Metaverse and Healthcare: Machine Learning-Enabled Digital Twins of Cancer

Area of Science:

• Digital Health
• Medical Informatics
• Artificial Intelligence in Medicine

Background:

• Medical digital twins bridge the physical world and the metaverse, offering virtual medical services and immersive patient experiences.
• Digitalizing complex diseases like cancer for metaverse applications presents significant challenges.
• Breast cancer is the second most prevalent cancer globally, highlighting the need for innovative diagnostic and therapeutic tools.

Purpose of the Study:

• To develop real-time, reliable digital twins of cancer using machine learning (ML) techniques for diagnostic and therapeutic applications.
• To simplify the creation of cancer digital twins for medical specialists with limited Artificial Intelligence (AI) expertise.
• To meet the Internet of Medical Things (IoMT) requirements for latency and cost-effectiveness.

Main Methods:

• Utilized four classical machine learning techniques known for their simplicity and speed.
• Focused on breast cancer (BC) as a case study for digital twin development.
• Developed a conceptual framework for creating cancer digital twins.

Main Results:

• Demonstrated the feasibility and reliability of ML-based digital twins for cancer.
• Showcased the capability of digital twins in monitoring, diagnosing, and predicting medical parameters.
• Validated the use of simple ML techniques suitable for IoMT environments.

Conclusions:

• Machine learning enables the creation of effective digital twins for cancer management within the metaverse.
• These digital twins offer a viable solution for real-time patient monitoring and personalized treatment strategies.
• The proposed framework and methods support the integration of digital twins into clinical practice, particularly for breast cancer.