Nicolas Vandenbussche

arXiv2024

Addressing Data Quality Challenges in Observational Ambulatory Studies: Analysis, Methodologies and Practical Solutions for Wrist-worn Wearable Monitoring

Chronic disease management and follow-up are vital for realizing sustained patient well-being and optimal health outcomes. Recent advancements in wearable sensing technologies, particularly wrist-worn devices, offer promising solutions for longitudinal patient follow-up by shifting from subjective, intermittent self-reporting to objective, continuous monitoring. However, collecting and analyzing wearable data presents unique challenges, such as data entry errors, non-wear periods, missing wearable data, and wearable artifacts. We therefore present an in-depth exploration of data analysis challenges tied to wrist-worn wearables and ambulatory label acquisition, using two real-world datasets (i.e., mBrain21 and ETRI lifelog2020). We introduce novel practical countermeasures, including participant compliance visualizations, interaction-triggered questionnaires to assess personal bias, and an optimized wearable non-wear detection pipeline. Further, we propose a visual analytics approach to validate processing pipelines using scalable tools such as tsflex and Plotly-Resampler. Lastly, we investigate the impact of missing wearable data on "window-of-interest" analysis methodologies. Prioritizing transparency and reproducibility, we offer open access to our detailed code examples, facilitating adaptation in future wearable research. In conclusion, our contributions provide actionable approaches for wearable data collection and analysis in chronic disease management.

cs.CE↗

arXiv2022

Do Not Sleep on Traditional Machine Learning: Simple and Interpretable Techniques Are Competitive to Deep Learning for Sleep Scoring

Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improvements, often at the expense of requiring more data and more expensive training procedures. Despite all these efforts and their satisfactory performance, automatic sleep staging solutions are not widely adopted in a clinical context yet. We argue that most deep learning solutions for sleep scoring are limited in their real-world applicability as they are hard to train, deploy, and reproduce. Moreover, these solutions lack interpretability and transparency, which are often key to increase adoption rates. In this work, we revisit the problem of sleep stage classification using classical machine learning. Results show that competitive performance can be achieved with a conventional machine learning pipeline consisting of preprocessing, feature extraction, and a simple machine learning model. In particular, we analyze the performance of a linear model and a non-linear (gradient boosting) model. Our approach surpasses state-of-the-art (that uses the same data) on two public datasets: Sleep-EDF SC-20 (MF1 0.810) and Sleep-EDF ST (MF1 0.795), while achieving competitive results on Sleep-EDF SC-78 (MF1 0.775) and MASS SS3 (MF1 0.817). We show that, for the sleep stage scoring task, the expressiveness of an engineered feature vector is on par with the internally learned representations of deep learning models. This observation opens the door to clinical adoption, as a representative feature vector allows to leverage both the interpretability and successful track record of traditional machine learning models.

stat.ML↗