PolyU’s SWIM system provides analytics for rehabilitation from work-related injuries
A research team from the Department of Rehabilitation Sciences and the Department of Computing at PolyU has developed the “Smart Work Injury Management System” (SWIM), which can accurately predict with AI and big data the length of sick leave and return-to-work trajectory in the cases of injuries at work.
Dr Andy Cheng, Associate Professor of the Department of Rehabilitation Sciences, said in a group media interview that they provided the system with more than 90,000 cases collected from 68 insurance companies for building up analytic models through machine-learning.
With basic information such as age, job nature, salary, injured area and cause of injury, SWIM is able to predict the severity of a case, what treatment should be taken, the possibility of resumption of work, the amount of insurance claim costs, and more.
SWIM’s prediction accuracy reaches 70% and 60% in assessing the disability level and the days of sick leave respectively, both outperforming estimations conducted by humans.
Dr Cheng said SWIM would be a useful tool for stakeholders like employers, injured workers and insurance companies to acquire more comprehensive information so as to develop better rehabilitation plans and reduce the chances of work-related injuries.
Six insurance companies have already expressed their interest in SWIM for a 6-month trial run that will commence at the earliest by March. It is expected that SWIM will be put to use by the insurance and healthcare industries next year.
Here is some of the coverage of the media interview. Check it out!
