Digital Twin Monitoring System for Chronic Disease Patients: A Simulation-Based Proof of Concept

Area of Science:

• Biomedical Engineering
• Health Informatics
• Digital Health

Background:

• Digital twin (DT) technology offers transformative potential in healthcare.
• Current patient digital twins (PDTs) for remote monitoring often lack comprehensive data integration.
• Effective PDTs require integration of real-time physiological data and patient medical records for thorough analysis.

Purpose of the Study:

• To present a simulation-based proof-of-concept patient digital twin (PDT) for monitoring chronic diseases.
• To demonstrate the feasibility of remote patient support using a PDT.
• To evaluate the PDT framework's potential for early abnormality detection and timely intervention.

Main Methods:

• Developed a simulation-based PDT framework integrating physiological data streams and simulated medical records.
• Utilized publicly available datasets to emulate patient vitals and medical history.
• Performed cloud-based real-time simulation for remote access and continuous observation of the virtual patient replica.
• Integrated a drug-class prediction module for system validation.

Main Results:

• The PDT framework successfully simulated remote monitoring of chronic conditions (hypertension, diabetes, respiratory diseases).
• Cloud-based simulation enabled remote access and continuous observation of the patient's digital twin.
• The drug-class prediction module achieved 96.53% accuracy on a synthetic dataset, validating the system pipeline.

Conclusions:

• The developed PDT demonstrates a feasible approach for remote monitoring and analysis of chronic disease patients.
• Integrating real-time vitals with medical records enhances the comprehensiveness of PDT analysis.
• The PDT system shows promise for early abnormality detection and timely intervention, paving the way for clinical evaluation.