2023-12-13 17:55:22
This text is a translation of an article from CTV News.
Scientists at the University of Gothenburg, Sweden, have developed a method to detect changes in sugar molecules using artificial intelligence (AI) that might indicate cancer.
These molecules, called glycans, are linked to proteins in human cells, according to the summary of a small-scale study published Wednesday in the journal Cell Report Methods. These molecules can be collected by a simple saliva sample.
“We analyzed data from around 220 patients with 11 different cancers and identified differences in glycan substructure depending on cancer type,” explained Daniel Bojar, associate lecturer in bioinformatics at the University of Gothenburg and lead author of the study, in a press release.
Glycans are thus used to identify inflammation or disease, it is indicated.
Researchers say AI can find patterns in the way glycans look when a patient has cancer. When the glycan’s “structure” is linked to a form of cancer, it might provide a “precise answer” regarding the person’s health.
“By letting our new, AI-enhanced method work on large amounts of data, we were able to find these connections,” Bojar said.
Analyzing changes in glycan structure and observing patterns associated with different conditions constitutes a new research method for cancer detection, according to the press release.
The researchers said they were able to ensure that the cancer type and glycan structure were consistent for each test by including AI.
Previous research on glycans aimed to determine whether the sugar level was higher or lower, but this method is “unreliable,” according to the study.
“We can trust our results; they are statistically significant. If we know what we are looking for, it is easier to find the right result,” said Mr. Bojar.
With a grant of 4 million Swedish crowns (CA$519,304) from the Lundberg Foundation, the team hopes to develop a faster method to detect cancer itself and its type from saliva or a blood sample.
Bojar added that the team may be able to carry out clinical trials on human samples within four to five years.
1702490468
#simple #saliva #sample #detect #stage #cancer