Identifying Sub-Phenotypes of Acute Kidney Injury using Structured and Unstructured Electronic Health Record Data with Memory Networks

This study used a memory network-based deep learning approach to discover AKI sub-phenotypes using structured and unstructured electronic health record (EHR) data of patients before AKI diagnosis. We leveraged a real world critical care EHR corpus including 37,486 ICU stays. Our approach identified three distinct sub-phenotypes: sub-phenotype I is with an average age of 63.03±17.25years, and is characterized by mild loss of kidney excretory function (Serum Creatinine (SCr) 1.55±0.34 mg/dL, estimated Glomerular Filtration Rate Test (eGFR) 107.65±54.98 mL/min/1.73m2). These patients are more likely to develop stage I AKI. Sub-phenotype II is with average age 66.81±10.43years, and was characterized by severe loss of kidney excretory function (SCr 1.96±0.49 mg/dL, eGFR 82.19±55.92 mL/min/1.73m2). These patients are more likely to develop stage III AKI. Sub-phenotype III is with average age 65.07±11.32years, and was characterized moderate loss of kidney excretory function and thus more likely to develop stage II AKI (SCr 1.69±0.32 mg/dL, eGFR 93.97±56.53 mL/min/1.73m2). Both SCr and eGFR are significantly different across the three sub-phenotypes with statistical testing plus postdoc analysis, and the conclusion still holds after age adjustment.Graphical abstractWe propose a deep learning model architecture to identify sub-phenotypes of AKI using longitudinal structured and unstructured EHR data. An ICU stay representation v is derived by integrating structured and unstru...
Source: Journal of Biomedical Informatics - Category: Information Technology Source Type: research