Related Experiment Video
Updated: Mar 11, 2026

Improving Strength, Power, Muscle Aerobic Capacity, and Glucose Tolerance through Short-term Progressive Strength Training Among Elderly People
Published on: July 5, 2017
Identifying Predictors of Early Treatment Intensification in Individuals With Type 2 Diabetes Treated With GLP-1
Pierpaolo Falcetta1, Rita Zilich2, Fabio Baccetti3
1Diabetes Unit, Azienda USL Toscana Centro, Empoli, Italy.
Aims:
Despite the proven efficacy of GLP-1 receptor agonists (GLP-1 RAs), many patients with type 2 diabetes (T2DM) are not able to achieve glycaemic targets with these agents and they require additional therapies. Timely identification of individuals at higher risk of early intensification may improve outcomes and reduce therapeutic inertia.
Materials And Methods:
In this retrospective cohort study, we analysed data from 69 194 individuals with T2DM initiating GLP-1 RA. We applied logic learning machine (LLM), an explainable machine-learning algorithm, to identify-at the time of GLP-1 RA prescription-predictors of early intensification (≤ 12 months from GLP-1 RA initiation). For this purpose, we developed two distinct models: Model 1, which compared characteristics of individuals intensified early (≤ 12 months) versus those not intensified in the first year, and Model 2, comparing individuals intensified early vs. those never intensified (> 5 years of GLP-1 RA treatment).
Results:
Both models identified the same clinical phenotype, characterised by longer diabetes duration, unstable glycaemic control, prior insulin use, and cardio-renal complications. Model 1 showed limited discriminative ability (AUC 0.65) with many false positives, suggesting therapeutic inertia in real-world practice. Model 2, while selecting same predictors of Model 1, achieved better performance (AUC 0.78), suggesting clearer differentiation between patient cohorts.
Conclusions:
Explainable AI identified a reproducible phenotype of patients associated with early intensification after GLP-1 RA initiation. These models may support earlier, more personalised treatment decisions in routine diabetes care.
Insights
Identifying patients needing earlier type 2 diabetes treatment intensification is key. Explainable AI identified a patient profile linked to early intensification after starting GLP-1 receptor agonists, aiding personalized care.
Area of Science:
- Endocrinology
- Artificial Intelligence in Healthcare
- Pharmacotherapy
Background:
- Glucagon-like peptide-1 receptor agonists (GLP-1 RAs) are effective for type 2 diabetes (T2DM), but many patients require additional therapies to reach glycaemic targets.
- Early identification of patients at risk for treatment intensification can help overcome therapeutic inertia and improve outcomes.
Purpose of the Study:
- To identify predictors of early treatment intensification in patients with T2DM initiating GLP-1 RAs using explainable machine learning.
- To develop models that can support personalized treatment decisions in T2DM management.
Main Methods:
- Retrospective cohort study of 69,194 individuals with T2DM initiating GLP-1 RA.
- Application of logic learning machine (LLM), an explainable AI algorithm, to identify predictors of early intensification (≤12 months).
- Two models were developed: early intensification vs. no intensification in year 1 (Model 1), and early intensification vs. never intensified (Model 2).
Main Results:
- Both models identified a consistent clinical phenotype associated with early intensification: longer diabetes duration, unstable glycaemic control, prior insulin use, and cardio-renal complications.
- Model 1 demonstrated limited discriminative ability (AUC 0.65), indicating real-world therapeutic inertia.
- Model 2 showed improved performance (AUC 0.78), offering clearer differentiation between patient cohorts.
Conclusions:
- Explainable AI successfully identified a reproducible patient phenotype associated with early intensification after GLP-1 RA initiation.
- These AI-driven models have the potential to facilitate earlier and more personalized treatment decisions in routine diabetes care.
Related Concept Videos
Glucagon-like Receptor Agonists
GLP-1, when administered in high doses intravenously, triggers insulin secretion, inhibits glucagon release, slows gastric emptying, reduces food intake, and restores normal insulin secretion. However, its rapid inactivation by...
Oral Hypoglycemic Agents: Biguanides and Glitazones
Dipeptidyl Peptidase 4 Inhibitors
Oral Hypoglycemic Agents: Glinides
Diabetes Mellitus: Type 2 and Gestational
Insulin: Dosing Regimen and Adverse Effects
The basal dose constitutes about 40%-50% of the total daily dose, with the rest as premeal insulin. The mealtime insulin dose should mirror...

