AI for turning quality registers into personalised decision support systems in health care

Reference number 2017-01555
Coordinator Mälardalens högskola - Akademin för innovation, design och teknik, Västerås
Funding from Vinnova SEK 1 336 000
Project duration April 2017 - November 2018
Status Completed
Venture Digital health

Purpose and goal

The project has developed a decision support system prototype based on AI which uses a quality register to improve and individualize patientcare. By combining methods and techniques from AI and Informatics a decision support system created to help doctors/clinicians to improve care at an individual level. We have great potential to individualize treatments and measures based on the national surveillance program and quality register for people with cerebral palsy (CPUP) which has a coverage of >95% and includes longitudinal covering more than 4500 people.

Expected results and effects

By using the suggested hybrid system which uses an existing quality register and building on a combination of methods and techniques from AI statistics and Informatics, a decision support system created which helps doctors and other healthcare professionals in improving care and rehabilitation at an individual level. We see this project as a useful knowledge and experience source for how other quality registers can be used in the future for clinical decision making, adapted treatments and individualized care.

Planned approach and implementation

We have developed a prototype in conjunction with caregivers / stakeholders and clinical experts as a ‘Proof of Concept’. Development was carried out by leading experts within the area; Gunnar Hägglund Professor of Pediatric Orthopedics and register holder for CPUP, associate professor Elisabet Rodby Bousquet, National coordinator for CPUP and researcher in cerebral palsy and Peter Funk, Professor of Artificial Intelligence & Computer Science.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.