Can computers read the signs of frailty and falls in older adults’ records? A review
We reviewed how language technology has been used to find geriatric syndromes in the free text of health records, and what is still hard.
The question
Geriatric syndromes are complex conditions in older adults, such as falls, delirium and frailty, that often need several kinds of professionals to assess. Much of what clinicians know about them is written as free text in health records, not in tidy tick boxes.
What we did
We carried out a systematic review, which means searching and examining the research in a structured way, of how natural language processing has been used to find and track geriatric syndromes in that text. We looked at what it has been used for, what methods were used, and how well they worked.
What we found
The review maps the applications and methods, and sets out the challenges and limits that stand in the way. It also points to where future work is most needed.
Why it matters
If computers can reliably read these notes, services could spot older people who are slipping towards problems sooner. This review is a map for the researchers trying to build that.