A new AI-based technology developed by Cedars-Sinai researchers accurately predicted which individuals would be affected by pancreatic ductal adenocarcinoma. based on what their CT scan images looked like years before the disease was diagnosed. This is a very important result for all oncology, because we are talking about a tool capable of preventing an inauspicious course of the type of cancer through the early diagnosis of one of the most difficult cancers to treat.
The results of the Research have been published in the scientific journal Cancer Biomarkers.
Pancreatic ductal adenocarcinoma: what is it?
Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive lethal neoplasm characterized by the lack of an early diagnosis and which does not respond adequately to drug therapies.
It is the most common type of pancreatic cancer and develops in the exocrine compartment: reaches over 90% of pancreatic cancer cases. Despite the advances made by oncology in studying the tumor biology of PDAC and the development of new therapeutic regimens, we are talking about a tumor that has an average 5-year survival rate of less than 10%.
Nearly 60% -70% of pancreatic ductal adenocarcinoma cases arise from the pancreatic head, and these cases are usually diagnosed earlier than tumors arising from the body and tail, as the pancreatic head contains the common bile duct.
The main and most common symptoms involve weight loss, abdominal pain and jaundice are the most common symptoms. Less common symptoms include new onset type 2 diabetes and thromboembolic disease. Classic treatments such as chemotherapy, surgery, and radiotherapy have been used extensively, but have not shown significant improvements in clinical outcomes.
Overall survival for pancreatic ductal adenocarcinoma remains poor and less than 20% of affected patients survive beyond the end of the first year. Surgical resection and chemotherapy have been successful in improving the survival of patients with early-stage pancreatic cancer, but these treatments are not sufficient for patients with advanced stages of the disease.
Pancreatic ductal adenocarcinoma: preventing it with artificial intelligence
“This artificial intelligence tool was able to capture and quantify very subtle and early signs of pancreatic ductal adenocarcinoma on CT scans years before the disease occurred. These are signs that the human eye would never be able to discern“, he has declared Debiao Li, director of Biomedical Imaging Research Instituteprofessor of biomedical sciences and imaging al Cedars-Sinai and senior author and correspondent of the study. There is also there Karl Storz chair in minimally invasive surgery in honor of George Berci.
Pancreatic ductal adenocarcinoma is not only the most common type of pancreatic cancer, it is also the one with poorly diagnosed late diagnosis. As explained above, fewer than 10% of people diagnosed with the disease live more than five years after diagnosis or treatment initiation, but recent studies have reported that early cancer detection can increase survival rates up to to 50%. However, there is currently no easy way to diagnose pancreatic cancer early.
“There are no unique symptoms that can provide an early diagnosis for pancreatic ductal adenocarcinoma“, he has declared Stephen J. Pandoldirector of basic and translational pancreas research and program director of the Gastroenterology Fellowship Program at Cedars-Sinai, and another author of the study. “This artificial intelligence tool may eventually be used to detect disease early in people undergoing CT scans for abdominal pain or other problems. “
The researchers carefully studied electronic health records to identify people who were diagnosed with cancer in the past 15 years and who had CT scans six months to three years before diagnosis. These CT images were considered normal at the time they were taken. The team identified 36 patients who met these criteria, most of whom had undergone CT scans in the emergency room due to abdominal pain.
The AI tool was trained to analyze these pre-diagnostic CT images of people with pancreatic cancer and compare them to CT images of 36 people who did not develop cancer. THE researchers reported that the model was 86% accurate in identifying people who would eventually find out they had pancreatic cancer and those who would not develop cancer.
The artificial intelligence model detected variations on the surface of the pancreas between people with cancer and healthy controls. These structural differences could be the result of molecular changes that occur during the development of pancreatic cancer.
“Our hope is that this tool will predict cancer early enough for more people to have the tumor completely removed through surgery.“, he has declared Touseef Ahmad Qureshi, scientist at Cedars-Sinai and first author of the study.
Researchers are currently collecting data from thousands of patients in health centers across the United States to continue studying the prediction ability of artificial intelligence.
#Pancreatic #ductal #adenocarcinoma #predicts #onset