A revolutionary artificial intelligence-driven cancer testing system is poised to enhance treatment outcomes by identifying the most effective drugs for patients before therapy commences. The innovative technology enables scientists to cultivate miniature living replicas of a patient’s tumor in the laboratory, subsequently exposing them to a wide array of drugs and combinations to determine the most effective treatment options.
The AI analyzes the results rapidly, providing oncologists with a clearer understanding of which therapeutic approaches are likely to succeed against specific cancer types. PreComb, a UK-funded company leading this research, is currently applying this technology to various cancers, including small-cell lung cancer, bowel cancer, bone cancer, and both adult and pediatric brain cancers.
Experts believe this advancement could significantly improve care for thousands of patients, potentially extending lives or providing crucial time for those battling aggressive tumors. In the UK, approximately 412,000 individuals are diagnosed with cancer each year, translating to one diagnosis every 75 seconds. Out of these, more than 100,000 patients undergo chemotherapy.
Despite its prevalence, chemotherapy is often administered without a clear understanding of which drug or combination will be effective for each individual patient. This uncertainty arises because cancer is a complex group of diseases; even tumors that appear similar can behave differently due to variations in mutations, resistance mechanisms, and biological characteristics.
As a result, many patients experience severe side effects from treatments that are ultimately ineffective. Researchers assert that the new AI-driven approach has the potential to change this paradigm significantly. Instead of selecting drugs based primarily on historical data from average patient responses, the technology enables direct testing on living tumor material obtained from the patient.
Professor Javad Nazarian, an oncology scientist at the University of Zurich, is utilizing this technology for children with aggressive brain cancers, which remain highly challenging to treat. “These are very deadly tumors, and, in many cases, they are still incurable,” he stated. “Until now we have not had a reliable way of seeing and measuring how a patient’s cancer is responding to drugs. Now we have a new monitoring and AI-driven drug-screening platform that allows us to test therapies directly on tumor cells from the patient.”
In practice, doctors extract a small sample of tumor tissue, which scientists then use to cultivate living cancer cells in the lab, effectively creating a miniature version or “avatar” of the patient’s cancer. These “miniature tumors” are subsequently exposed to a broad panel of drugs selected according to the genetic profile of the tumor.
Professor Nazarian noted that his team can test over 120 drugs that may align with a patient’s tumor biology. Unlike conventional chemotherapy that indiscriminately targets all fast-growing cells, the goal here is to identify treatments that more precisely target the tumor. Over a period of two to three weeks, the platform monitors the cancer cells’ response.
The AI processes thousands of images to determine the status of the cells—whether they are growing, stabilizing, or dying off. “When fully developed, the system will give doctors a far clearer view of what is happening. We can tell if the cells are expanding or falling,” Professor Nazarian explained. “The AI platform helps us see whether tumor cells are dying, proliferating, or becoming dominant. That could hugely advance the way we treat patients.”
This timely insight is particularly critical for brain tumors, where clinicians often have a narrow window post-surgery to determine treatment options. “In many cases we have only a few weeks to think about how we treat,” he said, emphasizing the potential of this system to be a game-changer.
Professor Nazarian also shared a compelling case where a child, initially expected to survive only three months, lived for 19 months after treatment guided by the screening approach. “The tumor eventually recurred, but some of it disappeared, extending survival,” he remarked.
The PreComb system employs automated robotics and “well plates” containing the miniature tumors, allowing for extensive drug screening. Hal Bosher, Chief Executive of PreComb, stated, “Our platform generates around 5,500 images per test, and with the advent of AI and machine learning, we can now process that data and get meaningful outcomes.” He emphasized that tests are conducted by robots, which automatically deliver drugs into numerous tiny wells containing tumor cells or tissue. The company has completed 371 screens, amassing over 1.1 million tumor images across 272 different drugs.
This pioneering system not only exemplifies the potential of AI in oncology but also signifies a meaningful step toward personalized medicine, offering hope for better treatment outcomes in the ongoing battle against cancer.
See also
University of Sydney Secures $55M Boost for Leading Maths Research in AI Development
AI Guardrails Shape Conversations: New Study Reveals Their Impact on Digital Discourse
Machine Learning and IoT Transform Factories with Real-Time Analytics and Cybersecurity Advances
AWS Bedrock’s Code Interpreter Vulnerability Exposes Sensitive Data Risk, Researchers Warn
