What type of study is this?

This is a Meta-Analysis study (also classified as: Systematic Review).

January 14, 2026Diabetology0 citationsOpen Access

Artificial Intelligence Algorithms for Insulin Management and Hypoglycemia Prevention in Hospitalized Patients—A Scoping Review

EFEileen R. FauldsThe Ohio State University Wexner Medical Center MRMelanie Natasha RayanThe Ohio State University Wexner Medical Center MMMatthew K MlachakThe Ohio State University

Key Points

To characterize AI algorithms for insulin dosing and glycemic management in hospitalized patients.
Conducted a scoping review following PRISMA-ScR guidelines.
An interdisciplinary team defined AI concepts, including machine learning and deep learning.
Searched five databases for relevant citations and screened based on inclusion criteria.
Identified 26 studies focusing on ICU and general ward patients.
Model predictive control showed mean glucose improvement to 5.7–6.2 mmol/L.
Machine learning models achieved AUROC of 0.80–0.96 for hypoglycemia risk prediction.

Abstract

Background: Dysglycemia remains a persistent challenge in hospital care. Despite advances in outpatient diabetes technology, inpatient insulin management largely depends on intermittent point-of-care glucose testing, static insulin dosing protocols and rule-based decision support systems. Artificial intelligence (AI) offers potential to transform this care through predictive modeling and adaptive insulin control. Methods: Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines, a scoping review was conducted to characterize AI algorithms for insulin dosing and glycemic management in hospitalized patients. An interdisciplinary team of clinicians and engineers reached consensus on AI definitions to ensure inclusion of machine learning, deep learning, and reinforcement learning approaches. A librarian-assisted search of five databases identified 13,768 citations. After screening and consensus review, 26 studies (2006–2025) met the inclusion criteria. Data were extracted on study design, population, AI methods, data inputs, outcomes, and implementation findings. Results: Studies included ICU (N = 13) and general ward (N = 9) patients, including patients with diabetes and stress hyperglycemia. Early randomized trials of model predictive control demonstrated improved mean glucose (5.7–6.2 mmol/L) and time in target range compared with standard care. Later machine learning models achieved strong predictive accuracy (AUROC 0.80–0.96) for glucose forecasting or hypoglycemia risk. Most algorithms used data from Medical Information Mart for Intensive Care (MIMIC) databases; few incorporated continuous glucose monitoring (CGM). Implementation and usability outcomes were seldom reported. Conclusions: Hospital AI-driven models showed strong algorithmic performance but limited clinical validation. Future co-designed, interpretable systems integrating CGM and real-time workflow testing are essential to advance safe, adaptive insulin management in hospital settings.

问 AI

Bookmark

View Full Paper