Prediction and visualization of acute kidney injury in intensive care unit using one-dimensional convolutional neural networks based on routinely collected data. (July 2021)

• Record Type: Journal Article
• Authors: Sato, Noriaki; Uchino, Eiichiro; Kojima, Ryosuke; Hiragi, Shusuke; Yanagita, Motoko; Okuno, Yasushi
• Is Part Of: Computer methods and programs in biomedicine. Volume 206(2021)
• Publication Date: 2021-07
• Subjects: Acute kidney injury -- Convolutional neural networks -- Intensive care unit -- Visualization; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106129
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Acute kidney injury (AKI) occurs frequently in the intensive care unit and it is important to identify high-risk patients. We proposed a system to predict AKI using convolutional neural networks with providing the basis of prediction. The proposed system could predict AKI in moderate performance, and provided the reasonable interpretation. Abstract: Background: Acute kidney injury (AKI) occurs frequently in in-hospital patients, especially in the intensive care unit (ICU), due to various etiologies including septic shock. It is clinically important to identify high-risk patients at an early stage and perform the appropriate intervention. Methods: We proposed a system to predict AKI using one-dimensional convolutional neural networks (1D-CNN) with the real-time calculation of the probability of developing AKI, along with the visualization of the rationale behind prediction using score-weighted class activation mapping and guided backpropagation. The system was applied to predicting developing AKI based on the KDIGO guideline in time windows of 24 to 48 h using data of 0 to 24 h after admission to ICU. Results: The comparison result of multiple algorithms modeling time series data indicated that the proposed 1D-CNN model achieved higher performance compared to the other models, with the mean area under the receiver operating characteristic curve of 0.742 ± 0.010 for predicting stage 1, and 0.844 ± 0.029 for stage 2 AKI using the input of the vital signs, the demographic information, and serum creatinine values. The visualization results suggested the reasonable interpretation that time points with higher respiratory rate, lower blood pressure, as well as lower SpO2, had higher attention in terms of predicting AKI, and thus important for prediction. Conclusions: We presumed the proposed system's potential usefulness as it could be applied and transferred to almost any ICU setting that stored the time series data corresponding to vital signs.