Artificial Intelligence Assisted Insulin Titration System

Phase 4

Completed

• Conditions: Type 2 Diabetes
• Interventions: Drug: AI assisted insulin system; Drug: Physician based insulin regime

• Registration Number: NCT04053959
• Lead Sponsor: Shanghai Zhongshan Hospital

Brief Summary

This is a single-center, open-labeled, parallel group, randomized controlled trial to access the effect and safety of the Artificial Intelligence Assisted Insulin Titration System in patients with Type 2 Diabetes Mellitus.

Detailed Description

The study enrolls 44 patients with Type 2 Diabetes in Zhongshan Hospital who are on treatment with insulin for at least 3 months. They are randomly allocated into 2 groups at a ratio of 1:1 after screening for the inclusion and exclusion criteria. Patients in the Intervention group receive insulin regimen set by the AI assisted system and patients in Control group receive insulin regimen set by physicians. This study will be conducted in the Department of Endocrinology, Zhongshan Hospital,Fudan University and consist of a 7-day intervention period. Patient allocation will be stratified by HbA1c, BMI and previous total insulin doses.The primary endpoint is the percentage of time of sensor glucose measurements in targeted range (3.9-10 mmol/L) during the 7-days trial period.

Study Timeline

• Study First Submitted: 2019-08-10
• Study First Submitted QC: 2019-08-10
• Study First Posted: 2019-08-13
• Study Start: 2019-09-27
• Primary Completion: 2020-01-22
• Study Completion: 2020-04-15
• Status Verified: 2020-07
• Last Update Submitted: 2020-07-24
• Last Update Posted: 2020-07-27

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 46

Inclusion Criteria

• Men or women aged 18-75 years old;
• Subjects who had been diagnosed with type 2 diabetes;
• Subjects who are on treatment with insulin for at least 3 months;
• HbA1c: 7.0%-11.0%.

Exclusion Criteria

• Subjects with acute complications of diabetes such as ketoacidosis or hyperglycemic hyperosmolar state;
• Subjects who change the insulin regimens during hospitalization;
• BMI ≥ 45kg/m2;
• Women who are pregnant or nursing;
• Subjects with severe cardiac, hepatic, renal or general diseases;
• Subjects with psychiatric disorders or impaired cognitive function;
• Subjects with severe edema, infections or peripheral circulation disorders;
• Patients treated with surgery during hospitalization;
• Subjects that are, in the judgement of the investigator, unlikely to comply with the protocol.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Arm && Interventions

Group	Intervention	Description
AI Group	AI assisted insulin system	Artificial intelligence assisted insulin titration system group
Control Group	Physician based insulin regime	Physicians decided insulin titration group

Primary Outcome Measures

Name	Time	Method
Proportion of time in target range	During 7-day intervention	The well-controlled blood glucose level is defined as the time of sensor glucose measurements in targeted range (3.9-10 mmol/L)

Secondary Outcome Measures

Name	Time	Method
Proportion of time in which the blood glucose level is over 10 mmol/L	During 7-day intervention	The poor control of blood glucose level is defined as greater than 10 mmol/L
Proportion of time in which the blood glucose level is below 3.9 mmol/L	During 7-day intervention	The hypoglycemia is defined as blood glucose level less than 3.9mmol/L
Total insulin dose	Each day during 7-day intervention	The total insulin dose is defined as daily insulin dose

Trial Locations

Locations (1)

180 Fenglin Road; 🇨🇳 Shanghai, China