Researchers from the University of Pennsylvania and the Perelman School of Medicine, in collaboration with VOC Health, have developed an artificial intelligence program that can detect pancreatic and ovarian cancer with promising levels of accuracy.
Equipped with nanosensors, the program was able to detect volatile organic compounds (VOCs) from a patient’s serum sample. With an accuracy of 95%, the program was able to distinguish between 20 patients with ovarian cancer, 20 patients with benign ovarian tumours and 20 age-matched controls with no cancer. Similar results were obtained with the detection of pancreatic cancer- at an accuracy of 90%, the program was able to distinguish between 13 patients with pancreatic cancer, 10 patients with benign pancreatic disease and 10 controls. Of note, was the fact that the program was able to detect all 8 patients with early-stage cancer, highlighting the technologies potential applicability to clinical practice.
VOCs are emitted by cells within the human body, and emerging research suggests that VOCs can be unique to certain disease states, such as different types of cancer. It is hoped that the detection of VOCs can be applied to clinical practice as a diagnostic tool. Similar to a human nose, the tool was trained to identify VOC patterns that are more prevalent in cancer cells in 20 minutes or less.
“It’s an early study but the results are very promising,” co-author Charlie Johnson, PhD, said. “The data shows we can identify these tumours at both advanced and the earliest stages, which is exciting. If developed appropriately for the clinical setting, this could potentially be a test that’s done on a standard blood draw that may be part of your annual physical.”
The study was presented at the annual American Society of Clinical Oncology and in light of these results, the research team has subsequently been awared a $2 million grant from the National Institutes of Health National Center for Advancing Translational Sciences, in order to produce a handheld device that can detect a VOC signature in people with COVID-19.
Reference
Top
