Skip to content

Research

Research Update:
Revolutionizing Cancer Treatment with AI and Mathematical Modeling

Professor Qingpeng ZHANG

Associate Professor
HKU IDS / Pharmacology and Pharmacy

Led by Professor Qingpeng Zhang, Associate Professor jointly affiliated with the HKU IDS and the Faculty of Medicine, pioneering research advancement in cancer therapy by combining artificial intelligence (AI) and mathematical modeling to create personalized treatment plans has been seen. This innovative approach, published in Briefings in Bioinformatics, focuses on optimizing the combination of chemotherapy and immune checkpoint inhibitors (ICIs) for individual patients.

Chemotherapy and ICIs are powerful cancer treatments, but their effectiveness varies widely among patients. This is partly due to the complex interactions within the tumor immune microenvironment (TIME). Traditional treatment plans often don’t account for these individual differences, leading to less effective outcomes.

The research team led by Professor Zhang has developed a sophisticated mathematical model to understand how chemotherapy and ICIs interact with immune cells and tumor cells. They then used deep reinforcement learning (DRL), a type of AI algorithm, to derive personalized treatment schedules for patients.

Figure 1: The schematic visualization of the complex interactions within the tumor immune microenvironment.

The AI-driven approach outperformed standard treatment schedules by tailoring therapy to each patient’s unique tumor environment. For example:

  • Patients with higher immune cell presence (“hot tumors”) respond better to a combination of chemotherapy and ICIs, adjusted to their specific needs.
  • Patients with very low immune cell presence (“extremely cold tumors”) benefit most from high-dose chemotherapy alone.
  • Patients with low to medium immune cell presence (“cold tumors”) could benefit from ICIs by combining with low dosage of chemotherapy.

This interdisciplinary application of AI and mathematical modeling represents a major step forward in personalized cancer therapy. By customizing treatment plans based on individual patient data, this approach aims to improve outcomes and reduce side effects. Prof. Zhang’s team is collaborating with oncologists to further validate their model in clinical settings. They aspire to unleash the potential of AI to transform cancer treatment, offering hope for more effective and personalized therapies in the future.

For more detailed insights, read the full paper at https://academic.oup.com/bib/article/25/6/bbae547/7841508