AI tool successfully identifies patients at high risk of CRC in real-world study

Results from the first live, physician-supported implementation of Medial EarlySign's machine learning-based cancer detecting solution were published in the Journal of Oncology.

The tool reviewed the files of 79,000 adult patients who had not been compliant with colorectal cancer screening. The tool determined approximately 688 men and women were at higher risk for CRC. They were recommended for further evaluation.

Physicians were notified and, in turn, followed up with their patients. Of the 688 flagged patients, 254 had a colonoscopy. From that, 19 cases of colorectal cancer were diagnosed as well as 22 advanced adenomas.

The results of the study show "this technology can successfully provide a safety net in clinical practice."

Medial EarlySign's CMO Ran Goshen, MD, said, "The implementation of machine learning-based algorithms to risk stratify populations at risk is commonly feared by many clinicians and population health managers as a hard-to-trust black box. In collaboration with [Tel Aviv, Israel-based Maccabi Healthcare Services], we have shown for the first time that given the correct set-up of clinical leadership and top-notch technology, obstacles and hurdles can be overcome."

Copyright © 2024 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.


Featured Webinars

Featured Whitepapers

Featured Podcast