortality, and length of stay.

RESULTS

Among 8473 encounters studied, AKI occurred in 516 (10.2%), 207 (9%), and 27 (2.5%) encounters in the derivation, and internal and external validation cohorts, respectively. The highest-performing model used a machine learning-based genetic algorithm, with an overall receiver operating characteristic curve in the internal validation cohort of 0.76 [95% confidence interval (CI), 0.72 to 0.79] for AKI, 0.79 (95% CI, 0.74 to 0.83) for severe AKI, and 0.81 (95% CI, 0.77 to 0.86) for neonatal AKI. To translate this prediction model into a clinical risk-stratification tool, we identified high- and low-risk threshold points.

CONCLUSIONS

Using various machine learning algorithms, we identified and validated a time-updated prediction model of ten readily available electronic health record variables to accurately predict imminent AKI in hospitalized children.

Diagnostics, Risk Factors, Treatment and Outcomes of Acute Kidney Injury in a New Paradigm

Acute kidney injury (AKI) is a common clinical condition among patients admitted in the hospitals. The condition is associated with both increased short-term and long-term mortality. With the development of a standardized definition for AKI and the acknowledgment of the impact of AKI on patient outcomes, there has been increased recognition of AKI. Two advances from past decades, the usage of computer decision support and the discovery of AKI biomarkers, have the ability to advance the diagnostic method to and further management of AKI. The increasingly widespread use of electronic health records across hospitals has substantially increased the amount of data available to investigators and has shown promise in advancing AKI research. In addition, progress in the finding and validation of different forms of biomarkers of AKI within diversified clinical environments and has provided information and insight on testing, etiology and further prognosis of AKI, leading to future of precision and personalized approach to AKI management. In this this article, we discussed the changing paradigms in AKI: from mechanisms to diagnostics, risk factors, and management of AKI.

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.

Artificial Intelligence in Acute Kidney Injury Risk Prediction

Acute kidney injury (AKI) is a frequent complication in hospitalized patients, which is associated with worse short and long-term outcomes. It is crucial to develop methods to identify patients at risk for AKI and to diagnose subclinical AKI in order to improve patient outcomes. The advances in clinical informatics and the increasing availability of electronic medical records have allowed for the development of artificial intelligence predictive models of risk estimation in AKI. In this review, we discussed the progress of AKI risk prediction from risk scores to electronic alerts to machine learning methods.

Early prediction of acquiring acute kidney injury for older inpatients using most effective laboratory test results

BACKGROUND

Acute Kidney Injury (AKI) is common among inpatients. Severe AKI increases all-cause mortality especially in critically ill patients. Older patients are more at risk of AKI because of the declined renal function, increased comorbidities, aggressive medical treatments, and nephrotoxic drugs. Early prediction of AKI for older inpatients is therefore crucial.

METHODS

We use 80 different laboratory tests from the electronic health records and two types of representations for each laboratory test, that is, we consider 160 (laboratory test, type) pairs one by one to do the prediction. By proposing new similarity measures and employing the classification technique of the K nearest neighbors, we are able to identify the most effective (laboratory test, type) pairs for the prediction. Furthermore, in order to know how early and accurately can AKI be predicted to make our method clinically useful, we evaluate the prediction performance of up to 5 days prior to the AKI event.

RESULTS

We compare our method with two existing works and it shows our method outperforms the others. In addition, we implemented an existing method using our dataset, which also shows our method has a better performance. The most effective (laboratory test, type) pairs found for different prediction times are slightly different. However, Blood Urea Nitrogen (BUN) is found the most effective (laboratory test, type) pair for most prediction times.

CONCLUSION

Our study is first to consider the last value and the trend of the sequence for each laboratory test. In addition, we define the exclusion criteria to identify the inpatients who develop AKI during hospitalization and we set the length of the data collection window to ensure the laboratory data we collect is close to the AKI time. Furthermore, we individually select the most effective (laboratory test, type) pairs to do the prediction for different days of early prediction. In the future, we will extend this approach and develop a system for early prediction of major diseases to help better disease management for inpatients.

Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone

BACKGROUND

Cardiovascular diseases kill approximately 17 million people globally every year, and they mainly exhibit as myocardial infarctions and heart failures. Heart failure (HF) occurs when the heart cannot pump enough blood to meet the needs of the body.Available electronic medical records of patients quantify symptoms, body features, and clinical laboratory test values, which can be used to perform biostatistics analysis aimed at highlighting patterns and correlations otherwise undetectable by medical doctors. Machine learning, in particular, can predict patients' survival from their data and can individuate the most important features among those included in their medical records.

METHODS

In this paper, we analyze a dataset of 299 patients with heart failure collected in 2015. We apply several machine learning classifiers to both predict the patients survival, and rank the features corresponding to the most important risk factors. We also perform an alternative feature ranking analysis by employing traditional biostatistics tests, and compare these results with those provided by the machine learning algorithms. Since both feature ranking approaches clearly identify serum creatinine and ejection fraction as the two most relevant features, we then build the machine learning survival prediction models on these two factors alone.

RESULTS

Our results of these two-feature models show not only that serum creatinine and ejection fraction are sufficient to predict survival of heart failure patients from medical records, but also that using these two features alone can lead to more accurate predictions than using the original dataset features in its entirety. We also carry out an analysis including the follow-up month of each patient: even in this case, serum creatinine and ejection fraction are the most predictive clinical features of the dataset, and are sufficient to predict patients' survival.

CONCLUSIONS

This discovery has the potential to impact on clinical practice, becoming a new supporting tool for physicians when predicting if a heart failure patient will survive or not. Indeed, medical doctors aiming at understanding if a patient will survive after heart failure may focus mainly on serum creatinine and ejection fraction.

Early prediction of pediatric acute kidney injury from the emergency department: A pilot study

BACKGROUND

Identifying acute kidney injury (AKI) early can inform medical decisions key to mitigation of injury. An AKI risk stratification tool, the renal angina index (RAI), has proven better than creatinine changes alone at predicting AKI in critically ill children.

OBJECTIVE

To derive and test performance of an "acute" RAI (aRAI) in the Emergency Department (ED) for prediction of inpatient AKI and to evaluate the added yield of urinary AKI biomarkers.

METHODS

Study of pediatric ED patients with sepsis admitted and followed for 72 h. The primary outcome was inpatient AKI defined by a creatinine >1.5× baseline, 24-72 h after admission. Patients were denoted renal angina positive (RA+) for an aRAI score above a population derived cut-off. Test characteristics evaluated predictive performance of the aRAI compared to changes in creatinine and incorporation of 4 urinary biomarkers in the context of renal angina were assessed.

RESULTS

118 eligible subjects were enrolled. Mean age was 7.8 ± 6.4 years, 16% required intensive care admission. In the ED, 27% had a +RAI (22% had a >50% creatinine increase). The aRAI had an AUC of 0.92 (0.86-0.98) for prediction of inpatient AKI. For AKI prediction, RA+ demonstrated a sensitivity of 94% (69-99) and a negative predictive value of 99% (92-100) (versus sensitivity 59% (33-82) and NPV 93% (89-96) for creatinine ≥2× baseline). Biomarker analysis revealed a higher AUC for aRAI alone than any individual biomarker.

CONCLUSIONS

This pilot study finds the aRAI to be a sensitive ED-based tool for ruling out the development of in-hospital AKI.

Acute kidney injury risk-based screening in pediatric inpatients: a pragmatic randomized trial

BACKGROUND

Pediatric acute kidney injury (AKI) is common and associated with increased morbidity, mortality, and length of stay. We performed a pragmatic randomized trial testing the hypothesis that AKI risk alerts increase AKI screening.

METHODS

All intensive care and ward admissions of children aged 28 days through 21 years without chronic kidney disease from 12/6/2016 to 11/1/2017 were included. The intervention alert displayed if calculated AKI risk was > 50% and no serum creatinine (SCr) was ordered within 24 h. The primary outcome was SCr testing within 48 h of AKI risk > 50%.

RESULTS

Among intensive care admissions, 973/1909 (51%) were randomized to the intervention. Among those at risk, more SCr tests were ordered for the intervention group than for controls (418/606, 69% vs. 361/597, 60%, p = 0.002). AKI incidence and severity were the same in intervention and control groups. Among ward admissions, 5492/10997 (50%) were randomized to the intervention, and there were no differences between groups in SCr testing, AKI incidence, or severity of AKI.

CONCLUSIONS

Alerts based on real-time prediction of AKI risk increased screening rates in intensive care but not pediatric ward settings. Pragmatic clinical trials provide the opportunity to assess clinical decision support and potentially eliminate ineffective alerts.

Acute kidney injury

Acute kidney injury (AKI) is defined by a rapid increase in serum creatinine, decrease in urine output, or both. AKI occurs in approximately 10-15% of patients admitted to hospital, while its incidence in intensive care has been reported in more than 50% of patients. Kidney dysfunction or damage can occur over a longer period or follow AKI in a continuum with acute and chronic kidney disease. Biomarkers of kidney injury or stress are new tools for risk assessment and could possibly guide therapy. AKI is not a single disease but rather a loose collection of syndromes as diverse as sepsis, cardiorenal syndrome, and urinary tract obstruction. The approach to a patient with AKI depends on the clinical context and can also vary by resource availability. Although the effectiveness of several widely applied treatments is still controversial, evidence for several interventions, especially when used together, has increased over the past decade.

Machine learning versus physicians' prediction of acute kidney injury in critically ill adults: a prospective evaluation of the AKIpredictor

Background

Early diagnosis of acute kidney injury (AKI) is a major challenge in the intensive care unit (ICU). The AKIpredictor is a set of machine-learning-based prediction models for AKI using routinely collected patient information, and accessible online. In order to evaluate its clinical value, the AKIpredictor was compared to physicians’ predictions.

Methods

Prospective observational study in five ICUs of a tertiary academic center. Critically ill adults without end-stage renal disease or AKI upon admission were considered for enrollment. Using structured questionnaires, physicians were asked upon admission, on the first morning, and after 24 h to predict the development of AKI stages 2 or 3 (AKI-23) during the first week of ICU stay. Discrimination, calibration, and net benefit of physicians’ predictions were compared against the ones by the AKIpredictor.

Results

Two hundred fifty-two patients were included, 30 (12%) developed AKI-23. In the cohort of patients with predictions by physicians and AKIpredictor, the performance of physicians and AKIpredictor were respectively upon ICU admission, area under the receiver operating characteristic curve (AUROC) 0.80 [0.69–0.92] versus 0.75 [0.62–0.88] (n = 120, P = 0.25) with net benefit in ranges 0–26% versus 0–74%; on the first morning, AUROC 0.94 [0.89–0.98] versus 0.89 [0.82–0.97] (n = 187, P = 0.27) with main net benefit in ranges 0–10% versus 0–48%; after 24 h, AUROC 0.95 [0.89–1.00] versus 0.89 [0.79–0.99] (n = 89, P = 0.09) with main net benefit in ranges 0–67% versus 0–50%.

Conclusions

The machine-learning-based AKIpredictor achieved similar discriminative performance as physicians for prediction of AKI-23, and higher net benefit overall, because physicians overestimated the risk of AKI. This suggests an added value of the systematic risk stratification by the AKIpredictor to physicians’ predictions, in particular to select high-risk patients or reduce false positives in studies evaluating new and potentially harmful therapies. Due to the low event rate, future studies are needed to validate these findings.

Trial registration

ClinicalTrials.gov, NCT03574896 registration date: July 2nd, 2018

Electronic supplementary material

The online version of this article (10.1186/s13054-019-2563-x) contains supplementary material, which is available to authorized users.

Predictive Modeling of the Risk of Acute Kidney Injury in Critical Care: A Systematic Investigation of The Class Imbalance Problem

Acute Kidney Injury (AKI) in critical care is often a quickly-evolving clinical event with high morbidity and mortality. Early prediction of AKI risk in critical care setting can facilitate early interventions that are likely to provide ben- efit. Recently there have been some research on AKI prediction with patient Electronic Health Records (EHR). The class imbalance problem is encountered in such prediction setting where the number of AKI cases is usually much smaller than the controls. This study systematically investigates the impact of class imbalance on the performance of AKI prediction. We systematically investigate several class-balancing strategies to address class imbalance, includ- ing traditional statistical approaches and the proposed methods (case-control matching approach and individualized prediction approach). Our results show that the proposed class-balancing strategies can effectively improve the AKI prediction performance. Additionally, some important predictors (e.g., creatinine, chloride, and urine) for AKI can be found based on the proposed methods.

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

OBJECTIVE

To develop and validate a prediction model of acute kidney injury (AKI) of any severity that could be used for AKI surveillance and management to improve clinical outcomes.

PATIENTS AND METHODS

This retrospective cohort study was conducted in medical, surgical, and mixed intensive care units (ICUs) at Mayo Clinic in Rochester, Minnesota, including adult (≥18 years of age) ICU-unique patients admitted between October 1, 2004, and April 30, 2011. Our primary objective was prediction of AKI using extant clinical data following ICU admission. We used random forest classification to provide continuous AKI risk score.

RESULTS

We included 4572 and 1958 patients in the training and validation mutually exclusive cohorts, respectively. Acute kidney injury occurred in 1355 patients (30%) in the training cohort and 580 (30%) in the validation cohort. We incorporated known AKI risk factors and routinely measured vital characteristics and laboratory results. The model was run throughout ICU admission every 15 minutes and achieved an area under the receiver operating characteristic curve of 0.88 on validation. It was 92% sensitive and 68% specific and detected 30% of AKI cases at least 6 hours before the criterion standard time (AKI stages 1-3). For discrimination of AKI stages 2 to 3, the model had 91% sensitivity, 71% specificity, and 53% detection of AKI cases at least 6 hours before AKI onset.

CONCLUSION

We developed and validated an AKI prediction model using random forest for continuous monitoring of ICU patients. This model could be used to identify high-risk patients for preventive measures or identifying patients of prospective interventional trials.

A Survey Study of Self-Rated Patients' Knowledge About AKI in a Post-Discharge AKI Clinic

BACKGROUND

Survivors of acute kidney injury (AKI) are at risk of adverse outcomes. Post-discharge nephrology care may improve patients' AKI knowledge and prevent post-AKI complications.

OBJECTIVE

The purpose of this study was to examine patients' awareness about their AKI diagnosis and self-rated knowledge and severity of AKI before and after their first post-discharge AKI Clinic encounter.

DESIGN

We conducted a pre- and post-survey study among AKI survivors who attended a post-discharge AKI Clinic.

SETTING

AKI Clinic at the University of Kentucky Medical Center (October 2016 to December 2017). Education about AKI was based on transformative learning theory and provided through printed materials and interdisciplinary interactions between patients/caregivers and nurses, pharmacists, and nephrologists.

PATIENTS

A total of 104 patients completed the survey and were included in the analysis.

MEASUREMENTS

Three survey questions were administered before and after the first AKI Clinic encounter: Question 1 (yes-no) for awareness, and questions 2 and 3 (Likert scale, 1 = lowest to 5 = highest) for self-rated knowledge and severity of AKI.

METHODS

Two mixed-model analysis of variance (ANOVA) was used for between-group (AKI severity) and within-group (pre- and post-encounter) comparisons. Logistic regression was used to examine parameters associated with the within-group change in self-perceived knowledge.

RESULTS

Twenty-two out of 104 (21%) patients were not aware of their AKI diagnosis before the clinic encounter. Patients' self-ratings of their AKI knowledge significantly increased after the first AKI Clinic encounter (mean ± SEM: pre-visit = 1.94 ± 0.12 to post-visit = 3.88 ± 0.09, P = .001), even after adjustment for age, gender, Kidney Disease Improving Global Outcomes (KDIGO) severity stage, or poverty level. Patients with AKI stage 3 self-rated their AKI as more severe than patients with AKI stage 1 or 2.

LIMITATIONS

Our study population may not be representative of the general AKI survivor population. Administered surveys are subject to response-shift bias.

CONCLUSIONS

Patients' self-perceived knowledge about AKI significantly increased following the first post-discharge AKI Clinic encounter that included interdisciplinary education. This is the first survey study examining self-perceived AKI knowledge in AKI survivors. Further examination of AKI literacy in survivors of AKI and its effect on post-AKI outcomes is needed.

TRIAL REGISTRATION

Not applicable.