Friday, August 16

How AI in Healthcare is performing diagnosis and saving lives at NHS

A doctor can use Optical Coherence Tomography (OCT) scanners to scan an eye and detect eye diseases. OCT scanners create around 65 million data points each time they are used – mapping each layer of the retina and that's lot of data for doctor to study. DeepMind's AI claims to recognise 50 common eye problems from the OCT data - which means a doctor does not have to spend time in analyzing the data. The results of AI have been promising in the trials considering the algorithms were correct 94.5 per cent of the time, which is equal to retina specialists doctors who were using extra notes along with the OCT scans.
                                       Deepmind & Google joined force in 2014 to accelerate AI research in healthcare and built medical assistant application for the National Health Scheme.. The significant AI work done by Deepmind in diagnosing eye diseases as effectively as the world’s top doctors, to in saving 30% of the energy used to keep data centers cool & to predict the complex 3D shapes of proteins is disruptive in field of Artificial General Intelligence (AGI).
The application called Streams is a mobile phone app that aims to provide timely diagnoses using AI so that right nurse or doctor get to the right patient in time and save the lilfe of patient who would have died otherwise. Each year, many thousands of patients in UK hospitals die from conditions like sepsis and acute kidney injury (AKI), because the warning signs aren't picked up and acted on in time

Streams mobile medical assistant for clinicians has been in use at the Royal Free London NHS Foundation Trust since early 2017. The app uses the existing national AKI algorithm to flag patient deterioration, supports the review of medical information at the bedside, and enables instant communication between clinical teams. Shortly after rolling out at the Royal Free, clinicians said that Streams was saving them up to two hours a day. We also heard about patients whose treatment was escalated thanks to the timely alert by the app. Statistics show that the app saved clinicians time, improved care and reduced the number of AKI cases being missed at the hospital.


The above figure shows how the automated process in the medical app saves time and connects doctor directly to the patient with serious condition.

There has been controversy around Google taking Over NHS data when DeepMind was taken over by Google in early 2017. DeepMind, which is now owned by Google used to operate the NHS app independently until 2017. DeepMind justified the decision explaining how Google would allow the app to scale in a way that would not be possible by itself.  Earlier in 2017 the Streams app attracted controversy after the UK’s data watchdog found that the NHS had illegally handed 1.6 million patient records to DeepMind as part of a trials. DeepMind subsequently made assurances that the medical data “will never be linked or associated with Google accounts, products or services”, and that all patient data will remain under the strict control of its NHS partners. As long as DeepMind does not share or link patient data with Google it will be major achievement for NHS in providing smarter health monitoring for AKI and many more diseases. 

Link to NHS Website-  link

No comments:

Post a Comment

Understanding Generative AI and Generative AI Platform leaders

We are hearing a lot about power of Generative AI. Generative AI is a vertical of AI that  holds the power to #Create content, artwork, code...