AI-based smartphone app can predict user’s health risks

Researchers have developed AI based data analysis methods used in a smartphone app which can estimate its users’ health risks…


VTT Technical Research Centre of Finland has developed artificial intelligence (AI)-based data analysis methods used in a smartphone application of Odum Ltd. The application can estimate its users’ health risks and, if necessary, guide them towards a healthier lifestyle.

“Based on an algorithm developed by VTT, we can predict the risk of illness-related absence from work among members of the working population over the next 12 months, with an up to 80 percent sensitivity,” says VTT’s Mark van Gils, the scientific coordinator of the project.

“This is a good example of how we can find new information insights that are concretely valuable to both citizens and health care professionals by analysing large and diverse data masses.”

The application also guides individuals at risk to complete an electronic health exam and take the initiative in promoting their own health.

Smartphone data

During the project Odum and VTT examined health data collected from 18-64 year-olds over the course of several years. The project received health data from a total of 120,000 working individuals.

“Health care costs are growing at an alarming pace and health problems are not being addressed early enough,” says Jukka Suovanen, CEO of Odum. “Our aim is to decrease illness-related absences by 30 percent among application users and add 10 healthy years to their lives.”

The most cost-efficient way to improve quality of life and decrease health care costs for both individuals and society is to promote the health of individuals and encourage them to take initiative in reducing their health risks.

VTT is one of the leading research and technology companies in Europe. We help our clients develop new technologies and service concepts in the areas of Digital Health, Wearable technologies and Diagnostics – supporting their growth with top-level research and science-based results.

Leave a Reply

Your email address will not be published. Required fields are marked *