Carl Oskar Kraft Sahlgaard
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Carl Oskar Kraft Sahlgaard has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Ankica Babic
University of Bergen
2 shared publications - Ida Wergeland Sævareid
Department of Information Science and Media Studies, University of Bergen, Norway
1 shared publication - William Røise
Department of Information Science and Media Studies, University of Bergen, Norway
1 shared publication
Latest Publications
- Open Access
- 29 June 2026
- Published by IOS Press
- Vol. 338, 688-692
Digital Cousins in Arthroplasty: An Interpretable Clustering Framework
Digital twins are increasingly proposed as a route toward personalized medicine, but in routine clinical data the more realistic near-term goal may be the identification of digital cousins, that is, clinically similar patients who can support outcome interpretation. This study explored whether interpretable clustering of baseline arthroplasty data can provide a useful methodological foundation for outcome analysis. Hip arthroplasty-related records were extracted from MIMIC-IV and separated into primary and revision representations. Because MIMIC-IV is an acute-care, ICU-enriched hospital dataset rather than a dedicated arthroplasty registry, this cohort should be interpreted as a medically complex arthroplasty subset rather than the standard elective population. This non-registry selection is also clinically relevant because revision-related hospital episodes are high-risk and burdensome. Patients were clustered using standardized continuous variables (age, body mass index, and Charlson Comorbidity Index), while grouped diagnosis categories were reserved for post hoc interpretation rather than Euclidean distance calculations. The resulting clusters produced clinically readable patient profiles and highlighted differences between primary and revision surgery patterns. The findings support an interpretable digital cousin framework rather than a full digital twin claim.
- 29 June 2026
- Published by IOS Press
- Vol. 338, 688-692
Open AccessDigital Cousins in Arthroplasty: An Interpretable Clustering Framework
Digital twins are increasingly proposed as a route toward personalized medicine, but in routine clinical data the more realistic near-term goal may be the identification of digital cousins, that is, clinically similar patients who can support outcome interpretation. This study explored whether interpretable clustering of baseline arthroplasty data can provide a useful methodological foundation for outcome analysis. Hip arthroplasty-related records were extracted from MIMIC-IV and separated into primary and revision representations. Because MIMIC-IV is an acute-care, ICU-enriched hospital dataset rather than a dedicated arthroplasty registry, this cohort should be interpreted as a medically complex arthroplasty subset rather than the standard elective population. This non-registry selection is also clinically relevant because revision-related hospital episodes are high-risk and burdensome. Patients were clustered using standardized continuous variables (age, body mass index, and Charlson Comorbidity Index), while grouped diagnosis categories were reserved for post hoc interpretation rather than Euclidean distance calculations. The resulting clusters produced clinically readable patient profiles and highlighted differences between primary and revision surgery patterns. The findings support an interpretable digital cousin framework rather than a full digital twin claim.
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 1639-1643
Toward Clinical Digital Twins: A Three-Dimensional Framework for Knowledge Extraction, Pathway Modeling, and Visualization Using MIMIC-IV Data
This paper explores three dimensions of digital twin development in healthcare: knowledge extraction, clinical pathway modeling, and conceptual visualization. Using the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, the study investigates how unsupervised learning, event-log analysis, and visualization design can be combined to support the instantiation of clinical digital twins. The proposed framework integrates patient similarity modeling, temporal pathway reconstruction, and user-oriented visualization into a coherent design science research artifact. Although the resulting implementation does not yet constitute a fully realized clinical digital twin, it illustrates how digital twins can be initialized from real-world clinical data, support early predictive modeling, and evolve through iterative refinement. The findings highlight the importance of data granularity, temporal structure, and interpretability, and demonstrate how such models may bridge analytical and clinical perspectives. Future work will extend the framework through richer data inclusion, clinical validation, and real-time deployment.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 1639-1643
Open AccessToward Clinical Digital Twins: A Three-Dimensional Framework for Knowledge Extraction, Pathway Modeling, and Visualization Using MIMIC-IV Data
This paper explores three dimensions of digital twin development in healthcare: knowledge extraction, clinical pathway modeling, and conceptual visualization. Using the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, the study investigates how unsupervised learning, event-log analysis, and visualization design can be combined to support the instantiation of clinical digital twins. The proposed framework integrates patient similarity modeling, temporal pathway reconstruction, and user-oriented visualization into a coherent design science research artifact. Although the resulting implementation does not yet constitute a fully realized clinical digital twin, it illustrates how digital twins can be initialized from real-world clinical data, support early predictive modeling, and evolve through iterative refinement. The findings highlight the importance of data granularity, temporal structure, and interpretability, and demonstrate how such models may bridge analytical and clinical perspectives. Future work will extend the framework through richer data inclusion, clinical validation, and real-time deployment.