Predicting dry weight change in Hemodialysis patients using machine learning

Abstract

Background Machine Learning has been increasingly used in the medical field, including managing patients undergoing hemodialysis. The random forest classifier is a Machine Learning method that can generate high accuracy and interpretability in the data analysis of various diseases. We attempted to apply Machine Learning to adjust dry weight, the appropriate volume status of patients undergoing hemodialysis, which requires a complex decision-making process considering multiple indicators and the patient’s physical conditions. Methods All medical data and 69,375 dialysis records of 314 Asian patients undergoing hemodialysis at a single dialysis center in Japan between July 2018 and April 2020 were collected from the electronic medical record system. Using the random forest classifier, we developed models to predict the probabilities of adjusting the dry weight at each dialysis session. Results The areas under the receiver-operating-characteristic curves of the models for adjusting the dry weight upward and downward were 0.70 and 0.74, respectively. The average probability of upward adjustment of the dry weight had sharp a peak around the actual change over time, while the average probability of downward adjustment of the dry weight formed a gradual peak. Feature importance analysis revealed that median blood pressure decline was a strong predictor for adjusting the dry weight upward. In contrast, elevated serum levels of C-reactive protein and hypoalbuminemia were important indicators for adjusting the dry weight downward. Conclusions The random forest classifier should provide a helpful guide to predict the optimal changes to the dry weight with relative accuracy and may be useful in clinical practice.

Machine learning models to predict post-dialysis blood pressure in children and young adults on maintenance hemodialysis

“…Similarly, Bi et al developed a time series-based regression model that predicted weight fluctuations in adult HD patients using Electronic Health Records (EHR) 7 . More recently, Inoue et al took a different approach using a random forest classifier to predict the probability of adjusting DW at each dialysis session 8 . In this study, we chose to predict BP instead since there is currently no "gold standard" method to measure DW and therefore the accuracy of a ML model to predict DW cannot be reliably measured.…”

“…They achieved remarkable accuracy (> 95%) in predicting DW within a 0.5 kg absolute error margin. More recently, Inoue et al developed a random forest classifier model to help guide dry weight adjustment in hemodialysis patients 8 . On the other hand, the evidence for the utility of ML in children on HD is very limited.…”