Clinical Evidence · Day 15

How Bio-Well Detected Blood Sugar Patterns: The Diabetes Study

When researchers in Bangalore scanned 102 people's fingertips, the patterns that emerged matched their fasting blood sugar levels — in ways nobody expected.

In This Guide

1. Why This Study Matters
2. What the Researchers Did
3. Interactive: The Key Findings
4. The Surprise: Why Patterns Differed by Group
5. The Second Bangalore Study
6. What the Study Can't Tell Us
7. What This Means for Bio-Well Users

Here's the question the researchers were asking: If you scan someone's fingertips with a GDV device, can the patterns in the data tell you anything about their blood sugar levels?

This matters because fasting blood sugar (FBS) testing currently requires a blood draw — needles, lab processing, waiting for results. If fingertip emission patterns correlate reliably with blood sugar levels, it could open the door to a completely non-invasive screening method. Not a replacement for blood tests, but a potential early-warning system.

The team at S-VYASA University in Bangalore screened 200 people from yoga camps and the university's health center. Of those, 102 qualified for the study (the rest had incomplete data or image quality issues). Each person got both a standard fasting blood sugar test and a full EPI (GDV) fingertip scan.

Each participant received a standard 10-finger EPI scan. The researchers then used regression analysis to look for correlations between EPI parameters (area, intensity, entropy, organ-specific readings) and fasting blood sugar levels. They analyzed each group separately — because, as it turned out, the correlations were different depending on whether you were healthy, prediabetic, or diabetic.

Tap each group to see what the researchers found when they compared fingertip emission patterns to blood sugar levels:

Perhaps the most interesting finding wasn't that the EPI data correlated with blood sugar — it was that the correlations were different depending on the stage of the disease.

Think about what this means: the fingertip emission patterns didn't just show "high sugar" or "low sugar." They showed a progression — from generalized patterns in healthy people, to organ-specific patterns in prediabetics, to multi-system disruption in diabetics. This mirrors exactly how diabetes actually develops in the body.

The same research group at S-VYASA published a companion study in 2016 — this time with 200 subjects from a diabetic center in Bangalore. Rather than looking for correlations, this study went a step further: they used a neural network classifier to try to predict diabetes status from EPI data alone.

Together, these two studies from the same university and timeframe provide independent data points suggesting that EPI/GDV parameters contain information relevant to metabolic health. The combination of correlation analysis and machine learning classification strengthens the overall finding.

This is a genuinely interesting study — but like all single studies, it has important limitations that must be stated clearly:

This study doesn't mean Bio-Well can diagnose diabetes. It means that GDV/EPI technology captures data that has a statistically significant relationship with a major metabolic marker. That's a meaningful finding that supports the broader premise of Bio-Well: that fingertip emission patterns contain physiologically relevant information.

For practitioners, the takeaway is that the organ-sector readings in your Bio-Well reports — especially pancreas and kidney zones — may be capturing real physiological signals, not just noise. This supports using Bio-Well as a complementary screening tool alongside conventional lab work, rather than as a replacement for it.

Sources Cited in This Article

1. Bhat RK, Deo G, Mavathur R, Srinivasan TM. "Correlation of Electrophotonic Imaging Parameters With Fasting Blood Sugar in Normal, Prediabetic, and Diabetic Study Participants." J Evidence-Based Complementary & Alternative Medicine. 2016;22(3):441-448. PMC5871158 → · PMID: 27821611 →
2. Kumar SK, Srinivasan TM, Nagendra HR, Marimuthu P. "Electrophotonic Imaging Based Analysis of Diabetes." Int J Complement Alt Med. 2016;4(5):134-137. DOI: 10.15406/ijcam.2016.04.00134 →
3. Korotkov, K. "Review of EPI papers 2008–2018." Int J Complement Alt Med. 2018;11(6). DOI →
4. IUMAB GDV research database — diabetes studies index. iumab.org →
5. Bio-Well technology overview. bio-well.com/pages/science →