Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Development of AI-supported scheduling for healthcare professionals

Reference number
Coordinator HELSINGBORGS KOMMUN - Vård- och omsorgsförvaltningen
Funding from Vinnova SEK 240 000
Project duration September 2020 - December 2020
Status Completed
Venture Innovations to mitigate the crisis
Call Finding new ways in the time of a crisis

Important results from the project

The aim of the project was to develop an AI-driven model capable of creatíng at least as good schedules as a human, but based on more aspects, faster and regardless of the time of day. A model that can work tirelessly during all hours of the day to optimize staff schedules, primarily based on operations and continuity figures - but also with the goal of generating schedules that can take into account individual life situations and thereby reduce stress and increase employees´ quality of life.

Expected long term effects

In addition to the explicit purpose of developing a working AI model that, based on real values, can generate sharp schemes in less time than a human, several very interesting observations and conclusions were made. Completely new and innovative working methods for working with scheduling have been identified. Reeinvent continues with the model as a concept "Just Schedule". In 2021, there will be a sharp pilot of AI in the city´s common system for scheduling. The need for AI-driven scheduling has been validated and innovation work has taken place in practice in the business.

Approach and implementation

The project was carried out during the autumn-winter 2020, with the nursing home Murteglet in Helsingborg as test bed. The unit manager and responsible for scheduling was part of the project group and employees at the accommodation were interviewed. We placed great emphasis on interviewing the staff at the accommodation and understanding the scheduling before the development began. This made programming more efficient and enabled two iterations of user testing. In addition, several insights were gained about the work with the schedule during the interviews.

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

Last updated 27 January 2021

Reference number 2020-03256