Self-supervised Pretraining and Transfer Learning Enable Flu and COVID-19 Predictions in Small Mobile Sensing Datasets
This addresses the problem of limited predictive accuracy in behavioral health applications for medical surveillance, though it appears incremental in adapting existing deep learning techniques to this specific domain.
The paper tackles the challenge of predicting flu and COVID-19 from small mobile sensing datasets with issues like missing data and class imbalances, achieving performance improvements of up to 0.15 ROC AUC over baselines and 16% PR AUC gains through transfer learning in small data scenarios.
Detailed mobile sensing data from phones, watches, and fitness trackers offer an unparalleled opportunity to quantify and act upon previously unmeasurable behavioral changes in order to improve individual health and accelerate responses to emerging diseases. Unlike in natural language processing and computer vision, deep representation learning has yet to broadly impact this domain, in which the vast majority of research and clinical applications still rely on manually defined features and boosted tree models or even forgo predictive modeling altogether due to insufficient accuracy. This is due to unique challenges in the behavioral health domain, including very small datasets (~10^1 participants), which frequently contain missing data, consist of long time series with critical long-range dependencies (length>10^4), and extreme class imbalances (>10^3:1). Here, we introduce a neural architecture for multivariate time series classification designed to address these unique domain challenges. Our proposed behavioral representation learning approach combines novel tasks for self-supervised pretraining and transfer learning to address data scarcity, and captures long-range dependencies across long-history time series through transformer self-attention following convolutional neural network-based dimensionality reduction. We propose an evaluation framework aimed at reflecting expected real-world performance in plausible deployment scenarios. Concretely, we demonstrate (1) performance improvements over baselines of up to 0.15 ROC AUC across five prediction tasks, (2) transfer learning-induced performance improvements of 16% PR AUC in small data scenarios, and (3) the potential of transfer learning in novel disease scenarios through an exploratory case study of zero-shot COVID-19 prediction in an independent data set. Finally, we discuss potential implications for medical surveillance testing.