Sum of previous inpatient serum creatinine measurements predicts acute kidney injury in rehospitalized patients
This work addresses AKI prediction for rehospitalized patients, offering a potentially easy-to-integrate model, though it is incremental as it builds on existing risk estimation methods with a novel feature approach.
The study tackled predicting acute kidney injury (AKI) in rehospitalized patients by using serum creatinine measurements, finding that a simple multilayer perceptron model processing the sum of previous measurements achieved an AUROC of 0.92 and AUPRC of 0.70.
Acute Kidney Injury (AKI), the abrupt decline in kidney function due to temporary or permanent injury, is associated with increased mortality, morbidity, length of stay, and hospital cost. Sometimes, simple interventions such as medication review or hydration can prevent AKI. There is therefore interest in estimating risk of AKI at hospitalization. To gain insight into this task, we employ multilayer perceptron (MLP) and recurrent neural networks (RNNs) using serum creatinine (sCr) as a lone feature. We explore different feature input structures, including variable-length look-backs and a nested formulation for rehospitalized patients with previous sCr measurements. Experimental results show that the simplest model, MLP processing the sum of sCr, had best performance: AUROC 0.92 and AUPRC 0.70. Such a simple model could be easily integrated into an EHR. Preliminary results also suggest that inpatient data streams with missing outpatient measurements---common in the medical setting---might be best modeled with a tailored architecture.