Youth care faces complex challenges. How can we get a grip on the diversity of services and products in this sector? An innovative chain analysis technique, based on machine learning, should provide this and improve the quality and efficiency of youth care.
For the past six months, the national Data Science Expertise Group, part of VNG's Data and Society Knowledge Network, has been working on a new methodology to make the complexity in youth care manageable. The new chain analysis technique uses machine learning (algorithms) to make in-depth analyses of client journeys, interventions, waiting times and care outflows. As a result, care pathways can be better understood and compared.
The method maps the steps a person has taken in youth care, with less manual work and unbiased data analysis. The client's perspective is central so that appropriate and correct care can be provided.
Youth care is a labyrinth of services, pathways and care pathways in which young people must move. Policymakers often have only a fragmented view of the chain, making it difficult to determine the most effective interventions. The new technology helps policymakers and practice professionals get accurate and up-to-date information needed to provide effective care.
The effectiveness of this technique, which has yet to be put into practice, is due to the cooperation between municipalities, regions and the UNG in the national expert group.
This post was written based on an interview with Tjark van Merwe, data specialist at Kennispunt Twente, the partnership and research agency of 14 Twente municipalities and SamenTwente. Read the full article 'Getting a better picture of youth care with machine learning' on the website of Knowledge Network Data and Society.
