Using AI To Maximize The Potential Of Immunotherapies

Immunotherapy is a treatment used to fight cancer that stimulates the body's own immune system to eliminate cancer cells. Although the first immunotherapy for cancer was approved in 2011, only a fraction of patients who receive immunotherapy respond to the treatment. To improve real-world efficacy, researchers are using AI to help predict which patients will benefit from immunotherapy. Although many ML models have been developed to predict immunotherapy outcomes, very few have undergone clinical testing, and most ML based immunotherapy decision support systems have encountered obstacles transitioning from research to clinical practice.

Yuan Luo, PhD and his colleagues at the Northwestern University Feinberg School of Medicine have published a review article summarizing ML approaches in immunotherapy. The article aims to inspire cutting-edge machine learning research to maximize the potential of immunotherapies. The article entitled "Informing immunotherapy with multi-omics driven machine learning" was published on March 14, 2024 in NPJ Digital Medicine. In today's AI newsletter I'm sharing highlights from Dr. Luo's article which is open access and can be downloaded here: https://doi.org/10.1038/s41746-024-01043-6

 

Center for Collaborative AI in Healthcare

Dr. Luo is Chief AI Officer and Associate Professor at Northwestern University Feinberg School of Medicine, and head of the Center for Collaborative AI in Healthcare. He is an established researcher and thought leader in biomedical machine learning, natural language processing, time series analysis, computational phenotyping, and integrative multi-omic analysis.

Highlights from the article

• The authors provide an overview of cutting-edge ML models for immunotherapy analysis, immunotherapy response prediction, and tumor microenvironment identification.
• The authors describe how ML leverages diverse data types to identify significant biomarkers, enhance understanding of immunotherapy mechanisms, and optimize decision-making process.
• The authors discuss current limitations of ML and outline future directions to overcome obstacles and improve efficiency of ML in immunotherapy.

1. Genomic landscape of ML in tumor immunotherapy.

 Image source: Informing immunotherapy with multi-omics driven machine learning 

2. Overview of ML techniques for immunotherapy response prediction.

Image source: Informing immunotherapy with multi-omics driven machine learning

3. ML offers promising strategies for evaluating the tumor microenvironment.

Image source: Informing immunotherapy with multi-omics driven machine learning

4. Identification of tumor neoantigens using ML models. 

Image source: Informing immunotherapy with multi-omics driven machine learning

This article was written by Margaretta Colangelo. Margaretta is a leading AI analyst who tracks significant milestones in AI in healthcare. She consults with AI healthcare companies and writes about some of the companies she consults with. Margaretta serves on the advisory board of the AI Precision Health Institute at the University of Hawaiʻi Cancer Center.