Metraipolis › archive › dc_906aa2a5307d

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting — arXiv:2609.11872

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11872
License (as archived)
CC0-1.0
Archived
2026-10-16T05:55:26.999Z
SHA-256 of the archived text
6b84c7298c92fa05952a316320a571f3d216f9082b1431abb2276f341c5d78c0
Stable URL of this page
https://metraipolis.com/documento/dc_906aa2a5307d

How to cite

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting — arXiv:2609.11872 — arXiv (en), https://arxiv.org/abs/2609.11872 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_906aa2a5307d (Metraipolis archive dc_906aa2a5307d, sha256 6b84c7298c92fa05952a316320a571f3d216f9082b1431abb2276f341c5d78c0)
BibTeX
@misc{dc906aa2a5307d,
  title = {Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting — arXiv:2609.11872},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11872},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_906aa2a5307d; sha256 6b84c7298c92fa05952a316320a571f3d216f9082b1431abb2276f341c5d78c0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11872. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We conduct a comprehensive empirical study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol across multiple context lengths and prediction horizons, zero-shot foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST. In contrast, lightweight fine-tuning substantially improved forecasting performance. For example, fine-tuned Chronos-Bolt reduced RMSE by 6.5%-18.4% in the T1D cohort and by 8.6%-18.2% in the non-diabetes/T2D cohort, with comparable improvements in both in-distribution and out-of-distribution test settings. We further evaluate multimodal dietary context using CGMacros, which provides temporally aligned CGM signals, food images, and macronutrient records. A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline. Moreover, Chronos-based CGM representations were more strongly correlated with observed postprandial glucose increments than representations from LSTM and CatBoost, even after those models incorporated additional dietary modalities, suggesting that pretrained temporal representations better preserve meal-induced excursion patterns. These findings show that foundation models require CGM-specific adaptation for reliable forecasting and that dietary context provides clinically meaningful signals beyond CGM alone, especially during postprandial periods.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.11872 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:44:25.109Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).