Corresponding Author: Gerald C. Hsu, eclaireMD Foundation, USA.
This clinical case is based on a 46-year-old female with type 2 diabetes (T2D). Her health data for a period of 174 days (from 9/11/2018 to 2/11/2019) are listed as follows:
This particular patient has been following the guidelines outlined from published findings, conclusions, and recommendations of the GH-Method: math-physical medicine approach (MPM), which utilized the developed AI Glucometer tool to predict and control her T2D conditions.
The major data facts and condition improvements for this patient are:
- Weight reduced by 27 lbs. within 5 months.
- As a direct result from weight reduction, her FPG has also decreased by 50 mg/dL.
- Weight and FPG have a very high correlation of 89%.
- PPG decreased by 80 mg/dL. It has a 46% correlation with her carbs/sugar intake (15 gram, low-carbs diet) and -53% correlation with post-meal walking (2,179 steps and ~20 minutes).
- The accuracy of predicted glucose (120.21 mg/dL) vs. measured glucose (125.65 mg/dL) is 96%; however, their correlation is only 61% due to some missing or incorrect data input around November 2018.
- This patient utilized the author’s developed AI Glucometer which has learned sufficient local food information to be able to predict PPG extremely accurate (96%). As a comparison, the author’s PPG prediction model has 99.3% accuracy and 82% correlation based on his collected 3,992 meals data (53% US and 47% international).
Prior to the trial on GH-Method: math-physical medicine and AI tool, her medications included
As she refused the insulin therapy suggested ,Empagliflozin was added. Within 2 to 3 months of trial her medications were reduced.
By using the GH-Method: math-physical medicine and AI tool, along with following the physician’s methodical medication treatment plan, this T2D patient has achieved significant improvement on controlling her diabetes conditions within five months.