Erythropoiesis stimulating agent recommendation model using recurrent neural networks for patient with kidney failure with replacement therapy

• Published in: Computers in biology and medicine Vol. 137; p. 104718
• Main Authors: Yun, Hae-Ryong, Lee, Gyubok, Jeon, Myeong Jun, Kim, Hyung Woo, Joo, Young Su, Kim, Hyoungnae, Chang, Tae Ik, Park, Jung Tak, Han, Seung Hyeok, Kang, Shin-Wook, Kim, Wooju, Yoo, Tae-Hyun
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.10.2021; Elsevier Limited
• Subjects: Algorithms; Anemia; Blood transfusions; Computer simulation; Confidence intervals; Data collection; Dialysis; Dosage; Erythropoiesis; Erythropoiesis stimulating agent; FDA approval; Heart failure; Hemodialysis; Hemoglobin; Internal Medicine; Kidney failure with replacement therapy; Kidneys; Laboratories; Machine learning; Medical prognosis; Mortality; Neural networks; Other; Patients; Prediction models; Recurrent neural networks; Renal failure; United States > US; Erythropoiesis stimulating agent; Recurrent neural networks; Kidney failure with replacement therapy; Anemia; erythropoiesis stimulating agent; recurrent neural networks; kidney failure with replacement therapy; anemia
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2021.104718

In patients with kidney failure with replacement therapy (KFRT), optimizing anemia management in these patients is a challenging problem because of the complexities of the underlying diseases and heterogeneous responses to erythropoiesis-stimulating agents (ESAs). Therefore, we propose a ESA dose recommendation model based on sequential awareness neural networks. Data from 466 KFRT patients (12,907 dialysis sessions) in seven tertiary-care general hospitals were included in the experiment. First, a Hb prediction model was developed to simulate longitudinal heterogeneous ESA and Hb interactions. Based on the prediction model as a prospective study simulator, we built an ESA dose recommendation model to predict the required amount of ESA dose to reach a target hemoglobin level after 30 days. Each model's performance was evaluated in the mean absolute error (MAE). The MAEs presenting the best results of the prediction and recommendation model were 0.59 (95% confidence interval: 0.56–0.62) g/dL and 43.2 μg (ESAs dose), respectively. Compared to the results in the real-world clinical data, the recommendation model achieved a reduction of ESA dose (Algorithm: 140 vs. Human: 150 μg/month, P < 0.001), a more stable monthly Hb difference (Algorithm: 0.6 vs. Human: 0.8 g/dL, P < 0.001), and an improved target Hb success rate (Algorithm: 79.5% vs. Human: 62.9% for previous month's Hb < 10.0 g/dL; Algorithm: 95.7% vs. Human:73.0% for previous month's Hb 10.0–12.0 g/dL). We developed an ESA dose recommendation model for optimizing anemia management in patients with KFRT and showed its potential effectiveness in a simulated prospective study. [Display omitted] •Anemia management is challenging in patients with kidney failure with replacement therapy (KFRT).•We developed the ESA dose recommendation algorithm using recurrent neural networks (RNNs).•The algorithm can successfully achieve the target HB level while retaining a reduced ESA dose and a smaller HB difference.•RNN based anemia management in KFRT patients showed its potential effectiveness in a simulated prospective study.