RI-MUHC study uses AI to find liver cancer biomarkers in extracellular vesicles

In a groundbreaking study published in the journal Informatics in Medicine Unlocked, researchers from the Research Institute of the McGill University Health Centre (RI-MUHC) and Modal Technology Corporation have leveraged a unique AI system, ALiX, to advance personalized and less invasive treatments for liver cancer patients.

Liquid Biopsy: A Revolutionary Approach

A liquid biopsy is a blood test designed to detect cancer by identifying tumor cells and DNA. This method aims to replace traditional surgical biopsies, which are often more expensive, painful, and risky. Although liquid biopsy is still a developing field, its potential for transforming cancer diagnosis and management is immense.

“Accurate, low-cost liquid biopsy can transform how we diagnose and manage cancer,” says Dr. Peter Metrakos, a senior scientist in the Cancer Research Program at RI-MUHC. The research team is focused on finding effective biomarkers and managing the vast amounts of data produced in their studies.

Extracellular Vesicles: Tiny Messengers with Big Potential

Dr. Metrakos and Dr. Anthoula Lazaris have created an extensive tissue and liquid database through the MUHC Liver Disease Biobank. Their study specifically isolated extracellular vesicles (EVs) from the blood of patients with colorectal cancer liver metastases, both before and after surgical resection of the tumor.

Extracellular vesicles are small particles released by cells that contain proteins, which can serve as biomarkers. These biomarkers are crucial for identifying cancer and monitoring disease progression. The isolation and analysis of these EVs are central to understanding how to predict and monitor patient responses to cancer treatments.

The flow of the study

Harnessing AI for Deeper Insights

Recognizing the potential of their data, Metrakos and Lazaris partnered with Modal Technology Corporation to apply their AI software, ALiX. Unlike traditional AI systems based on statistics, ALiX uses set theory to analyze data, providing deep insights with high confidence.

“Modal’s software, known as ALiX, can provide deep insights from data like ours with an unprecedented level of confidence,” says Anthoula Lazaris. “One of the key reasons for that is because ALiX is the world’s first AI platform not based on statistics but set theory.”

The ALiX software was used to analyze the EVs and their protein content, identifying a unique blood profile for each patient. This analysis allowed the researchers to rank biomarkers by their significance in predicting treatment response, a capability not matched by any other AI system to date.

“To our knowledge, there is no other AI system or method that can provide a ranked list of proteins like this,” says Anthoula Lazaris. “Of course, the ranked biomarker solution ALiX has provided now leads us to new questions and further hypotheses. We need to develop new strategies to understand the wealth of information that can be found in blood.”

Moving Forward: New Questions and Hypotheses

The insights gained from ALiX have led to new questions and hypotheses, driving the need for further research and new strategies to fully understand the wealth of information available in blood samples.

This research underscores the importance of patient participation, as the samples obtained from those who consented to the Liver Disease Biobank were essential for this study. The research team expresses immense gratitude for their support.

In conclusion, this study highlights the promise of extracellular vesicles and advanced AI technology in revolutionizing cancer treatment, paving the way for more personalized and effective approaches in oncology.

SourceMcGill University

Lazaris A, Tsamchoe M, Kaplan S, Metrakos P, Hayes N. (2024) Predictive biomarker discovery in cancer using a unique AI model based on set theory. Inform Med Unlocked 46(1), 101481. [article]

Leave a Reply

Your email address will not be published. Required fields are marked *