Introduction and Objectives: Digital twin (DT) platform uses Artificial Intelligence (AI) and Internet of Things, to integrate multi-dimensional data to give precision nutrition and health recommendations via the mobile app and by coaches. Remission was defined as A1C levels less than 6.5% without medication for over 3 months. Status of diabetic retinopathy (DR) was assessed in patients on DT platform.

Methods: We monitored 181 T2DM patients, across 4 centers, for remission of T2DM, assessing changes in DR and HbA1c levels, with a focus on participants with initial DR. Validated handheld fundus camera facilitated retinal imaging. Statistical analysis, including the Pearson correlation coefficient, explored the link between HbA1c levels and DR progression or regression.

Results: Mean age, duration of diabetes, were 44 years (±8.6) and 3.7 years (±2.7). Mean HbA1c decrease was 3.03 (8.9% to 5.8), indicating significant glycemic control improvements from baseline to Day 360. 75.69% of the participants (n=137) achieved remission. Among those initially diagnosed with DR (n=16), 43.75% (n=7) showed regression, with no evidence of DR. 55.25% of the participants (n=100), continued, with absence of the evidence of DR. There was a weak negative correlation between remission of T2DM and retinopathy reversal (r=-0.0867) which indicates that remission of T2DM might not be a strong predictor of retinopathy improvement.

Conclusion: DT which leads to remission of T2DM has potential for regressing diabetic retinopathy in a significant subset of patients. The remarkable percentage of individuals moving from DR to absence of DR emphasizes the potential for positive retinopathy outcomes. However, the minimal correlation with remission of T2DM suggests the importance of comprehensive diabetic care strategies, extending beyond glycemic management to include specific retinopathy interventions.

Disclosure

S. Joshi: None. M. Dharmalingam: None. A. Vadavi: None. A. Keshavamurthy: None. S. Bhonsley: None. L. Shah: Employee; Twin Health. M. Panandikar: None. P. Shamanna: None.

Readers may use this article as long as the work is properly cited, the use is educational and not for profit, and the work is not altered. More information is available at http://www.diabetesjournals.org/content/license.