SYDNEY, Oct. 13 (Xinhua/APP): Non-small cell lung cancer (NSCLC), the most common form of lung cancer, was mapped cell-by-cell using spatial biology and artificial intelligence (AI), taking the guesswork out of drug treatment, according to research involving Australian scientists.
People with the most common form of lung cancer could receive more effective, individualized treatment after Australia’s University of Queensland (UQ) researchers, in collaboration with researchers at Yale University in the United States, developed a way to predict how cancer cells will respond to different therapies, according to a UQ statement released Monday.
The same precision-mapping approach could be used to inform treatments for other malignancies like melanoma, head and neck, and bladder cancer, the statement said.
Researchers studied the tumors of 234 patients with NSCLC across three cohorts in Australia, the United States and Europe.
This approach can “pinpoint areas within tumors that are both responsive and resistant to therapies, which will be a game changer for lung cancer treatment,” said Associate Professor Arutha Kulasinghe from UQ’s Frazer Institute.
“Rather than having to use a trial-and-error approach, oncologists will now know which treatments are most likely to work with new precision medicine tools,” said Kulasinghe, a corresponding author of the study published in Nature Genetics.
David Rimm, Anthony N. Brady professor of Pathology at Yale, the study’s co-lead author, called the work a “road map for a new diagnostic test that could optimize treatment choice in lung cancer.”
As the leading cause of cancer death in the world, lung cancer kills about 1.8 million people globally each year, with NSCLC accounting for 85 percent of all cases. However, costly immunotherapies are effective in only 20-30 percent of patients, according to the study.
“These therapies also carry significant risks for patients receiving them, including severe immune-related toxicity that can be fatal,” Kulasinghe said, adding the challenges highlight the critical need to classify patients according to their likelihood to benefit from treatment.
By integrating data on the molecular geography of cancer and machine learning techniques, treatment decision-making could be improved, leading to better patient outcomes for lung cancer patients, he said.