A data-driven system for insulin pump dosing in type 2 diabetes: development, prospective evaluation and clinical applicability
- 1The First Affiliated Hospital of Sun Yat-sen University
Abstract
Open-loop insulin pump therapy depends on clinical expertise for dose initiation and titration. We developed a long short-term memory-based system, using 1738 treatment courses from 1641 patients with type 2 diabetes for initial prescribing and daily basal and bolus titration. Patient-grouped five-fold validation showed closer agreement with recorded prescriptions for subsequent titration than for initiation. Prospective evaluation in 97 patients from the model-directed arm of a randomized trial yielded a median derived time in range (3.9-10.0mmol/L) of 84.5%, with low hypoglycemic exposure. Favorable control extended to previously treated patients. Higher mean glucose during the first 24 hours was associated with poorer glycemic control thereafter. The association between distance from development data and glycemic outcomes was stronger when early glucose responses were included alongside baseline characteristics. These findings support model-directed pump dosing and highlight early treatment response as a clinically relevant signal for assessing applicability and identifying patients who may require additional oversight. Trial registration: ClinicalTrials.gov, NCT07066891.
Related
- Decision-Supported Collaborative Care for Gestational Diabetes: A Narrative Review of Development Pathways and Evaluation in Routine Clinical Practice.
- Image-Based Dietary Assessment Using Multimodal Large Language Models: Performance, Limitations, and Clinical Applicability in Diabetes
- Reduced serum Dickkopf-1 levels as a potential supportive biomarker for the development and severity of retinopathy of prematurity: a prospective observational clinical study
- inClinico Agent for clinical trial endpoint prediction and prospective evaluation
- Pulmonary Vein Isolation with Different Single-Shot Ablation Devices in Patients with Atrial Fibrillation: A Prospective Observational Single-Center Clinical Evaluation
BibTeX
@misc{cai2026datadriven,
title = {{A data-driven system for insulin pump dosing in type 2 diabetes: development, prospective evaluation and clinical applicability}},
author = {L. Cai and S. Huang and Y. Cao and Z. Huang},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.13.26365400},
url = {https://www.medrxiv.org/content/10.64898/2026.10.13.26365400v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - A data-driven system for insulin pump dosing in type 2 diabetes: development, prospective evaluation and clinical applicability
AU - L. Cai
AU - S. Huang
AU - Y. Cao
AU - Z. Huang
PY - 2026
DA - 2026/10/13
PB - medRxiv
DO - 10.64898/2026.10.13.26365400
UR - https://www.medrxiv.org/content/10.64898/2026.10.13.26365400v1
AB - Open-loop insulin pump therapy depends on clinical expertise for dose initiation and titration. We developed a long short-term memory-based system, using 1738 treatment courses from 1641 patients with type 2 diabetes for initial prescribing and daily basal and bolus titration. Patient-grouped five-fold validation showed closer agreement with recorded prescriptions for subsequent titration than for initiation. Prospective evaluation in 97 patients from the model-directed arm of a randomized trial yielded a median derived time in range (3.9-10.0mmol/L) of 84.5%, with low hypoglycemic exposure. Favorable control extended to previously treated patients. Higher mean glucose during the first 24 hours was associated with poorer glycemic control thereafter. The association between distance from development data and glycemic outcomes was stronger when early glucose responses were included alongside baseline characteristics. These findings support model-directed pump dosing and highlight early treatment response as a clinically relevant signal for assessing applicability and identifying patients who may require additional oversight. Trial registration: ClinicalTrials.gov, NCT07066891.
ER -