Garry Knight/Flickr

New test predicts a person's risk of dementia using family doctor records

But would you want to know?

PETER DOCKRILL
22 JAN 2016
 

An algorithm programmed by researchers in the UK is able to estimate people's chances of developing dementia with up to 85 percent accuracy, based on pooled health data collected from around 6 percent of Britain's GPs.

The so-called Dementia Risk Score uses anonymised patient data collected from 377 medical practices in the UK to predict an individual's future risk of developing the disease within the next five years.

 

"The score could be especially useful for identifying people at a very low risk of dementia (as recorded by their GP)," said lead researcher Kate Walters from University College London. "This could help general practitioners working with people who are anxious about developing dementia."

To develop the test, the researchers collected the records of 930,395 anonymous patients who showed no signs of dementia, cognitive impairment, or memory problems.

They then analysed the data, sourced from The Health Improvement Network (THIN) database, examining four variables as possible predictors of dementia risk. These included socio-demographic measures, health and lifestyle measurements, medical diagnoses, and the use of prescription medication.

Over five years of follow-up visits by the patients to their GPs, the researchers observed these variables to monitor their association with newly recorded dementia diagnoses.

Putting what they learned into the algorithm, the researchers tested their Dementia Risk Score evaluator against a new group of 264,224 patients, which they assessed in two separate subgroups based on age – those aged 60 to 79 and those aged 80 to 95.

They found that the test performs well in predicting risk for people aged 60 to 79, offering 85 percent accuracy. However it's not as effective in its estimates for people aged 80 to 95 – years in which the risk of dementia increases sharply, skewing the algorithm.

For those aged younger than 80, the test could offer peace of mind for many patients – provided their score indicates their chances of developing dementia are indeed low.

"Our algorithm can be added to clinical software systems and a practice could, for example, run this risk model on all eligible people and offer those at risk more detailed testing or specific preventive management," Walters told Sarah Knapton at The Telegraph.

But in light of the absence of established medical treatments for dementia, some have questioned the value of knowing one's likelihood of developing the disease.

"Today's dementia risk score is not the first to be published, but it is the first one that doesn't require any additional data to be collected from patients. This is a huge plus," Clare Walton of the Alzheimer's Society told The Telegraph.

"But without definite ways to prevent dementia or very accurate prediction methods, would you want to know? If I was approaching my later years, I'm not sure I would… With the fear surrounding dementia and the current gaps in our understanding, risk scores like this need to be used with caution until they can be improved further."

On that front, the researchers themselves are in agreement. "Before this score is widely used we would recommend that it is independently tested in further populations of people," said Walters, "and that the ethical implications of using it in practice are considered."

The findings are reported in BMC Medicine (site down at time of writing).

More From ScienceAlert