Machine learning can be used to predict which patients require emergency admission

November 20, 2018, University of Oxford
Credit: CC0 Public Domain

Machine learning—a field of artificial intelligence that uses statistical techniques to enable computer systems to 'learn' from data—can be used to analyse electronic health records and predict the risk of emergency hospital admissions, a new study from The George Institute for Global Health at the University of Oxford has found.

The research, published in the journal PLOS Medicine, suggests that using these techniques could help health practitioners accurately monitor the risks faced by patients and put in place measures to avoid unplanned admissions, which are a major source of healthcare spending.

"There were over 5.9 million recorded emergency hospital admissions in the UK in 2017, and a large proportion of them were avoidable," said Fatemeh Rahimian, former data scientist at The George Institute UK, who led the research.

"We wanted to provide a tool that would enable healthcare workers to accurately monitor the risks faced by their patients, and as a result make better decisions around patient screening and proactive care that could help reduce the burden of emergency admissions."

The study, of 4.6 million from 1985 to 2015, was conducted using linked from the UK's Clinical Practice Research Datalink. A wide range of factors was taken into account, including age, sex, ethnicity, , , lifestyle factors, comorbidities, medication and , as well as the time since first diagnosis, last use of the health system and latest laboratory tests.

Using more variables combined with information about their timing, machine learning models were found to provide a more robust prediction of the risk of emergency hospital admission than any models used previously.

"Our findings show that with large datasets which contain rich information about individuals, machine learning models outperform one of the best conventional statistical models," Rahimian said. "We think this is because machine learning models automatically capture and 'learn' from interactions between the data that we were not previously aware of."

Whether machine learning models can lead to similarly strong improvements in risk prediction in other areas of medicine requires further research.

Explore further: Big data model improves prediction of key hospital outcome

More information: PLOS Medicine (2018). journals.plos.org/plosmedicine … journal.pmed.1002695

Related Stories

Big data model improves prediction of key hospital outcome

February 18, 2016
More than half of hospital deaths in the United States are related to severe infections, or sepsis. Yale researchers developed a prediction model, drawing on "big data" about local patients and using machine-learning methods, ...

Artificial intelligence may fall short when analyzing data across multiple health systems

November 6, 2018
Artificial intelligence (AI) tools trained to detect pneumonia on chest X-rays suffered significant decreases in performance when tested on data from outside health systems, according to a study conducted at the Icahn School ...

Artificial intelligence may put private data at risk

August 3, 2018
Machine learning – a form of artificial intelligence in which computers use data to learn on their own – is rapidly growing and poised to transform the world. But current models are vulnerable to privacy leaks and other ...

EMR data can predict myopia development

November 9, 2018
(HealthDay)—Big data and machine learning approaches can improve prediction of myopia in Chinese children, according to a study published online Nov. 6 in PLOS Medicine.

Adults with intellectual disabilities are at high risk of preventable emergency admissions

September 12, 2017
Adults with intellectual disabilities have more than twice as many emergency hospital admissions and five times more preventable emergency admissions than other comparable individuals.

AI beats doctors at predicting heart disease deaths

September 4, 2018
A model developed using artificial intelligence (AI) is better at predicting risk of death in patients with heart disease than models designed by medical experts, a new study from the Francis Crick Institute shows.

Recommended for you

Female biology – two X chromosomes and ovaries – extends life and protects mice from aging

December 18, 2018
Around the world, women outlive men. This is true in sickness and in health, in war and in peace, even during severe epidemics and famine. In most animal species, females live longer than males.

Get a warrant: Researchers demand better DNA protections

December 18, 2018
New laws are required to control access to medical genetic data by law enforcement agencies, an analysis by University of Queensland researchers has found.

Wound care revolution: Put away your rulers and reach for your phone

December 18, 2018
Monitoring a wound is critical, especially in diabetic patients, whose lack of sensation due to nerve damage can lead to infection of a lesion and, ultimately, amputation. Clinicians and healthcare professionals at the McGill ...

Using light to stop itch

December 17, 2018
Itch is easily one of the most annoying sensations. For chronic skin diseases like eczema, it's a major symptom. Although it gives temporary relief, scratching only makes things worse because it can cause skin damage, additional ...

Law professor suggests a way to validate and integrate deep learning medical systems

December 13, 2018
University of Michigan professor W. Nicholson Price, who also has affiliations with Harvard Law School and the University of Copenhagen Faculty of Law, suggests in a Focus piece published in Science Translational Medicine, ...

Exercise-induced hormone irisin triggers bone remodeling in mice

December 13, 2018
Exercise has been touted to build bone mass, but exactly how it actually accomplishes this is a matter of debate. Now, researchers show that an exercise-induced hormone activates cells that are critical for bone remodeling ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.