AI Hub Central Finland (AIHub)
Main funder
Funder's project number: A75000
Funds granted by main funder (€)
- 423 995,00
Funding program
Project timetable
Project start date: 01/06/2019
Project end date: 30/06/2022
Summary
The aim of the project is to create a regional AI hub that promotes intelligent utilization of SOTE data in Central Finland. The regional AI-Hubs of Central Finland and Northern Savo interact with each other, which aims to the creation of larger and more diverse data sets. This enables the development of more accurate and reliable artificial intelligence models, as well as the generation of new knowledge for the prevention and treatment of diseases as well as optimization of the cost effects. To achieve the results, Central Finland's AI HUB works closely with regional organizations (Central Hospitals, Biobanks, various SOTE actors and companies).
The goal is to produce new information on how different SOTE actors can make artificial intelligence solutions at provincial, municipal and individual levels and develop computational decision support models that enable the assessment of the effectiveness of customer-specific interventions and decisions. In the main focus are the identification of customer risks and segmentation of customers, identification of care episodes of different customer groups, creation of different intervention scenarios, and functional and financial evaluation of different decision options. In addition, it is explored how artificial intelligence-based techniques can enhance the analysis of clinical data and biobank data, how these data sources can be supplemented with other open or self-collected data, and their potential for developing artificial intelligence applications. The project focuses on promising application areas identified in the previous research, such as enhancing treatment processes, cancer treatment, and prevention of osteoarthritis. The project activates companies in the area to utilize artificial intelligence and computational methods in their own Sote business processes and products. The starting point for project planning has been the needs of the Sote organizer, the corporate field and the business of the province.
The project will result in new computational decision support models, information on the potential of clinical data and biobank data in the development of artificial intelligence methods, new operating models for utilizing different data sources and, where possible, open databases for the exploitation of companies and researchers.
The goal is to produce new information on how different SOTE actors can make artificial intelligence solutions at provincial, municipal and individual levels and develop computational decision support models that enable the assessment of the effectiveness of customer-specific interventions and decisions. In the main focus are the identification of customer risks and segmentation of customers, identification of care episodes of different customer groups, creation of different intervention scenarios, and functional and financial evaluation of different decision options. In addition, it is explored how artificial intelligence-based techniques can enhance the analysis of clinical data and biobank data, how these data sources can be supplemented with other open or self-collected data, and their potential for developing artificial intelligence applications. The project focuses on promising application areas identified in the previous research, such as enhancing treatment processes, cancer treatment, and prevention of osteoarthritis. The project activates companies in the area to utilize artificial intelligence and computational methods in their own Sote business processes and products. The starting point for project planning has been the needs of the Sote organizer, the corporate field and the business of the province.
The project will result in new computational decision support models, information on the potential of clinical data and biobank data in the development of artificial intelligence methods, new operating models for utilizing different data sources and, where possible, open databases for the exploitation of companies and researchers.
Principal Investigator
Other persons related to this project (JYU)
Primary responsible unit
Related publications and other outputs
- Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer (2023) Petäinen, Liisa; et al.; A1; OA
- H&E Multi-Laboratory Staining Variance Exploration with Machine Learning (2022) Prezja, Fabi; et al.; A1; OA
- Developing and testing a discrete event simulation model to evaluate budget impacts of diabetes prevention programs (2020) Kaasalainen, Karoliina; et al.; A1; OA