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

by   Zhenxing Xu, et al.

Acute Kidney Injury (AKI) is a common clinical syndrome characterized by the rapid loss of kidney excretory function, which aggravates the clinical severity of other diseases in a large number of hospitalized patients. Accurate early prediction of AKI can enable in-time interventions and treatments. However, AKI is highly heterogeneous, thus identification of AKI sub-phenotypes can lead to an improved understanding of the disease pathophysiology and development of more targeted clinical interventions. This study used a memory network-based deep learning approach to discover predictive 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 ± 17.25 years, and is characterized by mild loss of kidney excretory function (Serum Creatinne (SCr) 1.55± 0.34 mg/dL, estimated Glomerular Filtration Rate Test (eGFR) 107.65± 54.98 mL/min/1.73m^2). These patients are more likely to develop stage I AKI. Sub-phenotype II is with average age 66.81 ± 10.43 years, and was characterized by severe loss of kidney excretory function (SCr 1.96± 0.49 mg/dL, eGFR 82.19± 55.92 mL/min/1.73m^2). These patients are more likely to develop stage III AKI. Sub-phenotype III is with average age 65.07 ± 11.32 years, 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/1.73m^2). 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.


Predicting Severe Sepsis Using Text from the Electronic Health Record

Employing a machine learning approach we predict, up to 24 hours prior, ...

Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives

Background: Electronic Health Records (EHRs) contain rich information of...

Risk markers by sex and age group for in-hospital mortality in patients with STEMI or NSTEMI: an approach based on machine learning

Machine learning (ML) has demonstrated promising results in the identifi...

Predicting Progression of Age-related Macular Degeneration from Fundus Images using Deep Learning

Background: Patients with neovascular age-related macular degeneration (...

Improving Clinical Disease Sub‐typing and Future Events Prediction through a Chest CT based Deep Learning Approach

Purpose To develop and evaluate a deep learning (DL) approach to extract...

Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts

While deep learning has shown promise in improving the automated diagnos...

Please sign up or login with your details

Forgot password? Click here to reset