A novel approach to dry weight adjustments for dialysis patients using machine learning

BACKGROUND AND AIMS: Knowledge of the proper dry weight plays a critical role in the efficiency of dialysis and the survival of hemodialysis patients. Recently, bioimpedance spectroscopy(BIS) has been widely used for set dry weight in hemodialysis patients. However, BIS is often misrepresented in clinical healthy weight. In this study, we tried to predict the clinically proper dry weight (DW(CP)) using machine learning for patient’s clinical information including BIS. We then analyze the factors that influence the prediction of the clinical dry weight. METHODS: As a retrospective, single center study, data of 1672 hemodialysis patients were reviewed. DW(CP) data were collected when the dry weight was measured using the BIS (DW(BIS)). The gap between the two (Gap(DW)) was calculated and then grouped and analyzed based on gaps of 1 kg and 2 kg. RESULTS: Based on the gap between DW(BIS) and DW(CP), 972, 303, and 384 patients were placed in groups with gaps of <1 kg, ≧1kg and <2 kg, and ≧2 kg, respectively. For less than 1 kg and 2 kg of GapDW, It can be seen that the average accuracies for the two groups are 83% and 72%, respectively, in usign XGBoost machine learning. As Gap(DW) increases, it is more difficult to predict the target property. As Gap(DW) increase, the mean values of hemoglobin, total protein, serum albumin, creatinine, phosphorus, potassium, and the fat tissue index tended to decrease. However, the height, total body water, extracellular water (ECW), and ECW to intracellular water ratio tended to increase. CONCLUSIONS: Machine learning made it slightly easier to predict DW(CP) based on DW(BIS) under limited conditions and gave better insights into predicting DW(CP). Malnutrition-related factors and ECW were important in reflecting the differences between DW(BIS) and DW(CP).