AI Tool Accurately Predicts Cancer Three Years Prior to Diagnosis

Researchers at Michigan Medicine (Ann Arbor, MI, USA) have developed an automated tool integrated into the electronic health record (EHR). This tool has the potential to bridge the awareness gap between healthcare providers and patients with an elevated risk of developing EAC and GCA. The researchers employed a specific type of AI for analyzing data related to EAC and GCA rates across more than 10 million U.S. veterans in order to develop and validate the Kettles Esophageal and Cardia Adenocarcinoma prediction tool, or K-ECAN for short.

K-ECAN leverages readily accessible data from the EHR, including patient demographics, weight, prior diagnoses, and routine lab results, to gauge an individual's risk of developing EAC and GCA. Outperforming published guidelines and previously validated prediction tools, K-ECAN accurately predicts cancer at least three years ahead of a diagnosis. Integrating this AI tool into the EHR could automatically notify healthcare providers about patients at a higher risk of developing EAC and GCA.

“Symptoms of GERD, like heartburn, are an important risk factor for esophageal adenocarcinoma,” said Joel Rubenstein, M.D., M.S., professor of internal medicine at Michigan Medicine. “But most people with GERD symptoms will never develop esophageal adenocarcinoma and gastric cardia adenocarcinoma. In addition, roughly half of the patients with this form of cancer never experienced prior GERD symptoms at all. This makes K-ECAN particularly useful because it can identify people who are at elevated risk, regardless of whether they have GERD symptoms or not.”

Related Links:
Michigan Medicine