Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Le S

PROVIDER: S-EPMC8116756 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAcute 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.ObjectiveThe 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.MethodsWe 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.ResultsThe 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.ConclusionsNAVOY 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.

Project description:BackgroundLarge studies evaluating pediatric acute kidney injury (AKI) epidemiology and outcomes are lacking, partially due to underuse of large administrative health care data.ObjectiveTo assess the diagnostic accuracy of administrative health care data-defined AKI in children admitted to the pediatric intensive care unit (PICU).DesignRetrospective cohort study utilizing chart and administrative data.SettingChildren admitted to the PICU at 2 centers in Montreal, QC.PatientsPatients between 0 and 18 years old with a provincial health insurance number, without end-stage renal disease and admitted to the PICU between January 1, 2003, and March 31, 2005, were included.MeasurementsThe AKI was defined from chart data using the Kidney Disease: Improving Global Outcomes (KDIGO) definition (Chart-AKI). The AKI defined using administrative health data (Admin-AKI) was based on International Classification of Disease, Ninth Revision (ICD-9) AKI codes.MethodsData available from retrospective chart review, including baseline and PICU patient characteristics, and serum creatinine (SCr) and urine output (UO) values during PICU admission, were merged with provincial administrative health care data containing diagnostic and procedure codes used for ascertaining Admin-AKI. Sensitivity, specificity, positive, and negative predictive value of Admin-AKI compared with Chart-AKI (reference standard) were calculated. Univariable associations between Admin-AKI and hospital mortality were evaluated.ResultsA total of 2051 patients (55% male, mean age at admission 6.1 ± 5.8 years, 355 cardiac surgery, 1696 noncardiac surgery) were included. The AKI defined by SCr or UO criteria occurred in 52% of cardiac surgery patients and 24% of noncardiac surgery patients. Overall, Admin-AKI detected Chart-AKI with low sensitivity, but high specificity in cardiac and noncardiac surgery patients. Sensitivity increased by 1.5 to 2 fold with each increase in AKI severity stage. Admin-AKI was associated with hospital mortality (13% in Admin-AKI vs 2% in non-AKI, P < .001).LimitationsThese data were generated in a PICU population; future research should study non-PICU populations.ConclusionsUse of administrative health care data to define AKI in children leads to AKI incidence underestimation. However, for detecting more severe AKI, sensitivity is higher, while maintaining high specificity.