The Driver-Blindness Phenomenon: Why Deep Sequence Models Default to Autocorrelation in Blood Glucose Forecasting

TL;DR

Deep sequence models for blood glucose prediction often ignore important clinical drivers due to architectural biases, data issues, and physiological variability, leading to minimal performance gains from multivariate data.

Contribution

This paper formalizes the Driver-Blindness phenomenon, identifies its causes, and proposes strategies to mitigate it in blood glucose forecasting models.

Findings

Multivariate models show negligible performance gain over univariate baselines.

Architectural biases favor autocorrelation, hindering driver utilization.

Strategies like physiological encoders and personalization can reduce Driver-Blindness.

Abstract

Deep sequence models for blood glucose forecasting consistently fail to leverage clinically informative drivers--insulin, meals, and activity--despite well-understood physiological mechanisms. We term this Driver-Blindness and formalize it via $\Delta_{\text{drivers}}$, the performance gain of multivariate models over matched univariate baselines. Across the literature, $\Delta_{\text{drivers}}$ is typically near zero. We attribute this to three interacting factors: architectural biases favoring autocorrelation (C1), data fidelity gaps that render drivers noisy and confounded (C2), and physiological heterogeneity that undermines population-level models (C3). We synthesize strategies that partially mitigate Driver-Blindness--including physiological feature encoders, causal regularization, and personalization--and recommend that future work routinely report $\Delta_{\text{drivers}}$ to prevent driver-blind models from being considered state-of-the-art.