ABAnkica Babic

Ankica Babic

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ankica Babic has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Alignment in Gamified Cognitive Assessment

    by Krister Bauge, Ankica Babic

  • Open Access

    Visual Digital Twins for Arthroplasty: Conceptual Dashboards Integrating Patient Clusters and Clinical Pathways

    by Ida Wergeland Sævareid, Ankica Babic

    Digital twins have increasingly been proposed as a means of supporting personalized clinical decision-making, yet their translation into clinically interpretable visual forms remains underdeveloped. This article presents a study of conceptual dashboard design for digital twins in arthroplasty. Using a design science research approach, five iterative prototype cycles were conducted to examine how patient similarity, expected outcomes, and clinical pathways may be represented in dashboard form. The work was informed by the MIMIC-IV database and drew on cluster analysis, event-log-based pathway analysis, dashboard design principles, and cognitive walkthrough evaluation. Three complementary design concepts were developed: a cluster-based twin view, a pathway-based twin view, and an integrated dashboard combining both perspectives. Among these, the integrated concept offered the clearest representation of the digital twin by linking baseline patient characteristics, similarity groupings, and likely treatment trajectories within one navigable interface for clinical interpretation and use. The findings suggest that digital twins in arthroplasty may be communicated more effectively through structured dashboards than through isolated graphics or purely technical models, while also indicating the value of a shared conceptual framework for future clinically oriented visualization in healthcare.

  • Open Access

    Digital Cousins in Arthroplasty: An Interpretable Clustering Framework

    by Carl Oskar Kraft Sahlgaard, Ankica Babic

    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

    Clinical Pathways and Digital Twins in MIMIC-IV: A Proof-of-Concept Study

    by William Røise, Ankica Babic

    This study examines whether MIMIC-IV can support the construction of clinical pathways and proof-of-concept digital twins, and whether such pathways can be updated automatically with machine learning. Using time-stamped hospital records, patient-level event logs were reconstructed from admissions, diagnoses, procedures, and selected derived variables. Directed graphs were used to visualize trajectories, and a baseline machine-learning pipeline regenerated predictive features when new events were added. MIMIC-IV proved suitable for pathway reconstruction because it contains enough temporal detail to order events and link pathway states to outcomes. However, the pathway structure was heterogeneous, no single universal pathway was adequate, and the results must be interpreted in the context of a US-based database and a proof-of-concept study design rather than as directly generalizable clinical recommendations.

  • Open Access

    Toward Gender-Aware Digital Twins for Modeling Cognitive Decline

    by Shrutha Morthala, Ankica Babic

    Digital twins (DTs) are increasingly used to model health trajectories, yet most frameworks remain gender neutral. This paper synthesizes evidence on sex- and gender-related differences relevant to digital twin modeling of cognitive decline. Reported differences in cognitive performance, disease progression, and biological risk factors implicate significantly diagnostic accuracy and model performance. These findings point to the relevance of gender-aware digital twin designs, with particular attention to transparent and equitable interpretation of model-derived information.

  • Open Access

    Toward Clinical Digital Twins: A Three-Dimensional Framework for Knowledge Extraction, Pathway Modeling, and Visualization Using MIMIC-IV Data

    by Ankica Babic, William Røise, Carl Oskar Kraft Sahlgaard, Ida Wergeland Sævareid

    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.

  • Open Access

    Balancing Engagement and Validity in Game-Based Cognitive Assessments

    by Krister Bauge, Ankica Babic

    Game features are used to improve engagement in cognitive assessments but may also influence the cognitive constructs being measured. This short communication reviews empirical work on how specific game features affect engagement and construct validity. Structural features such as points and feedback tend to improve engagement with limited validity risks, while narratives and time pressure can shift strategies and alter what is being measured. Evidence remains limited, indicating a need for clearer validation frameworks.

  • Open Access

    Designing a Multimodal Data Structure for Cognitive Decline Using All of Us Resources and Gemini Flash Thinking

    by Oliwia Kudyba, Ankica Babic

    Cognitive decline is not easily defined, as it can manifest across multilayered and heterogeneous data. Its understanding requires the design of data structures that integrate all relevant dimensions. In this study, we address the challenge of implementing artificial intelligence models in medicine, focusing on the “Black Box” problem, and propose a conceptual and methodological framework to enhance interpretability. The framework integrates the All of Us Resource and applies Gemini Flash Thinking to move beyond correlation and explore causality. The proposed multilayer design establishes the foundation for dynamic modeling. Future work will refine this Gemini-based structure using All of Us data and develop interpretable visualizations and outputs for diverse populations.