Using mathematical modelling and AI to improve delivery and efficacy of therapies in cancer

Area of Science:

• Oncology
• Mathematical Biology
• Computational Science

Background:

• Mathematical modeling is crucial for predicting the delivery and efficacy of various cancer therapies in solid tumors.
• Mechanistic models, encompassing continuous (lumped and distributed parameter) and discrete types, are based on biological understanding at multiple levels.
• These models integrate tumor biology, drug properties, and microenvironment interactions for optimized therapy and patient-specific predictions.

Purpose of the Study:

• To review diverse mathematical modeling approaches for cancer therapy.
• To explore the role of artificial intelligence (AI) and machine learning (ML) in oncology.
• To suggest synergistic combinations of mechanistic and AI-based models for improved patient outcomes.

Main Methods:

• Review of mechanistic mathematical models (continuous and discrete) for drug delivery and efficacy prediction.
• Discussion of artificial intelligence (AI) and machine learning (ML) applications in cancer research.
• Exploration of integrating mechanistic and AI-driven approaches.

Main Results:

• Mechanistic models provide insights into therapy delivery and efficacy by considering biological and drug properties.
• AI and ML offer complementary data-driven approaches with potential in cancer detection, treatment, and drug discovery.
• Combined mechanistic and AI models hold significant potential for personalized cancer treatment.

Conclusions:

• Mathematical modeling is essential for optimizing molecular, nano, and cellular therapies in solid tumors.
• AI and ML represent a paradigm shift in oncology, complementing traditional modeling.
• Integrating mechanistic and AI models is a promising strategy to advance cancer patient care and treatment effectiveness.