79-OR: A Novel Decision Support System for Automated Adaptations of Insulin Injections in Type 1 Diabetes—A Randomized Controlled Trial
Bibliographic record
Abstract
Introduction & Objective: Recent advancements in glucose sensing and smart insulin pens have spurred the development of decision support systems (DSSs) to optimize insulin dosing for people with T1D on multiple daily injections (MDI). We developed the iBolus DSS, composed of a mobile app and a model-based dose titration algorithm that provides adaptive basal and bolus recommendations. We aimed to assess the effectiveness of our iBolus DSS in adults with suboptimal glucose control. Methods: We conducted a 12-week outpatient, randomized, controlled, parallel trial in adults with T1D on insulin monotherapy and baseline HbA1c of ≥ 7.5%. Participants were randomized in a 1:1 ratio and stratified according to previous sensor usage to either use the iBolus DSS or a non-adaptive bolus calculator app (control). The iBolus DSS automatically adjusted participants’ basal and bolus doses weekly, while the control group adhered to standard care practices for dose adjustments. During the interventions, participants used flash glucose monitoring (FGM) with Freestyle Libre 1. The pre-defined primary endpoint was the change in HbA1c from baseline. Results: The study enrolled 84 participants (44% females; HbA1c 8.6±1.1%; age 38±12 years; diabetes duration 22±12 years; 61% used carbohydrate counting). The iBolus DSS reduced mean HbA1c from 8.6% to 8.1% while the control intervention reduced HbA1c from 8.6% to 8.5%; a treatment effect in favor of the DSS of -0.40% (95% CI: -0.75 to -0.051; p=0.025). The proportion of participants with improvements in HbA1c of > 0.5%, >1.0%, > 1.5%, and > 2.0% were almost doubled in the DSS arm compared to the control arm (52%, 19%, 12%, and 5% vs. 31%, 10%, 5%, and 0%, respectively). Differences in FGM outcomes were not statistically significant. There were no cases of severe hypoglycemia or diabetic ketoacidosis in either group. Conclusion: Our iBolus DSS significantly improves HbA1c in adults with suboptimal glucose control on MDI therapy. Disclosure A. Kobayati: None. A. El Fathi: None. N. Garfield: None. L. Legault: Advisory Panel; Abbott, Novo Nordisk. Speaker's Bureau; Novo Nordisk. Advisory Panel; Dexcom, Inc. J. Yale: Speaker's Bureau; Novo Nordisk Canada Inc., Abbott, Eli Lilly and Company. Advisory Panel; Novo Nordisk Canada Inc., Bayer Inc. Speaker's Bureau; Insulet Corporation. Advisory Panel; Eli Lilly and Company. Speaker's Bureau; Dexcom, Inc., Sanofi, Janssen Pharmaceuticals, Inc. Advisory Panel; Boehringer-Ingelheim, Mylan. Speaker's Bureau; Bayer Inc. Advisory Panel; Sanofi. Speaker's Bureau; Merck & Co., Inc. Research Support; Bayer Inc., Novartis Canada, Novo Nordisk Canada Inc. M. Tsoukas: Speaker's Bureau; Novo Nordisk, Eli Lilly and Company, Boehringer-Ingelheim, Janssen Pharmaceuticals, Inc., AstraZeneca, Sanofi, Bausch Health, Abbott. A. Haidar: Consultant; Eli Lilly and Company. Other Relationship; Bigfoot Biomedical, Inc. Research Support; ADOCIA, Tandem Diabetes Care, Inc., Dexcom, Inc., Ypsomed AG. Funding CIHR
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.013 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".