Zum Inhalt springen
Home » AI Technology Can Predict Cardiac Events

AI Technology Can Predict Cardiac Events

Caristo Diagnostics Limited, a global leader in cardiovascular disease diagnostics and risk prediction, announced the results of a landmark clinical study published in The Lancet that support the ability of Caristo’s CaRi-Heart® AI technology to quantify coronary artery inflammation and accurately predict cardiac events.

This landmark study, titled „Inflammatory risk and cardiovascular events in patients without obstructive coronary artery disease: the ORFAN multicentre, longitudinal cohort study,“ analysed results from the first 40,000 patients enrolled in the „ORFAN“ registry, the world’s largest study that evaluates coronary computed tomography angiography (CCTA) imaging biomarkers in predicting long-term cardiovascular outcomes.

Key study findings include:

Among patients undergoing CCTA, more than 80% did not have obstructive coronary artery disease (CAD) at the time of imaging, but twice as many fatal and non-fatal cardiac events occurred in that group
Coronary inflammation, as measured by Caristo’s CaRi-Heart FAI-ScoreTM, predicted fatal and non-fatal cardiac events (including heart attack and new heart failure), independently from traditional risk factors, routine clinical CCTA interpretation, calcium scoring and plaque quantification, at least 10 years in advance
Even among the 50% of patients who had no or minimal coronary plaque at the time of the initial CCTA, those with the most abnormal FAI-Score results experienced a 9.5-fold higher risk for cardiac mortality and 5.5-fold higher risk for major adverse cardiac events (MACE)
Caristo’s AI-Risk model, CaRi-Heart Risk Score, outperformed other scores in routine clinical use for prediction of cardiac mortality, and when presented to clinicians, resulted in changes of management decision in 45% of the patients. Most changes were due to clinicians‘ decision to target the previously undetected coronary inflammation.


https://pubmed.ncbi.nlm.nih.gov/31504423/