Science 2 min read

New DeepMind AI Detects Acute Kidney Injury in Advance

Researchers at DeepMind Health developed an AI system that could help doctors detect acute kidney injury 48 hours before the symptoms occur.

Image courtesy of Shutterstuck

Image courtesy of Shutterstuck

Aside from developing AI models that can defeat humans in different online games, DeepMind is also working on other projects that could benefit the health care industry. The U.K.-based, Google-owned artificial intelligence company has just designed an AI software that can detect acute kidney injury (AKI) in advance.

DeepMind’s latest technology is deemed as its most significant breakthrough in health care five years after being acquired by Google. The new system can reportedly determine signs of potentially fatal kidney injuries 48 hours before doctors can recognize the symptoms.

Despite advancement in current medical equipment and procedures, doctors are still having difficulty preventing AKI because of its varying causes. Joseph Vassalotti, the chief medical officer at the National Kidney Foundation, told Scientific American:

“It typically occurs during major surgery or complications to surgery and from sepsis. Some medications can cause acute kidney injury due to side effects or immune response.”

However, the arrival of DeepMind’s latest AI tech could help medical experts detect and prevent kidney injuries, saving more lives in the process.

Detecting Acute Kidney Injury

In their paper published in the journal Nature, the DeepMind researchers described how their AI system could detect an acute kidney injury.

First, they trained their algorithm using 703,782 anonymized electronic health records of adult patients from the U.S. Department of Veterans Affairs. The data included over 600,000 different health indicators the AI model could use like blood-test results, prescriptions, vital signs, and past procedures.

The researchers defined which of the factors were useful and which ones were potential danger signs. Then, they used deep learning to filter the right signals in the data.

The team was able to distinguish 4,000 relevant indicators that could potentially help predict AKI. Using these indicators, DeepMind’s AI was able to calculate a patient’s AKI risk even before the renal damage occurs. Dominic King, DeepMind Health’s product lead, said:

 “Clinicians being able to move from reactive to the ability to predict [AKI] two days before—that’s due to the richness of the data.”

The researchers noted that the extra time provided by their AI system could be used by doctors to prevent or alleviate any harm to the patient. Furthermore, it would allow medical experts to address all potential complications that might arise from the loss of kidney function earlier.

Read More: Google Disbands Advisory Board For DeepMind Health

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Rechelle Ann Fuertes know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Rechelle Ann Fuertes

Rechelle is an SEO content producer, technical writer, researcher, social media manager, and visual artist. She enjoys traveling and spending time anywhere near the sea with family and friends.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.