AI spots risk years ahead
A broken hip can change an older person’s life in seconds, taking away mobility, independence and, in some cases, survival. Now researchers in Sweden say information already sitting in health records could help spot danger before the fall happens.
A broken hip can completely alter an older individual's life, stripping away mobility, independence, and potentially even life itself. Swedish researchers believe that existing health records could be harnessed to anticipate such risks. By examining data from over 3.5 million individuals aged 50 and older, spanning up to ten years, scientists identified 142,327 people who had experienced a hip fracture during this period.
Utilising this wealth of information, the team created an artificial intelligence system named FRACTURE-ML. This tool scrutinises routinely gathered data, including ailments, medications, prior treatments, and basic social information, to pinpoint those most susceptible to a hip fracture. Unlike most current assessments, FRACTURE-ML does not necessitate in-person consultations, weight checks, or inquiries regarding lifestyle choices.
In trials, FRACTURE-ML detected nearly seven times as many individuals at risk of a hip fracture within two years compared to the screening methods currently employed in Sweden. Particularly noteworthy is a streamlined version of the tool that uses just 35 data points, which still performed almost as effectively. Researchers are confident that this innovation could enable preventive care to be provided to the most vulnerable individuals sooner.
However, the tool does not incorporate smoking or alcohol consumption, and the researchers stress that further trials in different countries are needed before its widespread implementation.
Written by urgent.news from Daily Star BD Health's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
