跳至主要内容
临床试验/NCT06642467
NCT06642467已完成不适用

BGEM Use as Blood Glucose Prediction Model in T2DM Population of Indonesia

Krida Wacana Christian University1 个研究点 分布在 1 个国家目标入组 885 人开始时间: 2024年7月30日最近更新:
适应症

试验速览

阶段
不适用
状态
已完成
发起方
入组人数
885
试验地点
1
主要终点
Prediction value of BGEM

研究概览

简要总结

Using signals from consumer-grade PPG sensors on wrist wearables, smart rings or hearables, BGEM® AI model computes the relevant digital biomarkers correlated with the change of blood glucose level to predict a blood glucose result for monitoring and evaluating diabetic risks Ukrida in collaboration with Actxa & Lif aims to enhance the current model's prediction accuracy to predict the blood glucose levels of individuals almost as accurately as a glucometer. To achieve this, Actxa aims to collect data from around 500 individuals with diabetes in this exercise and 400 healthy or undiagnosed (prediabetes/diabetes) individuals.

详细描述

Background Powered by our AI-driven algorithm, the Actxa's Blood Glucose Evaluation and Monitoring (BGEM®) is a cloud-based technology that enables wearables with photoplethysmography (PPG) sensors to monitor and evaluate diabetic risk of individuals regularly in a non-invasive way.

Using signals from consumer-grade PPG sensors on wrist wearables, smart rings or hearables, BGEM® AI model computes the relevant digital biomarkers correlated with the change of blood glucose level to predict a blood glucose result for monitoring and evaluating diabetic risks. Our previous study has shown the potential of using PPG sensors to detect elevated blood glucose levels among a non-diabetic population1.

Objective Ukrida in collaboration with Actxa & Lif to enhance the current model's prediction accuracy to predict the blood glucose levels of individuals almost as accurately as a glucometer. To achieve this, Actxa aims to collect data from around 500 individuals with diabetes in this exercise and 400 healthy or undiagnosed (prediabetes/diabetes) individuals, as part of Actxa's collaboration with UKRIDA Hospital.

With the data collected, our algorithm holds the potential to significantly improve the management of blood glucose levels for people with and without diabetes, ultimately enhancing their overall quality of life.

研究设计

研究类型
Observational
观察模型
Case Crossover
时间视角
Cross Sectional

入排标准

年龄范围
18 Years 至 59 Years(Adult)
性别
All
接受健康志愿者

入选标准

  • age between 18-59 yo
  • diabetic or non diabetic
  • healthy enough to undergoes normal daily activity

排除标准

  • o Wears a pacemaker
  • Is currently pregnant
  • Has an infection
  • Has a fever

结局指标

主要结局

Prediction value of BGEM

时间窗: July-December 2024

Result of predictive model will be compared with Hba1c

次要结局

  • Variables influencing BGEM(July-December 2024)

研究者

发起方
Krida Wacana Christian University
申办方类型
Other
责任方
Sponsor

研究点 (1)

Loading locations...

相似试验