arXiv：cs.LG· Adinath Madhavrao Dukre, Abdullah Mohammad, Yifan Lu, Eran Segal, Ahmed Metwally, Imran Razzak·· 11 小时前
GlucoPRISM：面向跨队列血糖迁移的协议监督预训练
GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer
AI 导读
GlucoPRISM 用响应契约监督 GlucoFM 骨干，将表征拆成 64 维 Trait、48 维 State 和 16 维 Sensor 三个频带，部署时以固定投影剔除 Sensor 频带且无需目标数据。
正文
Abstract:Continuous glucose monitoring (CGM) foundation models encode each day as one vector that mixes who the person is, what happened that day and how the sensor measured it, so measurement differences travel with the representation into new cohorts. We ask whether pretraining can place the measurement component that harms transfer in known coordinates, so that deployment drops them with a fixed projection and no target data. GlucoPRISM supervises a GlucoFM backbone with response contracts, rules for how each part of the representation should change when only the day or only the sensor changes: a 64-dimensional Trait band should change with neither, a 48-dimensional State band only across days, and a 16-dimensional Sensor band should track the device. Synthetic sensor views calibrated on paired Dexcom and Libre recordings, different-day pairs and glucose-summary targets supply this supervision without clinical labels. Across twelve cross-cohort directions, dropping the Sensor band from the same frozen encoder raises mean transfer AUROC from 68.75 to 73.57, against 69.3 for GlucoFM. The gain has two parts. Into CGMacros, the one target cohort recorded with two sensor types, filtering adds 11 to 19 points, and this holds when the generator is recalibrated on half of the participants and scored on the other half. On the other eight directions filtering is neutral and the encoder itself exceeds GlucoFM by 3.5 points. The device remains linearly decodable after filtering, so the filter removes a device-related component that harms transfer rather than all measurement information. The retained bands improve window AUROC on thirteen of fourteen public task--cohort cells (Holm-adjusted p=0.031) and correlation on fourteen of fifteen clinical endpoints in an external cohort of 9,303 participants.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.12528 [cs.LG] |
| (or arXiv:2610.12528v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12528 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Imran Razzak [view email]
[v1]
Thu, 8 Oct 2026 09:14:26 UTC (2,902 KB)
来源：arXiv：cs.LG · arxiv.org