AUTHOR=Chen Zhimeng , Chen Ming , Sun Xuri , Guo Xieli , Li Qiuna , Huang Yinqiong , Zhang Yuren , Wu Lianwei , Liu Yu , Xu Jinting , Fang Yuming , Lin Xiahong 

TITLE=Analysis of the Impact of Medical Features and Risk Prediction of Acute Kidney Injury for Critical Patients Using Temporal Electronic Health Record Data With Attention-Based Neural Network

JOURNAL=Frontiers in Medicine

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2021.658665

DOI=10.3389/fmed.2021.658665

ISSN=2296-858X

ABSTRACT=Acute kidney injury (AKI) is one of the most severe consequences of kidney injury, it will also cause or aggravate the complications by the fast decline of kidney excretory function.Accurate AKI prediction, including the AKI case, AKI stage and AKI onset time interval, can provide adequate support for the effective interventions.Besides, discovering how the medical features affect the AKI result may also provide supporting information for the disease treatment. An attention-based temporal neural network approach was employed in this study for the AKI prediction and medical features impact analysis by temporal electronic health record (EHR) data of patients before AKI diagnosis. We used the publicly available dataset provided by Medical Information Mart for Intensive Care (MIMIC) for model training, validation and testing, and then the model was applied in clinical practice. The improvement of the AKI case prediction is around 5% AUC (Area Under the Receiver Operating Characteristic Curve), and the AUC value of the AKI stage prediction on AKI stage 3 is over 82%. We also analyzed the data by two steps: the associations between the medical features and the AKI case (positive or inverse), and the extent of the impact of medical features on AKI prediction result. It shows that the features, such as lactate, glucose, creatinine, Blood Urea Nitrogen (BUN), Prothrombin Time (PT) and Partial Thromboplastin Time (PTT), are positive associations with AKI case, while they are inverse associations between AKI case and the features such as Platelet, Hemoglobin, Hematocrit, Urine and International Normalized Ratio(INR). The laboratory test features such as Urine, Glucose, Creatinine, Sodium, Blood Urea Nitrogen, and the medication features such as Non-steroidal anti-inflammatory drugs, Agents acting on the renin–angiotensin system, Lipid-lowering medication were detected to have higher weights than other features in the proposed model, which may imply that these features have great impact on AKI case.