## Electrical Engineering

#### Title

Blood Glucose Predictor

#### College - Author 1

College of Engineering

#### Department - Author 1

Electrical Engineering Department

#### Degree Name - Author 1

BS in Electrical Engineering

#### Date

12-2019

Tina Smilkstein, College of Engineering, Electrical Engineering Department

#### Abstract/Summary

For my senior project, I perform data analysis using statistical methods to determine body metrics that correlate with blood glucose levels. Working with Dr. Tina Smilkstein, I take repeat measurements from 6 different volunteers to establish trends in bodily metric data. The data taken includes weight, body fat, pulse rate, VO2, blood glucose, blood pressure, hours slept, and quality of sleep. Using these values, I use the program MiniTab to view results.

A few examples of correlations with blood glucose found in this project are:

• Systolic blood pressure for females had a regression line of 124.0 -0.3366*Blood Pressure. This indicates a negative correlation, meaning as blood pressure rose, blood glucose dropped. For males, the line equation is 59.47 + 0.2962*Blood Pressure, indicating a positive correlation.
• In the case of diastolic blood pressure, male data was quite scattered graphically, indicating the line of best fit is not an accurate representation of blood glucose. For females, the line is 111.9 – 0.3565*Blood Pressure (diastolic). This again indicates a negative correlation.
• In the case of weight, both lines graphically followed the data points. For males, the regression line is 162.6 – 0.342*Weight. For females, it is 103.2- 0.1525*Weight.
• The rest of the correlations and data is found in the contents of the report.

Leveraging the results of this research, patients can potentially input their information into a webpage that predicts whether or not they must prick their finger to view actual blood glucose. While this tool may provide an interesting learning opportunity, the numerical value provided is not meant to be taken as medical advice. Every individual has different bodily metrics, therefore the value given is for experimentation, not for a 100% accurate measurement. To be sure of your blood glucose, until the technology has improved, always use a Blood Glucose Monitor, since I am not a medical professional. Once perfected, this could lead to saved time, pain, and trouble for the user. For the following data, it reflects 18-24 year old college students without diabetes to establish a baseline.

COinS