Big Data News Hubb
Advertisement
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
Big Data News Hubb
No Result
View All Result
Home Big Data

How AI Can be Used to Help People See

admin by admin
December 17, 2022
in Big Data


In this special guest feature, Dr George Magrath, CEO of Lexitas, explains how AI is being harnessed in the development of eye care medicines. Lexitas is a 160-person company which partners with pharmaceutical firms to develop novel eye care drugs by running clinical trials. Dr Magrath is a trained ophthalmologist who, despite his busy day-to-day work leading Lexitas, still takes one day out every week to maintain his practice and treat patients with rare eye conditions. In fact, he is the only physician in his home state of South Carolina with fellowship training in treating cancers in and around the eye.

The potential of AI to make people healthier is revolutionary.

I’ve seen that potential first hand as we develop new medicines. I run a company which partners with pharmaceutical firms to develop novel eye care drugs by running clinical trials, and AI is playing an increasing role in these trials.

Put simply, it is already becoming a genuine force for making treatments better.

AI is transforming the development of new eye care drugs in ophthalmic clinical trials in two key ways. The first is to help pick out patients who are most likely to benefit from a potential treatment.

AI is being used to identify these patients based on imaging of their eyes before inclusion in a trial. A good example of this relates to age-related macular degeneration (AMD), a condition which can cause some patients to eventually suffer severe vision loss, while others do not.

By using AI and deep learning, you can train a machine to analyze historical imaging of patients who progressed with AMD and those who did not progress. Once the machine has learned to pick out which patients might or might not progress to AMD, you can then apply it to images of future patients who you’re considering putting into a clinical trial.

This means the AI can then predict the patients most likely to progress to severe vision loss – resulting in them being chosen for enrollment on a trial as they are most likely to benefit from participating. Being able to pick out the most suited patients, with less trial and error, is an extremely powerful tool because it improves data outputs and also cuts out unnecessary exposure to risk and potential side effects among those people who are unlikely to need the treatment anyway.

Second, AI is completely changing the way we can evaluate drug effectiveness data coming out of clinical trials. The data allow us to learn more about how our medicines work as we test them. 

One recent example of this that I oversaw was in a trial of a potential treatment for diabetic eye disease, the leading cause of blindness in working age adults in the US. We used AI to identify and quantify the volume of fluid in the retina over time on a 3D reconstruction using optical coherence tomography (OCT). The AI was able to map the fluid and quantify the change in fluid volume – i.e. swelling – in different areas of the retina, giving us amazing insight into the effect of the investigational product on the patients.

This is a specific example of evaluating the effect of a drug in ways we could not without AI, as it’s impossible for the naked human eye to pick up. Self-evidently, the purpose of a clinical trial is to learn as much as you can about a drug and its biological effect, so this is hugely important progress.

So, through predicting patients most at risk of sight loss, and providing ultra-precise data giving unprecedented insight into the biological effect of treatments, AI is already a powerful force in the ophthalmic clinical trial space – with so much further potential going forward. And the more this can be harnessed, the more it will help people see.

Sign up for the free insideBIGDATA newsletter.

Join us on Twitter: https://twitter.com/InsideBigData1

Join us on LinkedIn: https://www.linkedin.com/company/insidebigdata/

Join us on Facebook: https://www.facebook.com/insideBIGDATANOW





Source link

Previous Post

Getting started with AWS Glue Data Quality from the AWS Glue Data Catalog

Next Post

Cloudera Named a Leader in the 2022 Gartner® Magic Quadrant™ for Cloud Database Management Systems (DBMS)

Next Post

Cloudera Named a Leader in the 2022 Gartner® Magic Quadrant™ for Cloud Database Management Systems (DBMS)

Recommended

Enable cross-account sharing with direct IAM principals using AWS Lake Formation Tags

January 21, 2023

How To Get The Most Out Of Data Cleansing And Matching Tools

December 25, 2022

Why a Data-driven Culture is Important to the Success of your SaaS Business

January 21, 2023

Don't miss it

News

Stormy Skies Ahead? Report Finds 20% of Businesses Intend to Move Workloads From Cloud to On-Prem

February 5, 2023
Big Data

An Introduction to Disaster Recovery with the Cloudera Data Platform

February 4, 2023
Big Data

Comet Announces Convergence 2023, the Leading Conference to Explore the New Frontiers of Machine Learning

February 4, 2023
Big Data

Design Patterns for Batch Processing in Financial Services

February 4, 2023
News

AWS Lake Formation 2022 year in review

February 4, 2023
News

Data Mesh Creator Takes Next Data Step

February 4, 2023

big-data-footer-white

© 2022 Big Data News Hubb All rights reserved.

Use of these names, logos, and brands does not imply endorsement unless specified. By using this site, you agree to the Privacy Policy and Terms & Conditions.

Navigate Site

  • Home
  • Big Data
  • News
  • Contact us

Newsletter Sign Up

No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us

© 2022 Big Data News Hubb All rights reserved.