diabetes-congress-2019-keynote

June 24-25, 2019 | Philadelphia, USA

DIABETES, ENDOCRINOLOGY, NUTRITION

AND NURSING MANAGEMENT

International Conference on

Diabetes Congress 2019

Journal of Diabetology | Volume 3

Page 8

OF EXCELLENCE

IN INTERNATIONAL

MEETINGS

YEARS

21,000 data and then re-integrated them into three distinctive PPG waveform types which revealed different personal-

ity traits and psychological behaviors of type 2 diabetes patients. For single time-stamped variables, he used tradition-

al time-series analysis. For interactions between two variables, he used spatial analysis. Furthermore, he also applied

Fourier Transform to conduct frequency domain analyses to discover some hidden characteristics of glucose waves. He

then developed an AI glucometer tool for patients to predict their weight, FPG, PPG and A1C. It uses various computer

science tools, including big data analytics, machine learning (self-learning, correction and simplification) and artificial

intelligence to achieve very high accuracy (95% to 99%).

Results:

In 2010, his average glucose was 280 mg/dL and A1C was >10%. Now, his glucose value is 116 mg/dL and A1C

is 6.5%. Since his health condition is stable, he no longer suffers from repetitive cardiovascular episodes.

Conclusion:

Instead of utilizing traditional biology, chemistry and statistics, the methodology of GH-Method:

math-physical medicine uses advanced mathematics, physics concept, engineering modeling and computer science

tools (big data analytics, artificial intelligence), which can be applied to other branches of medical research in order to

achieve a higher precision and deeper insight.

Fig.1. Comparison of MPM vs. BCM