In a subset of patients diagnosed with non-small cell lung cancer (NSCLC), immunotherapy paradoxically exacerbates tumor growth and significantly shortens survival. Currently there are no clinically validated biomarkers that can identify patients at risk of this paradoxical response called “hyperprogression.”
Using artificial intelligence (AI) analysis of simple tissue scans, researchers at Case Western University claim they have discovered biomarkers that could tell which lung cancer patients might get worse from immunotherapy.
In addition to those who would benefit from immunotherapy, and those who might not, researchers and oncologists can now identify a third category of patients called hyper-progressors who would be harmed by the same immunotherapy, says Pranjal Vaidya, a PhD student in biomedical engineering and researcher at the university’s Center for Computational Imaging and Personalized Diagnostics (CCIPD).
“This is a significant subset of patients who should potentially avoid immunotherapy entirely,” says Vaidya, first author on a paper titled “Novel, non-invasive imaging approach to identify patients with advanced non-small cell lung cancer at risk of hyperprogressive disease with immune checkpoint blockade,” published in the Journal for Immunotherapy of Cancer. “Eventually, we would want this to be integrated into clinical settings, so that the doctors would have all the information needed to make the call for each individual patient.”
Immunotherapy, a more recent treatment approach, uses drugs to help a patient’s immune system fight cancer while chemotherapy uses drugs to directly kill cancerous cells. However, at present, only approximately 20% of all cancer patients actually benefit from immunotherapy, according to the National Cancer Institute. The use of immune checkpoint inhibitors (ICI) to the arsenal of therapies against cancer has resulted in unprecedented improvement in survival outcomes for various cancers, including non-small cell lung cancer (NSCLC).
Combining medical imaging and machine learning, scientists at CCIPD at Case Western University, led by Anant Madabhushi, PhD, Donnell Institute Professor of Biomedical Engineering, senior author on the study, aim to diagnose and characterize cancers and other diseases.
The team teaches computers to search for and identify patterns in preliminary computerized tomography (CT) scans taken when lung cancer is first diagnosed to reveal information that could have been useful if known before the commencement of treatment regimens.
Using this retrospective approach, reviewing electronic medical records of 109 patients with NSCLC 19 patients with hyperprogression, who received a single immunotherapy with either programmed cell death protein-1 (PD1) or programmed death-ligand-1 (PD-L1) checkpoint inhibitor drugs between January 1, 2015, and April 30, 2018, the authors identify radiomic biomarkers that distinguish hyper-progressors from responders and non-responders.
“This is an important finding because it shows that radiomic patterns from routine CT scans are able to discern three kinds of response in lung cancer patients undergoing immunotherapy treatment–responders, non-responders and the hyper-progressors,” says Madabhushi.
“There are currently no validated biomarkers to distinguish this subset of high-risk patients that not only don’t benefit from immunotherapy but may in fact develop rapid acceleration of disease on treatment,” said Pradnya Patil, MD, FACP, associate staff at Taussig Cancer Institute, Cleveland Clinic, and study author.
“Analysis of radiomic features on pre-treatment routinely performed scans could provide a non-invasive means to identify these patients,” says Patil. “This could prove to be an invaluable tool for clinicians while determining optimal systemic therapy for their patients with advanced non- small cell lung cancer.”
The team of scientists found some of the most significant clues to which patients would be harmed by immunotherapy outside the tumor.
“We noticed the radiomic features outside the tumor were more predictive than those inside the tumor, and changes in the blood vessels surrounding the nodule were also more predictive,” says Vaidya.
Although the study is limited in the total number of hyper-progression cases in the analysis, the authors note, “ Our findings suggest that radiomic analysis of pretherapy CT scans of patients with NSCLC who are being considered for immune checkpoint blockade could be used to identify patients who are at a higher risk of hyperprogression with this treatment.”
