Dataset Information

Assessment of acute kidney injury risk using a machine-learning guided generalized structural equation model: a cohort study.

ABSTRACT:

Background

Acute kidney injury is common in the surgical intensive care unit (ICU). It is associated with poor patient outcomes and high healthcare resource usage. This study's primary objective is to help identify which ICU patients are at high risk for acute kidney injury. Its secondary objective is to examine the effect of acute kidney injury on a patient's prognosis during and after the ICU admission.

Methods

A retrospective cohort of patients admitted to a Singaporean surgical ICU between 2015 to 2017 was collated. Patients undergoing chronic dialysis were excluded. The outcomes were occurrence of ICU acute kidney injury, hospital mortality and one-year mortality. Predictors were identified using decision tree algorithms. Confirmatory analysis was performed using a generalized structural equation model.

Results

A total of 201/940 (21.4%) patients suffered acute kidney injury in the ICU. Low ICU haemoglobin levels, low ICU bicarbonate levels, ICU sepsis, low pre-ICU estimated glomerular filtration rate (eGFR) and congestive heart failure was associated with the occurrence of ICU acute kidney injury. Acute kidney injury, together with old age (>?70?years), and low pre-ICU eGFR, was associated with hospital mortality, and one-year mortality. ICU haemoglobin level was discretized into 3 risk categories for acute kidney injury: high risk (haemoglobin ?9.7?g/dL), moderate risk (haemoglobin between 9.8-12?g/dL), and low risk (haemoglobin >?12?g/dL).

Conclusion

The occurrence of acute kidney injury is common in the surgical ICU. It is associated with a higher risk for hospital and one-year mortality. These results, in particular the identified haemoglobin thresholds, are relevant for stratifying a patient's acute kidney injury risk.

SUBMITTER: Wong WEJ

PROVIDER: S-EPMC7898752 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Assessment of acute kidney injury risk using a machine-learning guided generalized structural equation model: a cohort study.

Wong Wen En Joseph WEJ Chan Siew Pang SP Yong Juin Keith JK Tham Yen Yu Sherlyn YYS Lim Jie Rui Gerald JRG Sim Ming Ann MA Soh Chai Rick CR Ti Lian Kah LK Chew Tsong Huey Sophia THS

BMC nephrology 20210222 1

<h4>Background</h4>Acute kidney injury is common in the surgical intensive care unit (ICU). It is associated with poor patient outcomes and high healthcare resource usage. This study's primary objective is to help identify which ICU patients are at high risk for acute kidney injury. Its secondary objective is to examine the effect of acute kidney injury on a patient's prognosis during and after the ICU admission.<h4>Methods</h4>A retrospective cohort of patients admitted to a Singaporean surgica ...[more]

PMID: 33618695

Similar Datasets

Project description:BackgroundThe current acute kidney injury (AKI) risk prediction model for patients undergoing percutaneous coronary intervention (PCI) from the American College of Cardiology (ACC) National Cardiovascular Data Registry (NCDR) employed regression techniques. This study aimed to evaluate whether models using machine learning techniques could significantly improve AKI risk prediction after PCI.Methods and findingsWe used the same cohort and candidate variables used to develop the current NCDR CathPCI Registry AKI model, including 947,091 patients who underwent PCI procedures between June 1, 2009, and June 30, 2011. The mean age of these patients was 64.8 years, and 32.8% were women, with a total of 69,826 (7.4%) AKI events. We replicated the current AKI model as the baseline model and compared it with a series of new models. Temporal validation was performed using data from 970,869 patients undergoing PCIs between July 1, 2016, and March 31, 2017, with a mean age of 65.7 years; 31.9% were women, and 72,954 (7.5%) had AKI events. Each model was derived by implementing one of two strategies for preprocessing candidate variables (preselecting and transforming candidate variables or using all candidate variables in their original forms), one of three variable-selection methods (stepwise backward selection, lasso regularization, or permutation-based selection), and one of two methods to model the relationship between variables and outcome (logistic regression or gradient descent boosting). The cohort was divided into different training (70%) and test (30%) sets using 100 different random splits, and the performance of the models was evaluated internally in the test sets. The best model, according to the internal evaluation, was derived by using all available candidate variables in their original form, permutation-based variable selection, and gradient descent boosting. Compared with the baseline model that uses 11 variables, the best model used 13 variables and achieved a significantly better area under the receiver operating characteristic curve (AUC) of 0.752 (95% confidence interval [CI] 0.749-0.754) versus 0.711 (95% CI 0.708-0.714), a significantly better Brier score of 0.0617 (95% CI 0.0615-0.0618) versus 0.0636 (95% CI 0.0634-0.0638), and a better calibration slope of observed versus predicted rate of 1.008 (95% CI 0.988-1.028) versus 1.036 (95% CI 1.015-1.056). The best model also had a significantly wider predictive range (25.3% versus 21.6%, p < 0.001) and was more accurate in stratifying AKI risk for patients. Evaluated on a more contemporary CathPCI cohort (July 1, 2015-March 31, 2017), the best model consistently achieved significantly better performance than the baseline model in AUC (0.785 versus 0.753), Brier score (0.0610 versus 0.0627), calibration slope (1.003 versus 1.062), and predictive range (29.4% versus 26.2%). The current study does not address implementation for risk calculation at the point of care, and potential challenges include the availability and accessibility of the predictors.ConclusionsMachine learning techniques and data-driven approaches resulted in improved prediction of AKI risk after PCI. The results support the potential of these techniques for improving risk prediction models and identification of patients who may benefit from risk-mitigation strategies.

Dataset Information

Assessment of acute kidney injury risk using a machine-learning guided generalized structural equation model: a cohort study.

Background

Methods

Results

Conclusion

Publications

Assessment of acute kidney injury risk using a machine-learning guided generalized structural equation model: a cohort study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure