Machine learning helps predict frailty
A Flinders University study has found machine learning methods are well suited for predicting pre-frailty.
A Flinders University study has found both machine learning methods are well suited for predicting pre-frailty and a range of useful factors to include in targeted health assessments to identify pre-frailty in middle aged and older adults.
The researchers say machine learning could be the key component in developing effective early screening systems identifying frailty in these cohorts.
The research team undertook a comprehensive analysis of health assessment data for 656 adults in South Australia and evaluated machine learning’s accuracy in predicting pre-frailty.
The machine learning models – based on data collected using validated frailty assessment tools – identified higher body mass index, lower muscle mass, poorer grip strength and balance, higher levels of distress, poor quality sleep, shortness of breath and incontinence, as medical issues linked with being classified as pre-frail.
Lead author Dr Shelda Sajeev – from Flinders Digital Health Research Centre and the Artificial Intelligence Research Centre at Torrens University – said the machine learning analysis identified key health assessment measures that contribute to the shift between not frail and pre-frail.
“The use of machine learning has identified different categorisations between not frail and pre-frail participants than statistical analysis – which suggest machine-learning approaches can expose more subtle casual issues that could not have been identified with standard statistical analysis,” Dr Sajeev said in a statement.
In Australia, between 35 per cent and 45 per cent of 40 to 75-year-olds are pre-frail. Frailty results from cumulative exposures, with many of the precursors manifesting before middle age. There is an opportunity to intervene to reduce adverse outcomes during the pre-frailty period, but early indicators of a transition into frailty are often detected too late, the experts say.
Pre-frailty is a transitional period where individuals often do not know they are accumulating deficits, hence the need for screening to identify opportunities to reverse small deficits amenable to change,” said co-author Dr Stephanie Champion, a postdoctoral research fellow at Flinders University.
“It’s important we develop effective systems for identifying pre-frailty because the syndrome is linked with impairments to multiple physiological systems and results in decreased resilience, increased vulnerability to stressors, poorer health outcomes and increased morbidity and mortality.”
The article Machine learning models for identifying pre-frailty in community dwelling older adults (2022) is published in BMC Geriatrics (Springer Nature).
Follow Community Care Review on Facebook, Twitter and LinkedIn and sign up to our newsletter.
