Metraipolis › archive › dc_fc632463590b

FairGlucose: A CGM Fairness Benchmark Reveals Subgroup Disparities Hidden in Population-Level Validation — arXiv:2608.18296

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18296
License (as archived)
CC0-1.0
Archived
2026-10-18T13:45:00.265Z
SHA-256 of the archived text
e6d8cbe43ededeafdcc9065fd5db69530cdab2e3085f02fe477faf77c41d3595
Stable URL of this page
https://metraipolis.com/documento/dc_fc632463590b

How to cite

FairGlucose: A CGM Fairness Benchmark Reveals Subgroup Disparities Hidden in Population-Level Validation — arXiv:2608.18296 — arXiv (en), https://arxiv.org/abs/2608.18296 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc632463590b (Metraipolis archive dc_fc632463590b, sha256 e6d8cbe43ededeafdcc9065fd5db69530cdab2e3085f02fe477faf77c41d3595)
BibTeX
@misc{dcfc632463590b,
  title = {FairGlucose: A CGM Fairness Benchmark Reveals Subgroup Disparities Hidden in Population-Level Validation — arXiv:2608.18296},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18296},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc632463590b; sha256 e6d8cbe43ededeafdcc9065fd5db69530cdab2e3085f02fe477faf77c41d3595},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18296. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As CGM-based AI tools approach clinical deployment, whether their accuracy is equitable across patient demographics remains insufficiently tested. To enable this evaluation, we constructed FairGlucose, a 300-patient CGM cohort balanced across 12 demographic strata (age x gender x type 1/type 2 diabetes), with 132,480 forecasting samples and 3,945 unique behavioral events (meals, exercise, medication) logged by 81 patients. Benchmarking 33 models across four families on 2-hour glucose forecasting, we find that population-level external validation can conceal substantial subgroup disparities. Aggregate out-of-distribution metrics appear stable (approximately 1.0), yet subgroup-level ratios range from 0.8 to 1.4, with T1D patients showing 6 mg/dL higher prediction error than T2D (p < 0.001). This disparity persists across all 33 models, suggesting a property of the prediction task rather than any single architecture. Further analysis shows that subgroup performance gaps align with the proportion of clinically hard cases, and that input-length sensitivity varies across demographics, motivating personalized configurations. Frontier LLMs underperform specialized neural models by 1-6 mg/dL; behavioral events contribute negligibly (approximately 0.1 mg/dL) even under oracle event access. These findings establish that population-level validation alone is insufficient for equity assessment of digital health AI, motivating subgroup-disaggregated reporting as a default standard.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.18296 — 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 2026-10-18T13:41:17.927Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).