Forecasting Treatment Response with Deep Pharmacokinetic Encoders.

Abstract

Forecasting healthcare time series data is vital for early detection of adverse outcomes and patient monitoring. However, forecasting is challenging in practice due to variable medication administration and unique pharmacokinetic (PK) properties for each patient. To address these challenges, we propose a novel hybrid global-local architecture and a PK encoder that informs deep learning models of patient-specific treatment effects. We showcase the efficacy of our approach in achieving significant accuracy gains for a blood glucose forecasting task using both realistically simulated and real-world data. Our hybrid global-local architecture improves over patient-specific models by 15.8% on average. Additionally, our PK encoder surpasses baselines by up to 16.4% on simulated data and 4.9% on real-world data for individual patients during critical events of severely high and low glucose levels.