About CAISR Health

CAISR Health is a research profile within information driven care at Halmstad University, where research on the development of AI tools meet research on how these tools can be implemented in healthcare.

CAISR Health is a cross disciplinary research profile, gathering research from two Schools at Halmstad University. The research is carried out in close collaboration with Region Halland and Swedish companies. The abbreviation CAISR stands for Center for Applied Intelligent Systems Research which is a research center at Halmstad University that is strongly connected to the profile.

Improving healthcare with AI

The availability of data is changing rapidly in healthcare. Descriptive data analytics and machine learning technologies will have a huge impact on healthcare operations in a near future. In Sweden, Region Halland was first to act on this and gather and successfully synchronize all their healthcare data and creating an organisation for using this data to improve healthcare operations. This has contributed to excellent results – over the last 4-5 years the healthcare system of Region Halland has shown a remarkable increase in efficiency while maintaining top level quality and access to care. Yet, there are challenges, and a key challenge is understanding implementation; what are best practices for creating impact with information-driven healthcare, to get solutions into the system and for changing how people work? There are also opportunities. The development with information driven care opens international business opportunities. Digital services can be developed for an international market, not just the national, and skills and methods can be exported (and imported). Global business investments in healthcare and IT are therefore growing quickly.

Illustration from data to insight

Information driven care: by learning from the conclusions of data analysis, change can be achieved.

Objective of CAISR Health

CAISR Health will focus on understanding the information driven healthcare system and build up knowledge about the whole chain – from formulating and prioritising questions, to developing algorithms, collecting data and enable engagement, explainability and implementation. To do this, CAISR Health will work along four dimensions:

  • Research
  • Data infrastructure
  • Industrial cooperation and innovation
  • Education and increased competence

CAISR Health will aid Region Halland in maintaining a leading position in Sweden, and our industry partners to be forerunners in information driven care infrastructure.

Subject areas

The research profile has three subject areas:

1. Patient trajectories and XAI

A key prerequisite for precision healthcare is patient and disease characterisation, where patient trajectories can play an important role. Patient trajectories are a means of illustrating the temporal disease progression and correlations. These models often suffer from inscrutability, which prevents pervasiveness of AI applications in healthcare. Therefore, in subject area 1, we will address the patient trajectory and Explainable AI (XAI). Most of the previous research done in patient trajectories are neglecting the data fusion part as well as broadening the scope of the trajectories into other relevant available sources (e.g. self-care which is covered in subject area 3). We will enrich the concept of patient trajectory by exploring and injecting more valuable sources around the patient and disease. XAI can facilitate the process of trust and other issues regarding the "black box" aspects of AI. We aim at leveraging on existing XAI models and scale up them by taking into account the patient trajectory and human-in-the-loop approach involved from the early design steps to the final evaluation phases (covered in subject area 2), which is more or less ignored in general XAI as well as healthcare related XAI methods.

2. Healthcare transformation

There is an increasing awareness in healthcare of the importance of implementation strategies to promote uptake of research and development into routine clinical, organisational, or policy contexts. Although advanced analytics of healthcare data have the potential to transform healthcare through actionable data driven insights, the implementation of AI in healthcare practice is hampered by the lack of implementation strategies that are tailored to the specific settings and contexts for its application. There is a need to close the gap between how work is imagined, and what is actually taking place. This means providing more rigorous and empirical implementation studies of AI in healthcare, underpinning strong theory and real-world understanding. This applies to both the development of patient trajectories based on analysis of healthcare data (covered in subject area 1) and the involvement of relevant stakeholders in the development of new healthcare solutions (covered in subject area 3). Our overall objective is to build an internationally recognised and sustainable AI implementation learning environment and to become leading in the area of AI implementation in healthcare and well known for the quality and relevance of the AI implementation research.

Healthcare improvement

3. Information driven participatory care

The aim of information driven participatory care is to integrate caregivers, patients and technology into efficient, high quality healthcare experiences by creating opportunities to leverage the expertise of each stakeholder in a healthcare journey. While healthcare has been changing, the lack of integration with the existing healthcare system and the paternalistic healthcare model that is prevalent has prevented participatory care from being used to its full potential. The introduction of information driven care enables the use of all available expertise and resources, including intelligent computing, mHealth technologies such as sensors, wearables, digital healthcare apps, and self-care towards increasing the efficiency of the healthcare system while improving healthcare quality by delivering care where and when it is needed the most. Information driven participatory care utilizes patient trajectories (covered in subject area 1) to better match healthcare interventions, including self-care, with patient needs. Healthcare transformation (aubject area 2) is a core aim that creates a healthcare system that inherently utilizes information driven participatory care to provide the best possible care and patient empowerment. The key objectives for information driven participatory care are to define frameworks, design guidelines, design patterns and a case study for information driven participatory care that can be used by private companies as well as public actors in an interconnected ecosystem to leverage participation for increasing efficiency, quality and patient empowerment and satisfaction in healthcare.




Anna-Frida Agardson