Supporting sensemaking of data in healthcare: A multi-method approach
Författare
Summary, in English
In healthcare, the ability to make sense of data is crucial for informed and responsible decision-making. However, the ongoing digitalization of healthcare and its reliance on heterogeneous forms of data has made sensemaking increasingly complex. Data is generated, presented, and used through a variety of tools, practices, and algorithmic systems, and its meaning demands careful and context-sensitive interpretation that accounts for disease context, patient characteristics, and clinical workflows. This thesis addresses the research question: How to support the sensemaking of data in healthcare?
Drawing on a multi-method approach comprising five research papers, this dissertation develops theoretically informed and practically oriented support for sensemaking of data across three distinct functional roles: data as a tool, data as a practice, and data as algorithmic intelligence. Each role presents unique sensemaking challenges that require tailored forms of support.
The contributions of this thesis are threefold. First, it develops an integrated framework that delineates two essential dimensions of sensemaking support: interpretive support, which makes visible how data becomes meaningful through interaction, collaboration, and tool design and contextual fit support, which ensures that meaning aligns with the situated demands of clinical practice, disease-specific reasoning, and professional roles. Second, it contributes a multi-method approach that develops conceptual, processual, and design contributions tailored to each form of sensemaking support. Third, it advances the design of computational artifacts by demonstrating how tools can be designed to support sensemaking of complex data in the context of mental health assessments.
By exploring and offering support that is both exploratory and nuanced, the thesis advances healthcare Information Systems research on sensemaking of data, data use, healthcare technologies, and the collaborations between healthcare practitioners and artificial intelligence.
Drawing on a multi-method approach comprising five research papers, this dissertation develops theoretically informed and practically oriented support for sensemaking of data across three distinct functional roles: data as a tool, data as a practice, and data as algorithmic intelligence. Each role presents unique sensemaking challenges that require tailored forms of support.
The contributions of this thesis are threefold. First, it develops an integrated framework that delineates two essential dimensions of sensemaking support: interpretive support, which makes visible how data becomes meaningful through interaction, collaboration, and tool design and contextual fit support, which ensures that meaning aligns with the situated demands of clinical practice, disease-specific reasoning, and professional roles. Second, it contributes a multi-method approach that develops conceptual, processual, and design contributions tailored to each form of sensemaking support. Third, it advances the design of computational artifacts by demonstrating how tools can be designed to support sensemaking of complex data in the context of mental health assessments.
By exploring and offering support that is both exploratory and nuanced, the thesis advances healthcare Information Systems research on sensemaking of data, data use, healthcare technologies, and the collaborations between healthcare practitioners and artificial intelligence.
Avdelning/ar
Publiceringsår
2026-02-12
Språk
Engelska
Publikation/Tidskrift/Serie
Lund Studies in Informatics
Avvikelse
21
Fulltext
Dokumenttyp
Doktorsavhandling
Förlag
Lund University
Ämne
- Computer and Information Sciences
Nyckelord
- Sensemaking
- Healthcare
- Data
- Multi-method
Aktiv
Published
ISBN/ISSN/Övrigt
- ISSN: 1651-1816
- ISSN: 1651-1816
- ISBN: 978-91-8104-819-3
- ISBN: 978-91-8104-818-6
Försvarsdatum
6 mars 2026
Försvarstid
13:15
Försvarsplats
EC2:101
Opponent
- Erik Perjons (Associate Professor)