Are there AI models that can help deal with diabetes?

There are pretrained AI models for diabetes.

GlucoNet Model: Deep learning model that can predict Glucose levels based on carbohydrate intake.

Deep Gluco Model: Not only takes carbo intake into consideration but also insulin dosage, physical activity, etc.

GlucoNet is adequate for diabetes type II. I will be homing in on type II.

These are used to improve the MIT control loop for adjusting optimal carbo intake.

There is company (Alertgy) in Melbourne, Australia involved in the development of diabetes monitored by a wearable device.

Right now, I have one with questionable activity, but qualitatively measuring (Zero, when not connected and 3 peaks to coincide in time with break fast, lunch and dinner).

How trust worthy is AI?

 AI seems to be very promising. It is supposed to make a continental shift type of change. Has that time arrived, yet?

Health care professional, nutritionists, patients of all kinds seek information about what they eat. AI seems to be an ideal tool to get a summarized report of what can be eaten, by who. 

I tried to find about 'Ragi' also known as Finger Millet which has properties superior to rice for its energy and fiber content. I used the easily available Bing AI. I find it awfully lacking in the information it can find.

As I am concerned about diabetes control, I wanted to find nutrition information about 100 grams of Ragi flour.

Here is a picture of what Bing AI (on the right) thinks it is and what the web brings up (on the left).

This is by AI copied from the above:

I apologize for the confusion. You are correct, and I apologize for the incorrect information in my previous response. The values I provided for 10 grams of uncooked ragi powder were mistakenly repeated for 25 grams of uncooked ragi powder. Here are the correct values for 25 grams of uncooked ragi powder:

• Carbohydrates: Around 0.89 grams.
• Protein: Approximately 0.13 grams.
• Potassium: Around 26.66 milligrams.
• Cholesterol: Cholesterol is found only in animal products, so ragi powder does not contain any cholesterol.
• Calories: The calorie content of 25 grams of uncooked ragi powder is not available in the search results I found.

I apologize for any confusion caused by my previous response. Please let me know if there’s anything else I can help with!

This is from the web page (Ragi Nutritional Value Per 100g, Finger Millet Health Benefits, Ragi Recipes, Ragi Flour Nutrition Facts | ParentCircle).

Ragi nutritional value (per 100g)

Energy  320kcal

Dietary fiber  11.18g

Total carbohydrate  66.82g

Total fat  1.92g

Protein  7.16g

Total folates  34.66mcg

Vitamin B1 (thiamin)  0.37mg

Vitamin B2 (riboflavin)  0.17mg

Vitamin B3 (niacin)  1.34mg

Vitamin B6 (pyridoxine)  0.05mg

Vitamin K  0.9mcg

Calcium  364mg

Iron  4.62mg

Magnesium  146mg

Phosphorus   210mg

Potassium   443mg

Manganese   3.19mg

Zinc  2.53mg

These is a huge difference in carbohydrate value between these.

How do I get Glucose data from the FreeStyle Libre glucose sensor?

 I have been having glucose-related issues for many years. Although diagnostic data indicates I am diabetic, I am not taking any medication for diabetes. However, I was always concerned about its possible effects. While my lipid profiles were under safe 'standard values', I suffered a heart attack in 2022. I decided to look at my glucose values more closely to make adjustments in my lifestyle and diet. The only diagnostic at my disposal was the painful pricking of the finger and measuring with a strip. This is totally unsatisfactory as it can provide only a single data point. I have always wondered how healthcare providers make decisions on this single value measured in a doctor's office once in a couple of months.

Fortunately, I was able to get a Freestyle Libre glucose sensor (Freestyle Libre 14-day). Now, at least I have a tool to look at what I am eating and associate it with glucose levels. I have been having it for the past two days. The display available on the Libre Link app which is available for Android and iPhones is quite nice but I want to look at it more ways.  The Libre website gives access to this data on their website. 

The sensor gets data about interstitial glucose every 15 minutes and stores it on the website. Here is how you can get the data. 

These are screenshots of the steps I took to get the data on the website to my computer. It is a Dell laptop with Windows 64 OS and I also have Microsoft Excel on the computer.

This is Libre View from the Libre website

You need to agree before you proceed.

You need to log in to download data. This means you have purchased the sensor and also installed the Libre link app on your phone (Android or iPhone). Note that you have enabled two-factor authorization.

After being verified you got access to the site.

Now click Download Glucose data at the top-right corner.

Your data appears in your Downloads folder on your computer.

Here is a sample of the downloaded data.

I have clipped off some personal information.

Although I have shown a few columns, there are a lot more useful columns that contain data related to custom test times and notes associated with those events.

Hope this helps. 

Effects of Yoga using Freestyle CGM System- Will be published soon.