Rheumatic Digital Twin: Proposed Machine Learning–Based Multimodal Framework to Inform Clinical Decision-Making

Journal of Medical Internet Research, vol. 28, pp. e86763

Abstract

Unlabelled: Rheumatic diseases are chronic, immune-mediated conditions characterized by significant heterogeneity in presentation and disease course. However, current clinical approaches often rely on snapshot-based assessments that fail to capture the complex longitudinal evolution of these conditions. To address these limitations and support the implementation of precision medicine, we present the design for the Rheumatic Digital Twin, a novel, modular conceptual framework intended to integrate heterogeneous multimodal data, ranging from electronic health records and clinical notes to imaging and omics, into a dynamic, computational representation of the patient journey. Our theoretical architecture addresses challenges related to data silos and variable availability of data modalities through a multistage approach that envisions the use of domain-specific foundation models to independently process distinct data modalities. To effectively model the temporal progression inherent in chronic diseases, the proposed design utilizes Transformer architectures, leveraging self-attention mechanisms to treat patient events, such as lab results or medication changes, as sequential data tokens. We describe how these unimodal representations would subsequently be fused via joint embedding techniques to construct a shared, multimodal representational space. Envisioned to function analogously to a recommender system, the Rheumatic Digital Twin framework is modeled to map patients into a latent space where proximity reflects clinical and biological similarity. By identifying "nearest neighbors," historical patients with comparable trajectories, the system aims to enable in silico cohorting, theoretically allowing clinicians to forecast key clinical events, predict treatment responses, and identify likely disease courses based on the outcomes of similar peers.

Authors 4

1. Daniyal Selani Aachen Department of Rheumatology, Leiden University Medical Center

   Leiden University Medical Center · Delft University of Technology

   Affiliation as printed

   Department of Rheumatology, Leiden University Medical Center, Leiden, The Netherlands

   Pattern Recognition and Bioinformatics, Faculty Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, The Netherlands

2. Rachel Knevel Aachen Department of Rheumatology, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Department of Rheumatology, Leiden University Medical Center, Leiden, The Netherlands

3. Marcel Reinders Aachen Department of Biomedical Data Sciences

   Leiden University Medical Center · Delft University of Technology

   Affiliation as printed

   Department of Biomedical Data Sciences, Leiden University Medical Center, Einthovenweg 20, Leiden, 2333 ZC, The Netherlands, 31 1 526 30 13

   Pattern Recognition and Bioinformatics, Faculty Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, The Netherlands

4. Erik B. van den Akker Aachen Department of Biomedical Data Sciences

   Leiden University Medical Center · Delft University of Technology

   Affiliation as printed

   Department of Biomedical Data Sciences, Leiden University Medical Center, Einthovenweg 20, Leiden, 2333 ZC, The Netherlands, 31 1 526 30 13

   Pattern Recognition and Bioinformatics, Faculty Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, The Netherlands