ProFound AI Risk is supported by a recent study led by researchers at the Karolinska Institutet based on the prospective screening cohort, KARolinska MAmmography Project for Risk Prediction of Breast Cancer (KARMA), which recruited women from 2011-2017. Of 70,877 participants in the KARMA cohort, 974 women with incident cancers and 9,376 healthy women were sampled. ProFound AI Risk reached an area under the curve (AUC) of 0.73 (95% CI 0.71, 0.74). AUC is a standard performance measurement for AI technology that incorporates sensitivity and specificity into a single metric of overall performance. ProFound AI Risk’s AUC of 0.73 indicates high accuracy for risk assessment.
“The Profound AI Risk model performs better than any other current model,” according to the study’s principal investigator, Per Hall, MD, Professor/Senior Physician at the Karolinska Institutet. “The model is a short term risk model which is an advantage in the screening setting, builds heavily on analyses of mammograms, has a flexibility that allows users to choose variables included in the model, is easy and cheap to implement and has little requirement of staff and systems to manage the data.”
Ad Statistics
Times Displayed: 172926
Times Visited: 3140 For those who need to move fast and expand clinical capabilities -- and would love new equipment -- the uCT 550 Advance offers a new fully configured 80-slice CT in up to 2 weeks with routine maintenance and parts and Software Upgrades for Life™ included.
Researchers also found a statistically significant superior performance when comparing the ProFound AI Risk model to existing risk models at two years, such as the Tyrer-Cusick v8 model (+11 points) or GAIL model (+12 points), all including breast density within their calculations. Researchers concluded ProFound AI Risk identified women at high likelihood of being diagnosed with breast cancer within two years of a negative screen and in possible need of supplemental screening.i
“ProFound AI Risk is a powerful tool that may aid in the detection of interval cancers, or lesions that are detected between routine mammography screenings,” according to Dr. Axel Gräwingholt, Radiologie am Theater, Paderborn, Germany. “In my experience using the technology following its CE Mark approval and launch in Europe earlier this year, I have found it offers valuable insights for clinicians who may be looking to provide a stratified risk assessment for patients, and is easy to use compared to other breast cancer risk models.”
ProFound AI Risk is currently available on an introductory basis for 2D mammography and will subsequently be available for the rapidly growing 3D mammography market. It is the latest addition to iCAD’s Breast Health Solutions suite, which includes ProFound AI™ for Digital Breast Tomosynthesis (DBT), ProFound AI™ for 2D Mammography, and software solutions for breast density. ProFound AI Risk was CE marked and launched in Europe at the European Congress of Radiology (ECR) virtual meeting in July 2020.
