Actively Recruiting
Efficacy and Safety of the Artificial Intelligence-assisted Insulin Dose Adjustment System for Glycaemic Control in Patients With Type 2 Diabetes Mellitus in General Wards: a Multicentre, Single-blind, Randomised Controlled Study
Led by Shanghai Zhongshan Hospital · Updated on 2025-08-06
140
Participants Needed
1
Research Sites
8 weeks
Total Duration
On this page
Sponsors
S
Shanghai Zhongshan Hospital
Lead Sponsor
S
Shanghai Fifth People's Hospital
Collaborating Sponsor
AI-Summary
What this Trial Is About
Researchers are evaluating an artificial intelligence-assisted insulin dose adjustment system for patients with type 2 diabetes admitted to general hospital wards. This study is a single-blind, randomized, controlled, multicenter trial comparing this AI system to traditional insulin dose adjustments made by doctors. Its purpose is to assess the safety and effectiveness of the AI system in managing blood glucose levels in hospitalized patients. Participants are randomly assigned into two groups: one using the AI-assisted system to adjust subcutaneous insulin doses, and the other receiving insulin dose adjustments from physicians. The study plans to include 140 patients, divided equally between the two groups. The intervention lasts for at least 5 days during hospitalization, focusing on controlling blood glucose through insulin therapy. During the study, participants' blood glucose levels are closely monitored through sensor glucose and capillary blood sugar measurements over 3 or more days. Researchers will observe time spent within target glucose range and record hypoglycemic and hyperglycemic events, insulin doses administered, and doctor satisfaction. Hospitalization length and any adverse events will also be tracked. The total study duration per participant depends on their hospital stay, which must be at least 5 days.
CONDITIONS
Brief Title
Artificial Intelligence-assisted Insulin System in Type 2 Diabetes in General Wards
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Diagnosis of type 2 diabetes mellitus for more than 3 months
- Age 18 years or older
- Receiving glucose-lowering therapy for at least 90 days
- Blood glucose levels between 7.8 and 22.2 mmol/L
- Planned hospital stay of 5 days or longer
You will not qualify if you...
- Type 1 diabetes mellitus or other special types of diabetes mellitus
- Blood glucose above 22.2 mmol/L or acute diabetes complications such as ketoacidosis or hyperosmolar state
- History of severe or repeated low blood sugar episodes
- Body mass index of 45 kg/m2 or higher
- Pregnant or breastfeeding women
- Significant liver disease such as cirrhosis or portal hypertension
- Severe kidney disease with serum creatinine 3.0 mg/dL or higher or low kidney filtration rate
- Severe heart failure
- Use of cortisol-based hormone therapy above prednisone 5 mg/day
- Psychiatric disorders or impaired cognitive function
- Severe swelling, infections, or blood circulation problems
- Severe illness or planned transfer to intensive care
- Planned heart or abdominal surgery that could affect the study during hospitalization
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Your Study Journey
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - 5 days or longer
Participants are randomly assigned to receive insulin dose adjustments either via an artificial intelligence-assisted system or by doctors to control their blood glucose during their hospital stay.
Daily visits during hospital stay
Trial Site Locations
Total: 1 location
1
Zhongshan Hospital, Fudan University
Shanghai, Shanghai Municipality, China, 200032
Actively Recruiting
How is the study designed?
Study Type
INTERVENTIONAL
Masking
SINGLE
Allocation
RANDOMIZED
Model
PARALLEL
Primary Purpose
TREATMENT
Number of Arms
2
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here