What is Machine Learning?

What do you think of when you hear the words, “machine learning”? 

Do you think of something out of The Matrix? Machines developing superhuman intelligence and taking over the world? A post-apocalyptic world where machines enslave and subdue us? 

If that was your first thought, it wouldn’t be surprising. We see scenes like that all the time in movies and books. But is that really accurate?

In this post, we breakdown what machine learning really is, and its value to the healthcare sector.

 

What is machine learning?

So, what is machine learning?

Basically, it’s the idea that a machine can learn to perform specific tasks without needing a human to program it. It does this by recognizing patterns and trends. Check out our last blog post for more on this.

Machine learning is a subset of artificial intelligence (AI). AI is the idea that machines can perform tasks that we would normally associate with human intelligence. The term was coined in 1956 by Stanford University professor, John McCarthy.

 

What is machine learning?

 

How is machine learning used by businesses?

Some of the biggest businesses use machine learning to better assist their customers. Netflix uses it to learn our TV show and movie preferences. As a result, Netflix is able to give us tailor-made suggestions on what to watch next.

Similarly, Google uses it to learn our interests from our search histories. Thus, Google is able to show us ads that closely match our searches.

Finally, YouTube uses a machine learning algorithm to recommend videos for us to watch. It does this by learning a model for user preferences. Additionally, YouTube helps us search for specific clips. It does this by using the keywords used in video titles and descriptions, as well as the audio and visual content of the videos. 

 

Netflix using machine learning to learn our preferences.

 

How is machine learning used in the healthcare sector?   

In the past few years, machine learning has revolutionized the healthcare sector, helping doctors better assist their patients.

Here are a few recent examples of how it’s used in the healthcare sector:

1. Google researchers developed an algorithm that uses images of patients’ retinas to detect early signs of diabetic retinopathy.

2. Ginger.io uses smartphone technology, data science, and clinical services to provide personalized care and support for patients with depression and anxiety.

3. Lumiata developed a medical graph that organizes and analyzes data. As a result, doctors are able to better diagnose patients and prescribe medications.  

 

How does machine learning help patients with Type 1 Diabetes?

At Docto, we help patients with Type 1 Diabetes better manage their condition. We use metabolic, behavioural, and current glucose data to predict patients’ blood sugar levels one hour in advance. Knowing what your levels will be in the future can help you in a number of ways. Not only will you be able to better track your health, you will also be able to make smarter decisions. 

And how do we do this? You guessed it! Thanks to machine learning, Docto learns and predicts fluctuations in a user’s levels, and makes future predictions.

Docto learns and predicts future glucose data.

Will machine learning result in machines taking over humans?

While computers are getting smarter and smarter, thanks to machine learning algorithms, they do not have the ability to think and reason. For now, we’ll have to leave it to the movies to create stories about machines enslaving humans.

***

Interested in learning more about how Docto works? Check out this postAdditionally, make sure to follow us on Facebook and Twitter for more articles about Type 1 Diabetes innovation and research.

Download Button


Comments (0)

Leave a comment