Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

AI can predict certain forms of esophageal and stomach cancer

Aug 23, 2023 - michiganmedicine.org
A research team led by Joel Rubenstein, M.D., M.S., at the Lieutenant Colonel Charles S. Kettles Veterans Affairs Center for Clinical Management Research, has developed an artificial intelligence tool, K-ECAN, to predict the risk of esophageal and stomach cancer. The tool uses data from electronic health records (EHR) such as patient demographics, weight, previous diagnoses, and routine laboratory results. The team found that K-ECAN is more accurate than published guidelines or previously validated prediction tools and can predict cancer at least three years prior to a diagnosis.

The tool was tested on data from over 10 million U.S. veterans and the findings were published in Gastroenterology. The researchers believe that incorporating K-ECAN into EHR could alert healthcare providers about patients at an increased risk of developing esophageal adenocarcinoma and gastric cardia adenocarcinoma, potentially leading to increased screening and a decrease in preventable deaths. The study was funded by the Department of Defense and National Institutes of Health.

Key takeaways:

  • A team of researchers led by Joel Rubenstein, M.D., M.S., developed an artificial intelligence tool called K-ECAN to predict the risk of developing esophageal adenocarcinoma and gastric cardia adenocarcinoma.
  • The tool uses basic information available in the electronic health record (EHR) to determine an individual's risk, and is more accurate than published guidelines or previously validated prediction tools.
  • K-ECAN can identify people at elevated risk of these cancers, regardless of whether they have symptoms of gastroesophageal reflux disease (GERD), a known risk factor.
  • Incorporating K-ECAN into the EHR could alert providers to patients at increased risk, potentially leading to increased screening and a decrease in preventable deaths from these cancers.
View Full Article

Comments (0)

Be the first to comment!