The University of Chicago Medicine has joined the I3LUNG project, a research initiative funded by a five-year, €10M grant from the European Union to develop a decision-making tool for creating individually tailored lung cancer treatment plans. The project will use artificial intelligence (AI) software and machine learning to analyze a wide range of information from clinical data, radiology images, and biological characteristics of tumors.
“This highly innovative project has the goal of using machine learning and artificial intelligence to predict the outcomes of immunotherapy, which is something we are not currently capable of doing,” said Marina Garassino, MD, Professor of Medicine and the leader of the University of Chicago Medicine’s arm of the project. “Right now, we know that less than 30% of patients will have a great response to immunotherapy, but we are not able to predict who those patients are. Improving our ability to make these predictions can help us better tailor treatments for individual patients.”
The data will come from 2,000 patients across multiple research centers in the United States, Italy, Germany, Greece, Spain and Israel. Two hundred new patients will be enrolled in a prospective study to gather new biological data from tumor genetics, the immune system, digital pathology, gut microbiome, imaging and other genetic and molecular analyses. In parallel, researchers will also conduct a psychological study to integrate patient experiences and preferences into decision-making tools.
The team at UChicago Medicine will apply the expertise of researchers from the labs of Garassino and Alexander Pearson, MD, PhD, a longtime machine learning scientist and clinician, to help process the original set of patient data and prepare it for use by other researchers. The data can in turn be used to develop and test new algorithms for predicting immunotherapy outcomes.
“Here at UChicago Medicine, we have a lot of expertise in processing these types of data,” said Pearson, Assistant Professor of Medicine. “Finding the most relevant signal in messy genomic data, or finding the patterns in how a tumor grows, or the features in a CT scan that correspond to good or bad outcomes when a cancer is being treated, all of those domains have been led by us. So, when Dr. Garassino brought her global lungcancer expertise to the organization, it was clear that we could work together to leverage these emerging methods.”
Garassino arrived at UChicago Medicine during the COVID-19 pandemic, bringing not only her expertise in lung cancer but her connections to a multitude of international institutions.
“Our work will use all of the patient data that we have access to — genetics, histology, lipidomics, proteomics,” said Garassino. “We can use this data to create a huge database of all that’s been collected in the past, and with all of that information, we can try to build an algorithm and train the artificial intelligence to see if we can find a signature that will predict how effective immunotherapy will be for any given patient.”
Ultimately, the hope is that the tools developed by the I3LUNG project can be applied to not only non-small cell lung cancer treatments, but other types of cancers and treatments.
“When it first arrived on the scene, we had the idea that immunotherapy would be the solution to all cancerous tumors,” said Garassino. “But we now know that’s not true, and really, only some patients respond well. We’re very happy with what we’ve achieved, but we still don’t have one big solution. Tumors are incredibly complex, and with our normal statistical approaches, it’s impossible to understand that complexity. The promise of AI is that it can learn all of these complex layers and integrate all of that information to help inform individual care.”
Work on the I3LUNG project at the University of Chicago will build on expertise in integrating clinical data and AI into translational research, complemented by the work of Pearson, Garassino and others, who are dedicated to the use of machine learning for improving clinical care.
“Most people in my lab are clinicians first and machine learning experts second,” said Pearson. “That approach means that everything we do is in the service of our patients, rather than just designing algorithms for an algorithm’s sake. It’s really important to get it right for the physicians who will be making decisions for their patients using this information. These drugs can have lifelong effects. My hope is that with a careful, rigorous approach, we can really take advantage of these tools in ways that are safe and valuable for patient care.”
[Source(s): University of Chicago Medical Center, Newswise]