Non-invasive glucose estimation leaderboard
VitalDB: MARD
6 reported results for non-invasive glucose estimation on VitalDB, ranked by MARD. Top reported: MFCC + XGBoost (Prabha) (21.56). Every row cites its source…
This page ranks every result ChatPPG has recorded for non-invasive glucose estimation on VitalDB, measured by MARD (%) (lower is better). Each number is copied from the publication cited in its row, and ranks apply only within this dataset and metric.
| Rank | Method & evaluation | MARD (%)↓ Lower is better |
|---|---|---|
| 1 | MFCC + XGBoost (Prabha) MFCC features + XGBoost (Prabha et al. 2022 method) Evaluation detailsReproduced by Supraja et al. 2026 on VitalDB intraoperative finger PPG vs lab glucose; leave-some-participants-out (test = 1/5 of participants, non-overlapping), mean of 5 folds. A predict-the-training-mean baseline scores within ~1 mg/dL of every model. Reported as of: 2026-10-16 | 21.56 |
| 2 | 1D-CNN (Alghlayini) 1D-CNN on raw PPG (Alghlayini et al. 2023 method) Evaluation detailsReproduced by Supraja et al. 2026 on VitalDB intraoperative finger PPG vs lab glucose; leave-some-participants-out (test = 1/5 of participants, non-overlapping), mean of 5 folds. A predict-the-training-mean baseline scores within ~1 mg/dL of every model. Reported as of: 2026-10-16 | 21.8 |
| 3 | XGBoost (Gupta) PPG features + XGBoost (Gupta et al. 2021 method) Evaluation detailsReproduced by Supraja et al. 2026 on VitalDB intraoperative finger PPG vs lab glucose; leave-some-participants-out (test = 1/5 of participants, non-overlapping), mean of 5 folds. A predict-the-training-mean baseline scores within ~1 mg/dL of every model. Reported as of: 2026-10-16 | 21.96 |
| 4 | PLS (Islam) PPG features + partial least squares (Islam et al. 2021 method) Evaluation detailsReproduced by Supraja et al. 2026 on VitalDB intraoperative finger PPG vs lab glucose; leave-some-participants-out (test = 1/5 of participants, non-overlapping), mean of 5 folds. A predict-the-training-mean baseline scores within ~1 mg/dL of every model. Reported as of: 2026-10-16 | 22.28 |
| 5 | Mean baseline Mean-of-training-set baseline Evaluation detailsReproduced by Supraja et al. 2026 on VitalDB intraoperative finger PPG vs lab glucose; leave-some-participants-out (test = 1/5 of participants, non-overlapping), mean of 5 folds. A predict-the-training-mean baseline scores within ~1 mg/dL of every model. Reported as of: 2026-10-16 | 22.52 |
| 6 | ResNet34 (Zeynali) ResNet34 on raw 1 s PPG (Zeynali et al. 2025 method) Evaluation detailsReproduced by Supraja et al. 2026 on VitalDB intraoperative finger PPG vs lab glucose; leave-some-participants-out (test = 1/5 of participants, non-overlapping), mean of 5 folds. A predict-the-training-mean baseline scores within ~1 mg/dL of every model. Reported as of: 2026-10-16 | 22.55 |
Rows are ranked only within this task × dataset × metric. Protocols can differ; read each method's evaluation details before comparing. Latest reported row: 2026-10-16.
About the dataset
VitalDB: intraoperative multi-parameter vitals (PhysioNet mirror)
- Subjects
- 6388
- Signals
- ppg, ecg, resp, abp, co2
- Licence
- CC BY 4.0 (PhysioNet release)
Related leaderboards
Other metrics on VitalDB
Non-invasive glucose estimation on other datasets
- PPG Signals for Blood Glucose Measurement (Kermani / Mendeley): Clarke zone A (9)
- PPG Signals for Blood Glucose Measurement (Kermani / Mendeley): MAE (mg/dL) (9)
- PPG Signals for Blood Glucose Measurement (Kermani / Mendeley): MARD (9)
- BIG IDEAs Lab Glycemic Variability and Wearable Device Data: MARD (4)
- BIG IDEAs Lab Glycemic Variability and Wearable Device Data: RMSE (mg/dL) (4)
- PPG Signals for Blood Glucose Measurement (Kermani / Mendeley): RMSE (mg/dL) (3)
- BIG IDEAs Lab Glycemic Variability and Wearable Device Data: Clarke zone A (2)
Data and submissions
Download every leaderboard as JSON or CSV. Missing a published result? Email hello@chatppg.com with the paper link and the exact table it comes from.
Cite this
Cite the page URL and the date you accessed it. Please also cite the original publications listed above.
APA
ChatPPG. (2026). VitalDB MARD leaderboard: non-invasive glucose estimation [Data set]. ChatPPG Research Hub. https://chatppg.com/research/leaderboards/glucose-estimation/vitaldb-mard-pct
BibTeX
@misc{chatppg_glucose_estimation_vitaldb_mard_pct,
author = {{ChatPPG}},
title = {{VitalDB MARD leaderboard: non-invasive glucose estimation}},
year = {2026},
month = oct,
howpublished = {\url{https://chatppg.com/research/leaderboards/glucose-estimation/vitaldb-mard-pct}},
note = {ChatPPG Research Hub}
}CITATION.cff
cff-version: 1.2.0 message: "If you use this resource, please cite it as below." type: dataset title: "VitalDB MARD leaderboard: non-invasive glucose estimation" authors: - name: "ChatPPG" url: "https://chatppg.com/research/leaderboards/glucose-estimation/vitaldb-mard-pct" date-released: "2026-10-16"