Communications of the ACM
Neural Network for Elderly Care Could Save Millions
Researchers at Finland's Aalto University, the University of Helsinki, the Finnish Centre for Artificial Intelligence, and the Finnish Institute for Health and Welfare developed model to predict how frequently elderly people will seek treatment from a hea
Credit: Matti Ahlgren/Aalto University
Researchers at Finland's Aalto University, the University of Helsinki, the Finnish Centre for Artificial Intelligence, and the Finnish Institute for Health and Welfare (THL) have developed a risk adjustment model to predict how frequently elderly people will seek treatment from a healthcare center or hospital.
The researchers trained the model using data from THL's Register of Primary Health Care Visits, consisting of outpatient visit information for every Finnish citizen aged 65 or older. They found that the model worked better than count-based models even when it utilized just one-tenth of all available data.
"Our goal is not to put the model developed in this research into practice as such, but to integrate features of deep learning models to existing models, combining the best sides of both," said Aalto's Pekka Marttinen.
"In the future, the goal is to make use of these models to support decision-making and allocate funds in a more reasonable way." Aalto's Yogesh Kumar added, "Having an accurate model has the potential to save several millions of dollars."
From Aalto University (Finland)
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found