Prediction of chronic kidney disease progression using recurrent neural network and electronic health records

Abstract

Chronic kidney disease (CKD) is a progressive loss in kidney function. Early detection of patients who will progress to late-stage CKD is of paramount importance for patient care. To address this, we develop a pipeline to process longitudinal electronic heath records (EHRs) and construct recurrent neural network (RNN) models to predict CKD progression from stages II/III to stages IV/V. The RNN model generates predictions based on time-series records of patients, including repeated lab tests and other clinical variables. Our investigation reveals that using a single variable, the recorded estimated glomerular filtration rate (eGFR) over time, the RNN model achieves an average area under the receiver operating characteristic curve (AUROC) of 0.957 for predicting future CKD progression. When additional clinical variables, such as demographics, vital information, lab test results, and health behaviors, are incorporated, the average AUROC increases to 0.967. In both scenarios, the standard deviation of the AUROC across cross-validation trials is less than 0.01, indicating a stable and high prediction accuracy. Our analysis results demonstrate the proposed RNN model outperforms existing standard approaches, including static and dynamic Cox proportional hazards models, random forest, and LightGBM. The utilization of the RNN model and the time-series data of previous eGFR measurements underscores its potential as a straightforward and effective tool for assessing the clinical risk of CKD patients concerning their disease progression.

Predicting the Progression of Chronic Kidney Disease: A Systematic Review of Artificial Intelligence and Machine Learning Approaches

“…Each of these techniques offers unique strengths and capabilities, and their performance may vary depending on the specific characteristics of the dataset and the prediction task at hand. [11]. The identification of key predictive features and biomarkers is another crucial aspect of these studies.…”

“…Additionally, the integration of AI/ML techniques with EHRs and CDSS holds immense potential for improving patient care and resource allocation [7,11]. By leveraging these predictive models, healthcare providers can receive timely alerts or notifications when patients approach critical risk thresholds, enabling early referrals for nephrology consultations, diagnostic evaluations, and initiation of appropriate management strategies.…”

“…For instance,Makino et al (2019) demonstrated the significance of longitudinal data in improving prediction performance for DKD progression[9]. Similarly,Zhu et al (2023) reported that including longitudinal eGFR measurements significantly improved the prediction accuracy of their LSTM RNN model for CKD progression…”

“…By leveraging large volumes of patient data, including demographic information, clinical measurements, laboratory results, and longitudinal records, AI/ML algorithms can uncover intricate patterns and relationships that may not be apparent through traditional statistical methods. These techniques can handle complex, high-dimensional data and capture nonlinear relationships between multiple variables, making them well-suited for predicting CKD progression, which is influenced by a multitude of factors [10,11].…”

Predictive Modeling of Kuwaiti Chronic Kidney Diseases (KCKD): Leveraging Electronic Health Records for Clinical Decision-Making

“…Y. Zhu et al [7] presented a unique method utilizing longitudinal patient Electronic Health Records (EHRs) to predict the course of CKD. They forecasted the course of CKD with impressive accuracy by combining an AI prediction model with an EHR preprocessing pipeline.…”