GlucoSense: Non-Invasive Glucose Monitoring using Mobile Devices
Bibliographic record
Abstract
Regular glucose monitoring is crucial for diabetic patients to avoid the risk of health complications such as stroke, kidney failure, heart disease, and even death. Most current devices for measuring glucose are costly and painful. We propose GlucoSense, a non-invasive glucose sensing solution on mobile devices. GlucoSense builds on the fact that glucose is an optically active molecule, which interacts with various wavelengths. We first conduct spectral analysis to demonstrate the feasibility of measuring glucose in the visible and near-infrared range (400–1000 nm), which is the range available on mobile devices. We also identify the relative importance of various spectral bands in this range. We further propose multiple practical designs for obtaining the required spectral bands for measuring glucose. We then design GlucoSense exploiting the sensing capabilities of modern smartphones combined with machine learning models. We conduct an ethics-approved user study with a diverse set of participants in terms of age, sex, ethnicity, and body mass index (BMI). We compare GlucoSense against a widely-used, FDA-approved glucose measuring device. Our results show that 80.4% of GlucoSense predictions are within Zone A (clinically accurate), and the remaining 19.3% are in Zone B (clinically acceptable) of the Clarke Error Grid (CEG). In addition, 99.7% of the predictions are within the None and Slight risk zones of the Surveillance Error Grid (SEG), indicating their high accuracy. Both CEG and SEG are standard metrics for assessing glucose-measuring devices. These results were obtained by GlucoSense running on unmodified phones in realistic environments with diverse illuminations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".