A new artificial intelligence tool accurately predicts certain forms of cancer at least three years prior to a diagnosis
The incidence of esophageal and stomach cancers, specifically esophageal adenocarcinoma (EAC) and gastric cardia adenocarcinoma (GCA), has been increasing over the last few decades in Western countries. However, new research from the Lieutenant Colonel Charles S. Kettles Veterans Affairs Center for Clinical Management Research and Michigan Medicine suggests that AI-driven screening and prediction tools could help detect these cancers early and prevent their progression.
The researchers developed an AI tool named Kettles Esophageal and Cardia Adenocarcinoma prediction tool (K-ECAN) that uses patient demographic data, weight, previous diagnoses, and routine lab results from electronic health records (EHRs) to assess an individual’s risk of developing esophageal and stomach cancers. The tool presents the patient’s risk to healthcare providers at opportune times, such as when they are due for screenings or refilling medication prescriptions.
K-ECAN was found to be more accurate than published guidelines or previously validated prediction tools, accurately predicting cancer diagnoses at least three years before they occur. The tool can be valuable in identifying individuals at elevated risk, regardless of whether they experience symptoms like gastroesophageal reflux disease (GERD) or not.
The researchers suggest that incorporating this AI tool into EHR systems could alert providers about patients at increased risk of these cancers, potentially leading to increased screening rates and a decrease in preventable deaths.
