A new study reveals that specific types of cancer, including esophageal and stomach cancer, could be predicted in advance using artificial intelligence (AI). The research, published in the Gastroenterology journal, suggests that implementing preventive measures can prove to be a lifesaver, potentially reducing mortality rates associated with these cancers.
Over the past five decades, there has been a concerning rise in cases of gastric cardia adenocarcinoma (GCA) and esophageal adenocarcinoma (EAC) in the United States and other western nations. These forms of cancer are known to have a high mortality rate.
Dr. Joel Rubenstein, a research scientist at the Lieutenant Colonel Charles S. Kettles Veterans Affairs Centre for Clinical Management Research and a professor of internal medicine at Michigan Medicine, explains that early detection is crucial for improving survival rates. "Screening can identify pre-cancerous changes in patients, such as Barrett’s esophagus, which is often found in individuals with long-term gastroesophageal reflux disease (GERD)," he states. "When detected early, patients can take proactive steps to prevent cancer."
While existing guidelines already consider screening for high-risk patients, Dr. Rubenstein emphasizes that many medical providers are still unfamiliar with this recommendation. He highlights that "many individuals who develop these types of cancer never had screening to begin with."
However, the integration of a new automated tool into the electronic health record (EHR) system could bridge the gap between medical provider awareness and individuals at an elevated risk of developing esophageal and gastric cardia adenocarcinoma. Dr. Rubenstein and his team harnessed the power of AI to analyze data from over 10 million US veterans.
Their creation, the Kettles Esophageal and Cardia Adenocarcinoma prediction tool, or K-ECAN for short, employs readily available EHR data, including patient demographics, weight, prior diagnoses, and routine laboratory results, to determine an individual's risk of developing these cancers. Dr. Rubenstein notes that this AI tool improves upon previous methods, offering a more accessible and efficient solution for identifying patients at risk.
With the potential to predict cancer at least three years prior to a diagnosis, K-ECAN offers an innovative way to identify individuals who are susceptible to esophageal adenocarcinoma and gastric cardia adenocarcinoma, regardless of whether they exhibit GERD symptoms or not. Dr. Rubenstein envisions this AI tool as a crucial asset in enhancing early detection and preventive measures.
The collaborative effort behind this study highlights the power of team science and AI in improving cancer prevention. Dr. Akbar Waljee, a senior author of the study, emphasizes the vital role played by collaboration between institutions and researchers.
With this groundbreaking AI capability integrated into the electronic health record system, doctors could receive automated notifications about patients at a higher risk of developing stomach and esophageal cancers. This promising advancement holds the potential to substantially reduce the burden of these life-threatening tumors.
Dr. Rubenstein concludes, "We are excited that this tool could potentially lead to increased screening and a decrease in preventable deaths. We look forward to further validating K-ECAN for broader use beyond the VA Health Services Research & Development Center of Innovation." This groundbreaking research marks a significant step toward enhancing cancer prevention through the power of AI and data science.
HT
