Managing Exercise-Related Glycemic Events in Type 1 Diabetes: Development and Validation of Predictive Models for a Practical Decision Support Tool
Bibliographic record
Abstract
Background: Exercise is an important aspect of diabetes self-management. Patients with type 1 diabetes frequently struggle with exercise-induced hyperglycemia and hypoglycemia, decreasing their willingness to exercise. Objective: We aim to build accurate and easy-to-deploy models to forecast exercise-induced glycemic events in real-world settings. Methods: We analyzed free-living data from the Type 1 Diabetes Exercise Initiative study, where adults with type 1 diabetes wore a continuous glucose monitor (CGM) while performing video-guided exercises (30-minute exercises at least 6 times over 4 weeks), along with concurrent detailed phenotyping of their insulin program and diet. We built models to predict glycemic events (blood glucose ≤54 mg/dL, ≤70 mg/dL, ≥200 mg/dL, and ≥250 mg/dL) during and 1 hour post exercise with variables from 4 data modalities, such as demographic and clinical (eg, glycated hemoglobin; CGM (blood glucose value and their summary statistics); carbohydrate intake and insulin administration; and exercise type, duration, and intensity. We used repeated stratified nested cross-validation for model selection and performance estimation. We evaluated the relative contribution of the 4 input data modalities for predicting glycemic events, which informs the cost and benefit for including them in the decision support tool for risk prediction. We also evaluated other important aspects related to model translation into decision support tools, including model calibration and sensitivity to noisy inputs. Results: Our models were built based on 1901 exercise episodes for 329 participants. The median age for the participants was 34 (IQR 26-48) years. Of the participants, 74.8% (246/329) are female and 94.5% (311/329) are White. A total of 182/329 (55.3%) participants used a closed-loop insulin delivery system, while the rest used a pump without a closed-loop system. Models incorporating information from all 4 data modalities showed excellent predictive performance with cross-validated area under the receiver operating curves (AUROCs) ranging from mean 0.880 (SD 0.057) to mean 0.992 (SD 0.001) for different glycemic events. Models built with CGM data alone have statistically indistinguishable performance compared to models using all data modalities, indicating the other 3 data modalities do not add additional information with respect to predicting exercise-related glycemic events. The models based solely on CGM data also showed outstanding calibration (Brier score ≤0.08) and resilience to noisy input. Conclusions: We successfully constructed models to forecast exercise-induced glycemic events using only CGM data as input with excellent predictive performance, calibration, and robustness. In addition, these models are based on automatically captured CGM data, thus easy to deploy and maintain and incurring minimal user burden, enabling model translation into a decision support tool.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".