November 18, 2026
Health news, explained with evidence
LIVE
Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine The Role of Daily Mobility Training in Managing Sedentary Tension New Theoretical Framework Explores Memory Formation and Dementia Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine The Role of Daily Mobility Training in Managing Sedentary Tension New Theoretical Framework Explores Memory Formation and Dementia

Pilot Study Explores Non-Invasive Blood Glucose Tracking Using Optical Data

🧠 AI Analysis 2 min read 👁 2

A new pilot study published in Nature Health Sciences evaluated a non-invasive method for estimating continuous glucose monitoring levels using fingertip visible and near-infrared reflectance in ten adults.

🧠AI Analysis

Key points

  • Pilot study tested non-invasive glucose estimation in 10 adults
  • Random Forest model yielded 10.379% MARD under cross-validation
  • Small sample size and lack of lab reference limit immediate clinical application

Researchers in South Korea have investigated a non-invasive approach to tracking blood glucose levels by analyzing visible and near-infrared spectral data from fingertips. Published in Nature Health Sciences, the pilot evaluation involved ten adult participants aged 40 to 70. The system captured optical measurements at a rate of approximately 12 per minute, yielding a dataset of 6,816 optical samples that were paired with readings from a commercial continuous glucose monitor. Investigators compared seven regression models using cross-validation techniques to determine how effectively the optical data could estimate glucose metrics.

Under subject-independent cross-validation, a Random Forest model achieved a mean absolute relative difference of 10.379 percent and an R-squared value of 0.767. Clarke Error Grid analysis indicated that a combined 85.30 percent of predictions fell within zones A and B. However, the study authors noted several limitations, including a small sample size of only ten individuals and a manually timed ten-minute offset that served as an approximation rather than a validated physiological lag correction. Furthermore, because no independent capillary or laboratory blood glucose reference was utilized, the clinical accuracy and safety of the measurement technique have not yet been definitively established.

What to know: While the findings suggest that optical glucose estimation may be technically feasible, the technology remains in early-stage development and is not yet ready for clinical use. Readers should always consult a qualified healthcare professional before making any personal medical or dietary decisions.

Source Nature Health Sciences — nature.com/articles/s41598-026-80548-4 ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.