Key result
Machine learning predictive models for acute kidney injury in general hospital populations achieved a cross-validated area under the curve ranging from 0.720 to 0.764.
Why the study?
AKI in hospitalized patients increases risks of chronic kidney disease, stroke, and heart disease, but current prediction research pays little attention to model building strategies that meet complex clinical application scenarios.
Can machine learning models accurately predict acute kidney injury in general hospital populations using electronic medical records?
Cohort (n=76,957)
No
Can machine learning models accurately predict acute kidney injury in general hospital populations using electronic medical records?
Effect estimate: AUC 0.720-0.764
Machine learning models built from multiple clinical perspectives can effectively predict acute kidney injury in general inpatient populations with an AUC of 0.720-0.764.
ML models show moderate AKI prediction accuracy in inpatients; leaves open clinical utility pending prospective validation.
OBJECTIVES: Acute kidney injury (AKI) in hospitalized patients puts them at much higher risk for developing future health problems such as chronic kidney disease, stroke, and heart disease. Accurate AKI prediction would allow timely prevention and intervention. However, current AKI prediction researches pay less attention to model building strategies that meet complex clinical application scenario. This study aims to build and evaluate AKI prediction models from multiple perspectives that reflect different clinical applications. MATERIALS AND METHODS: A retrospective cohort of 76 957 encounters and relevant clinical variables were extracted from a tertiary care, academic hospital electronic medical record (EMR) system between November 2007 and December 2016. Five machine learning methods were used to build prediction models. Prediction tasks from 4 clinical perspectives with different modeling and evaluation strategies were designed to build and evaluate the models. RESULTS: Experimental analysis of the AKI prediction models built from 4 different clinical perspectives suggest a realistic prediction performance in cross-validated area under the curve ranging from 0.720 to 0.764. DISCUSSION: Results show that models built at admission is effective for predicting AKI events in the next day; models built using data with a fixed lead time to AKI onset is still effective in the dynamic clinical application scenario in which each patient's lead time to AKI onset is different. CONCLUSION: To our best knowledge, this is the first systematic study to explore multiple clinical perspectives in building predictive models for AKI in the general inpatient population to reflect real performance in clinical application.
No takes yet. Share an insight, caveat, or question.
He et al. (2018) conducted a cohort in Acute kidney injury (AKI) (n=76,957). Machine learning predictive models was evaluated on Prediction of acute kidney injury (cross-validated area under the curve) (AUC 0.720-0.764). Machine learning predictive models for acute kidney injury in general hospital populations achieved a cross-validated area under the curve ranging from 0.720 to 0.764.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: