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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Shakeri, Heman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917104031105024
author Shakeri, Heman
author_facet Shakeri, Heman
contents 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 $Δ_{\text{drivers}}$, the performance gain of multivariate models over matched univariate baselines. Across the literature, $Δ_{\text{drivers}}$ 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 $Δ_{\text{drivers}}$ to prevent driver-blind models from being considered state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20601
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Driver-Blindness Phenomenon: Why Deep Sequence Models Default to Autocorrelation in Blood Glucose Forecasting
Shakeri, Heman
Machine Learning
Artificial Intelligence
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 $Δ_{\text{drivers}}$, the performance gain of multivariate models over matched univariate baselines. Across the literature, $Δ_{\text{drivers}}$ 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 $Δ_{\text{drivers}}$ to prevent driver-blind models from being considered state-of-the-art.
title The Driver-Blindness Phenomenon: Why Deep Sequence Models Default to Autocorrelation in Blood Glucose Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.20601