GH-METHODS

Math-Physical Medicine

NO. 099A

Application of linear equation-based PPG prediction model for four type 2 diabetes clinical cases (GH-Method: math-physical medicine)

Corresponding Author: Gerald C. Hsu, eclaireMD Foundation, USA.

Introduction
This paper describes four clinic cases of applying two-parameters linear equation for postprandial plasma glucose (PPG) prediction.  The author developed this simplified yet highly accurate equation to predict PPG in order to help type 2 diabetes (T2D) patients on their disease control.

Math-physical medicine (MPM) starts with the observation of the human body’s physical phenomena (not biological or chemical characteristics), collecting elements of the disease related data (preferring big data), utilizing applicable engineering modeling techniques, developing appropriate mathematical equations (not just statistical analysis), and finally predicting the direction of the development and control mechanism of the disease.

Methods
As described in his previous paper (see Abstract 94), he developed the following linear equation:

  • PPG = A + (f(x) * B – f(y) * C) * D

Where

  • f(x) = carbs/sugar intake in grams
    f(y) = walking steps in thousands
    Variable A = baseline glucose value
    B, C, D = 3 different variables

The author selected four T2D patients with different ages, genders, races, diabetes history, and country of residence (varying lifestyles).  Each case of collected PPG data with starting dates are different.  Except Case C, all other three cases end on 7/5/2019.  For Case C, both measured PPG (missing ~60%) and meal phots (missing ~40%) are scarcely collected after 4/21/2019.  Therefore, his data period consists of one year (4/21/2018 – 4/20/2019).

The author used 90-days moving average curves for comparison since the PPG moving trends and variance patterns are easily detected.  Furthermore, linear accuracy and correlation coefficients of equation-based PPG versus finger-piercing measured PPG are calculated and listed in Table 1.

Table 1: Background, Data Integrity, and Results of 4 Clinical Cases

Results
Table 1 shows the summarized information of four clinic cases, including their background information, data integrity, analysis results of accuracy and correlation between equation-based PPG prediction versus finger-piercing measured PPG.

  • Case A: prediction accuracy is 99.9% and correlation is 75%.
  • Case B: prediction accuracy is 99.7% and correlation is 74%.
  • Case C: prediction accuracy is 99.7% and correlation is 78%.
  • Case D: prediction accuracy is 99.4% and correlation is 88%.
Figure 1: Both measured PPG and AI-based PPG of 4 Clinical Cases
to show data integrity
Figure 2: Both measured PPG and Equation-based PPG of 4 Clinical Cases
to show accuracy and correlation

Conclusion
This big data analytics derived two-parameters linear equation of PPG prediction model which is quite simple for patients to use, while offering a high accuracy for PPG prediction.  Through this study of four clinical cases, the author has proved the validity of this two-parameters linear equation-based PPG prediction model.  Over the past five years, he has been continuing his efforts to simplify his glucose prediction models in order to provide a simple and practical tool for T2D patients to use.  By offering this streamlined process, the patients will be able to control their diabetes by removing certain psychological resistance or reluctance.

References

  1. Hsu, Gerald C. (2018). Using Math-Physical Medicine to Control T2D via Metabolism Monitoring and Glucose Predictions. Journal of Endocrinology and Diabetes, 1(1), 1-6.
  2. Hsu, Gerald C. (2018). Using Signal Processing Techniques to Predict PPG for T2D. International Journal of Diabetes & Metabolic Disorders, 3(2),1-3.
  3. Hsu, Gerald C. (2018). Using Math-Physical Medicine and Artificial Intelligence Technology to Manage Lifestyle and Control Metabolic Conditions of T2D. International Journal of Diabetes & Its Complications, 2(3),1-7.
  4. Hsu, Gerald C. (2018). Using Math-Physical Medicine to Study the Risk Probability of having a Heart Attack or Stroke Based on Three Approaches, Medical Conditions, Lifestyle Management Details, and Metabolic Index. EC Cardiology, 5(12), 1-9.