[ad_1]
A team of scientists, led by US researchers, showed that a lab test using artificial intelligence tools had potential to more accurately determine which people with pancreatic cysts will develop pancreatic cancer in the future.
The description of the tool, which is currently a proof of concept, is published Wednesday in the journal Science Traslational Medicine and, according to officials, the results are "exciting, it must be validated prospectively ".
Called "CompCyst", this test integrates measurements of molecular and clinical markers of fluid from cysts and cysts. "Seems on track to significantly improve conventional clinical and imaging tests", says in a note the Johns Hopkins Medicine.
The test was developed from the patient's data, among those related to symptoms, tomography images and molecular features such as alterations of DNA in the cystic fluid.
Thus, the molecular profiles of a large number of pancreatic cysts (862) were evaluated, to which clinical and radiological data were added as part of a program using the same techniques. artificial intelligence clbadify patients into three different groups.
People with cysts without tumor potential and for whom periodic monitoring would not be necessary; cysts with low risk of progression to cancer and for which patients should be monitored periodically; and cysts for which surgery is recommended because of the high likelihood of progression to cancer.
Scientists discovered that surgery was not necessary in 45% of cases This unnecessary operation was done because the doctors could not determine if the cysts were dangerous.
If CompCyst had been used, 60 to 74% of patients – depending on the type of cyst – could have avoided unnecessary surgery, according to the same sources.
Pancreatic cysts – secretions of fluid in the pancreas – are common; they are found in 4% of people in their sixties and in 8% of over 70s. Some 800,000 people with pancreatic cysts are identified each year in the United States alone, although researchers say only a small proportion of them develop cancer.
Although most of these cysts are not cancerous, The dilemma faced by patients and physicians is the ability to distinguish between those who are precancerous and cysts that will not turn into tumors.Anne Marie Lennon, one of the authors of this work and physician of the Johns Hopkins Kimmel Cancer Center.
And, current clinical and imaging tests "often" do not do it, which makes it difficult to determine which patients will not need follow-upwhich will be necessary in the long term and to which patients an immediate withdrawal surgery should be applied.
That's why, says Christopher Wolfgang, nearly everyone diagnosed with a pancreatic cyst is being followed for the long term, and surgeons need to make risk-benefit recommendations with limited information.
"One rarely loses a cancer, but it is at the expense of an operation that might not have been necessary after the fact."Wolfgang, who summarizes, explains this study: this study directly addresses these fundamental problems of the management of these cysts.
[ad_2]
Source link
