Our Team

Background: Ultrafiltration (UF) during hemodialysis is typically prescribed as a fixed treatment goal and delivered using a largely constant ultrafiltration rate throughout the session. We evaluated whether Adaptive Ultrafiltration (Adaptive UF), a physiological closed-loop control strategy guided by continuous relative blood volume (RBV) monitoring, could improve RBV target attainment while individualizing fluid removal within predefined treatment constraints. Methods: We performed a paired patient-specific in silico study using 119,472 historical hemodialysis treatments from 11,246 U.S. patients. Treatment-specific plasma refill rate profiles were derived from recorded RBV and ultrafiltration data. For each historical treatment, a corresponding Adaptive UF treatment was simulated and compared with the corresponding originally delivered treatment. Outcomes included the percentage of time within a predefined favorable RBV target region, UF delivery, and operational performance. Results: Mean time within the RBV target region increased from 36.3% with historically delivered treatments to 56.4% with Adaptive UF, showing an absolute improvement of 20.2 percentage points (95% CI, 19.9-20.5); target attainment improved in 90.0% of patients. Mean area outside the target range decreased from 280.7 to 139.5 RBV %-minutes. Mean achieved UF volume increased by 296.4 mL, although treatment-level UF delivery was bidirectional, increasing in 83.1% and decreasing in 16.9% of treatments. UF rates remained below 13 mL/kg/h in all simulations, and 99.4% of treatments remained within predefined UF volume limits. Conclusions: Adaptive UF improved intradialytic RBV target attainment and individualized UF delivery within predefined treatment constraints. Prospective studies are required to determine whether these physiological improvements translate into clinical benefit.

RESULTSModels including BIS data showed excellent accuracy (R2 > 0.85), models excluding BIS features achieved inferior performance (R2 = 0.73-0.81). In models using BIS inputs, recent bioimpedance changes dominated feature importance. Models without BIS data relied primarily on urea distribution volume, age, and height.CONCLUSIONThese findings indicate that fluid volume compartments can be reliably estimated from routinely collected clinical data and history BIS measurements, offering valuable support for interim assessment of fluid status between scheduled BIS measurements.METHODUsing adult patients from the MONitoring Dialysis Outcomes (MONDO) 2012 cohort, we developed predictive models to estimate fluid volume compartments based on demographic data, laboratory values, treatment parameters, and multi-frequency whole-body bioimpedance spectroscopy (BIS) measurements. Clinical features were aggregated over an up-to-90-day look-back window, yielding 18,600 patients and 162,479 dialysis treatments. eXtreme Gradient Boosting (XGBoost) models were trained and tested using patient-level splits, with parallel models built either incorporating or excluding prior BIS measurements.BACKGROUNDOptimized fluid management is crucial in dialysis care because extracellular volume overload drives adverse cardiovascular outcomes. At the same time, comorbidities such as inflammation and protein energy wasting lead to decreased muscle mass and intracellular water. Accurate assessment of total body water (TBW) and its extracellular water (ECW) and intracellular water (ICW) compartments is therefore essential to guide ultrafiltration, evaluate dialysis adequacy, and monitor patient risk.