a

Lorem ipsum dolor sit amet, consectetur adicing elit ut ullamcorper. leo, eget euismod orci. Cum sociis natoque penati bus et magnis dis.Proin gravida nibh vel velit auctor aliquet. Leo, eget euismod orci. Cum sociis natoque penati bus et magnis dis.Proin gravida nibh vel velit auctor aliquet.

  /  Project   /  Blog: Artificial Intelligence is Going to Disrupt Healthcare — Here’s How

Blog: Artificial Intelligence is Going to Disrupt Healthcare — Here’s How


There’s been a lot of talk around how artificial intelligence is going to diagnose diseases — and it’s true ai is going to disrupt the medical field.

Creating a medical tricorder

A medical tricorder is a portable device capable of diagnosing diseases in humans and can automate diagnostics.

Disrupting Healthcare Around the World

Google

Researchers at Google developed a deep learning algorithm that can automatically detect the condition with great accuracy. According to one paper, the software had a sensitivity score of 87 to 90 percent and 98 percent specificity for detecting diabetic retinopathy, which they defined as “moderate or worse diabetic retinopathy or referable macular edema by the majority decision of a panel of at least seven US board-certified ophthalmologists.”

London

Then, doctors at a hospital in London decided to develop it even further. They trained an algorithm that could recommend the correct treatment approach for more than 50 eye diseases with 94 percent accuracy. “They compared that to eye specialists, and the machine didn’t miss one referral, but the eye doctors did,” doctors said. “The eye doctors were only in agreement about the referrals 65 percent of the time. So that’s the beginning of moving from narrow AI to triage.”

China

Doctors in China used AI to diagnose diseases in the colon during a colonoscopy. The AI system significantly increased the detection (29 percent compared to 20 percent)

We can shorten wait times by using AI
AI chatbots can also be used for diagnosis

Long story short, machine vision is starting to improve, and soon there is a possibility that we can have a handheld machine that can diagnose any disease.


Challenges

Obviously, like with any technologies, there are going to be obstacles. In this case, privacy and data problems come up.

Machine learning is best when lots of data is fed into an algorithm — the more data, the better. If we’re going to do deep learning and provide feedback, the only way it’ll work well is if we have all a person’s data: sensor data, genome data, microbiome data, medical records. It’s a long list. However, counties like Estonia have found a way to allow people full control of their personal and medical data.

Giving people their data will help with security.

Right now, our data is stored on massive servers and clouds. One of the ways for data to be safe and secure would be to store it in the smallest units possible — which could be helpful if each person was responsible for their own data.

There are so many other ways artificial intelligence can be used in the medical field; these are just a few. But even with these, imagine the implications it could have in the future and what it would mean.

AI can help with time-consuming tasks too, so what if in the future, artificial intelligence is note taking by voice and keeping records of the patients visit if ever needed?

There are a lot of possibilities.

“It’s likely that machines will be smarter than us before the end of the century — not just at chess or trivia questions but at just about everything, from mathematics and engineering to science and medicine.” — Gary Marcus


Key Takeaways

  • Diagnosing with artificial intelligence is going to make diagnostics more accurate and precise
  • Countries around the world have started to implement this, like London, China etc.
  • There is data that shows that using machine vision results in more accuracy
  • Diagnosing isn’t the only way AI is being used in healthcare, for example, it can also shorten wait times
  • However, there are obstacles, like data and privacy which could be harmful effects to this
  • But those obstacles do have a possible solution, by allowing each patient their data.

If you enjoyed this article, please give it some claps so I know you liked it!

You can also follow me on LinkedIn to see what I’m up to or sign up for my monthly newsletter to get updates from me:

Source: Artificial Intelligence on Medium

(Visited 3 times, 1 visits today)
Post a Comment

Newsletter