GluRing estimated blood glucose without a needle in China's review

In the maker's trial that China's CMDE reviewed, the GluRing ring's needle-free glucose estimates differed from venous values by 9.20% on average, with 99.32% in Clarke zones A and B.

  • Not rated a person

    Accuracy was measured in the maker's pre-market trial, and the report gives no outcome of diabetes care.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Venous blood glucose of the same subjects, measured in pairs as the reference standard. Measured.

The system’s part
Not isolated. The trial measured the ring's estimates against venous glucose. It did not compare the AI model with another way of turning the light signals into glucose values. The trial was the maker's own. The report says that an artificial-intelligence model predicts glucose and that the apps and server contain a deep learning algorithm.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
GluRing and GluRing s non-invasive glucose meter (无创血糖仪)
Made by
Beijing Lepu Diagnostics Technology Co., Ltd. (北京乐普诊断科技股份有限公司)
Used by
Beijing Lepu Diagnostics Technology (registration trial with 96 subjects at three clinical institutions)
Where
Three clinical institutions in China that the report does not name
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Estimating the Quantifiable Characteristics of Products, Events, or Information, Monitoring Processes, Materials, or Surroundings
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    Center for Medical Device Evaluation (CMDE), National Medical Products Administration, China. 医疗器械产品注册技术审评报告：无创血糖仪 (technical review report for the registration of a non-invasive blood glucose meter), acceptance no. CQZ2500265, applicant 北京乐普诊断科技股份有限公司. Undated report, posted on CMDE's website on 12 August 2026. Section 三、临床评价概述 (clinical evaluation).

    平均绝对相对误差值（MARD%）结果及 95%CI 为 9.20%（8.65%，9.74%）
    经综合评价，在当前认知水平上，认为该产品上市带来的受益大于风险，综合剩余风险可接受。

Details

AI system

Reported configuration

Release 1 of the GluRing apps and server (full version 1.1.0)

Workflow

An LED on one side of the ring sent near-infrared light through the finger to an optical sensor on the other side. An artificial-intelligence model in the apps and server predicted blood glucose from the light signals. Each user first calibrated the ring with finger-stick readings while fasting and two hours after a meal.

Follow-up

Conditions for replication

Users are adults with type 2 diabetes who do not use insulin. Users repeat the finger-stick calibration at least every 30 days and keep testing finger-stick blood. The estimates do not serve to screen for or diagnose diabetes or to decide on medication. The ring is used for self-management outside medical institutions.

Entry details

Sector

Healthcare.

Purpose

Beijing Lepu Diagnostics Technology built GluRing and GluRing s to estimate blood glucose without a needle, for self-management by adults with type 2 diabetes who do not use insulin.

30 more questions not yet checked

model, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). GluRing estimated blood glucose without a needle in China's review (AIBD-1159). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1159.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions