Denoising Autoencoders for Learning from Noisy Patient-Reported Data
Harry Rubin-Falcone* (University of Michigan), Joyce Lee (University of Michigan), Jenna Wiens (University of Michigan)
Abstract: Healthcare datasets often include patient-reported values, such as mood, symptoms, and meals, which can be subject to varying levels of human error. Improving the accuracy of patient-reported data could help in several downstream tasks, such as remote patient monitoring. In this study, we propose a novel denoising autoencoder (DAE) approach to denoise patient-reported data, drawing inspiration from recent work in computer vision. Our approach is based on the observation that noisy patient-reported data are often collected alongside higher fidelity data collected from wearable sensors. We leverage these auxiliary data to improve the accuracy of the patient-reported data. Our approach combines key ideas from DAEs with co-teaching to iteratively filter and learn from clean patient-reported samples. Applied to the task of recovering carbohydrate values for blood glucose management in diabetes, our approach reduces noise (MSE) in patient-reported carbohydrates from 72g2 (95% CI: 54-93) to 18g2 (13-25), outperforming the best baseline (33g2 (27-43)). Notably, our approach achieves strong performance with only access to patient-reported target values, making it applicable to many settings where ground truth data may be unavailable.