Kidney disease detected in minutes by application

A mobile phone application has accelerated the detection of life-threatening kidney disease in hospitalized patients.

Staff describe the technology as a "potential lifeline", providing diagnoses in minutes instead of hours.

Acute kidney injury is caused by serious health problems, including sepsis, and affects one in five admitted to the hospital.

The disease is more common in elderly patients and, if left untreated, may affect other organs.

In the UK, it causes about 100,000 deaths each year.

During a trial at the Royal Free Hospital in London, doctors and nurses received warnings via a mobile phone application in 14 minutes on average, when patients' blood tests revealed their condition.

Normally it would have taken several hours.

The new alert system, called Streams, developed by Royal Free with DeepMind technology company, sends the results directly to front-line clinicians in the form of easy-to-read graphs and results.

One of the blood tests is looking for high levels of a residual product called creatinine, which is normally filtered through the kidneys.

Information on other blood markers that can help treat patients are also made available to specialists quickly via the application.

DeepMind belongs to Alphabet and shares the same parent company as Google.

Hospital managers said the cost of treatment had been reduced.

Mary Emerson, a senior nurse at Royal Free, told the BBC that the system had made a big difference to her work.

"It's a huge change to be able to receive alerts about patients anywhere in the hospital," she said.

"Healthcare is mobile and real-time, and it's the first device that has allowed me to see mobile results in real-time."

She said it was the first system that "fits our way of working".

What's an acute kidney injury?

• This is when the kidneys stop working properly, normally as a result of complications from another serious illness.
• This can result in anything, from a minor loss of kidney function to complete kidney failure
• This type of kidney injury must be detected and treated quickly
• Otherwise, abnormal levels of salt and chemicals can accumulate in the body, making people very sick

Source: NHS UK – Acute kidney injury

University College London has evaluated data from about 12,000 alerts on acute kidney injury using the new system.

The findings, published in the journal Nature Digital Medicine, showed that patients' recovery rate was undergoing "no radical change", but that there had been a "significant improvement" in the rapid recognition of acute kidney injury. .

The report's authors called for further evaluation of the system in several hospitals.

They note that old technologies, such as pagers, are commonly used in the NHS to share this kind of important data.

Sally Hamour, kidney specialist at Royal Free, said the project "could save lives".

"We need to collect a lot more information about this technology and we need to look at it for a longer period of time," she said.

"But it is certain that some patients are very sick, that the information reaches the right team very quickly and that we can then put in place measures to try to protect it safely and reverse the consequences on its renal function. . "

One step forward

In 2017, the Information Commission (ICO) criticized the Royal Free for its relationship with DeepMind, claiming that it had not done enough to protect the patients' data.

The ICO has now given the hospital an irreproachable state of health after officials have committed to addressing data processing deficiencies.

The publication of the new research was planned to coincide with a report on another research involving DeepMind and published in the journal Nature.

The records of more than 700,000 patients from the US Department of Veterans Affairs have been badyzed retrospectively by an artificial intelligence system, which goes even further than the application.

Using hundreds of thousands of data, including blood tests and heart rate, it was possible to determine if a patient would develop an acute kidney injury up to 48 hours before his diagnosis.

The company argued that it was "a significant change in the way medicine is practiced".