Mobile app speeds up review and treatment of acute kidney injury

Evaluation led by UCL researchers has found a new mobile app is enabling doctors to detect urgent cases of acute kidney injury (AKI) significantly more quickly than existing systems, helping speed up specialist review and treatment.

That is one of the key findings of an evaluation of the ‘Streams’ app – a secure alerting tool - which has been developed by DeepMind Health in collaboration with clinicians at the Royal Free London NHS Foundation Trust (RFL) to help identify patients at risk of AKI.

The evaluation, led by UCL Applied Health Research and published in Nature Digital Medicine and the Journal of Medical Internet Research, shows the app improved the quality of care for patients by speeding up detection and preventing missed cases.

Using Streams, clinicians were able to respond to urgent AKI cases in 14 minutes or less - a process which, using existing systems, might otherwise have taken many hours.

It also concluded that the app reduced the cost of care to the NHS – from £11,772 to £9,761 for hospital admission for a patient with AKI.

Lead author, Professor Rosalind Raine (UCL Applied Health Research) said: “At a time when digital technology is being enthusiastically embraced by policy makers, it’s vital to demonstrate the importance of robust but timely evaluations which examine the extent to which desired benefits are achieved for patients, the various impacts on the NHS, as well as unforeseen consequences.

“We’ve shown that it’s feasible to undertake such evaluations and argue that all technology should be subjected to scrutiny, rather than rolling out untested innovations.”

Acute Kidney Injury – known as a silent killer because it can often be diagnosed late and is often hard to predict – contributes to nearly 20% of all hospital admissions, accounts for 100,000 deaths every year in the UK, and costs the NHS £1.2 billion annually.

Clinicians at the RFL worked closely with experts at DeepMind Health who developed Streams with the aim of improving outcomes for patients by getting the right data to the right clinician at the right time. Like breaking news alerts on a mobile phone, the technology notifies nurses and doctors immediately when test results show a patient is at risk of becoming seriously ill with AKI, and provides information they need to take action. 

Clinicians face real challenges when it comes to detecting conditions like AKI – patients deteriorate rapidly and, without the app, it could be hours before this was picked up due to the limitations of current NHS technology and the reliance on manual observations and intuition. Approximately one in three deaths from AKI may be preventable if clinicians are able to intervene earlier and more effectively.

The service evaluation and qualitative study compared data from four months after implementation of Streams to data from an eight month period prior to the implementation of Streams. Data was also included from a comparator site at RFL that did not implement Streams. Over the cumulative 12 months, the study evaluated 11,840 AKI alerts.

It found:

• Recognition of AKI improved from 87.6% to 96.7 % for emergency cases
• The average time from blood test results being available suggesting AKI to an in-application case review by a specialist was 11.5 minutes for emergency patients with AKI and 14 minutes for admitted patients. Previously it was not possible for specialists to review AKI cases arising across the hospital in real-time and it could have taken several hours to identify
• Key treatment was delivered faster
• Healthcare costs reduced by just over £2,000 for AKI patients treated (from £11,772 to £9,761)
• For emergency patients there were significant improvements in outcome trend in renal recovery and admissions to critical care and the kidney unit after AKI. There was also a significant reduction in the global hospital cardiac arrest rate.  These improvements at the implementation site were not, however, statistically different from the parallel improvements seen at the comparator site.

Dr Chris Laing, consultant nephrologist and Honorary Lecturer at UCL Department of Renal Medicine, who initiated the Streams project and co-led the evaluation said: “AKI is common, harmful, costly and may present across multiple clinical settings. It is often an early sign that a patient is becoming gravely Ill.

“Thanks to Streams we are able to monitor the kidney function of patients through real-time analysis of blood tests 24/7. If a potential change in kidney function in a patient is detected, at any time or anywhere at the Royal Free Hospital, a specialist will be notified and the case will be reviewed, in-application, in a matter of minutes, with follow-up bedside assessment as required.”

Mary Emerson, lead nurse specialist for the RFL patient at risk and resuscitation team, said: “The Streams app has made a huge difference to clinicians’ ability to respond rapidly to patients who are developing acute kidney injury. This means we can deliver treatment more quickly, and also identify deteriorating patients much earlier. The mobile technology is easy to use and fits with the way healthcare is delivered today. I’m excited about the possibilities this approach to alerting might have for other conditions and clinical teams.”

Dr Dominic King, lead at DeepMind Health, said: “We’re proud to see these findings demonstrate how modern digital technologies can support nurses and doctors in delivering faster, better care at the same time as delivering cost savings for the hospital. We’re excited to now explore how earlier warnings of patient deterioration could improve outcomes for more patients at the Royal Free London.”

Links

• Professor Rosalind Raine
• Evaluation paper in Journal for Medical Internet Research
• Evaluation paper in Nature Digital Medicine
• UCL Applied Health Research
• UCL Department of Renal Medicine
• Royal Free London NHS Foundation Trust
• DeepMind

Image

• Credit: Royal Free London

Source

• Royal Free London

Media contact

Henry Killworth

Tel: +44 (0) 207 6795296

E: h.killworth [at] ucl.ac.uk