AI Analysis Of CT Scans Finds 42.9% Of Patients Have Coronary Inflammation

TL;DR

For listenersOffer from Amazon

Turn quiet afternoons into listening time

• Thousands of audiobooks, podcasts and originals
• Listen on your phone, tablet or Echo — also offline
• Cancel anytime

Try Audible free →Free trial for new members

As an affiliate, we earn on qualifying purchases.Hide

A U.S. study by Biograph using Caristo Diagnostics’ AI analysis of coronary CT scans found elevated coronary inflammation in 42.9% of participating asymptomatic, conventionally low-risk adults. The company-reported findings also say routine blood markers and a risk calculator did not identify which participants had inflammation; whether the finding predicts future heart disease or changes outcomes remains unestablished.

Biograph says its first U.S. study using Caristo Diagnostics’ AI-powered CaRi-Heart analysis found elevated coronary inflammation in 42.9% of asymptomatic, low-risk participants whose coronary CT scans were assessed. The company also reported that routine blood tests and a standard cardiovascular risk calculator did not identify which participants had inflamed arteries, though the findings do not establish that the inflammation predicts future heart disease.

The company said the study combined coronary CT angiography (CCTA) with cardiometabolic profiling and Caristo’s CaRi-Heart and CaRi-Plaque technologies. Participants were described as asymptomatic and low risk under conventional assessment; the study was available to clinically eligible Biograph Black tier members. The source report does not state the number of participants, their demographic breakdown or the study’s recruitment period.

Biograph reported elevated inflammation in 42.9% of participants, with very high inflammation in at least one major heart artery in 17.9%. It also said about 47% of participants with no detectable coronary plaque nevertheless had elevated perivascular inflammation. These percentages describe the study participants, not the general population; the information provided does not give enough detail to judge how representative the group was.

According to the report, routine measures—including ApoB, non-HDL cholesterol, HbA1c, high-sensitivity C-reactive protein and the AHA PREVENT-ASCVD risk calculator—showed no correlation with the detected coronary inflammation and did not distinguish affected participants. That is the study authors’ reported finding, not evidence that these established measures are unhelpful for other clinical purposes. The company says the manuscript is available as a preprint.

What CT May Reveal Beyond Plaque

The results point to a possible gap between assessing plaque or narrowing and measuring inflammation in tissue around coronary arteries. If further research confirms the finding and connects it to future outcomes, this type of scan analysis could add information about cardiovascular risk among people who appear low risk on standard assessments. The current report, however, does not show that identifying inflammation prevents heart attacks, improves health, or should change treatment.

The distinction matters because a high rate within this study can draw attention to a potential signal without showing how often it occurs in other populations. Nor does a scan-based inflammation result, on its own, establish that an individual has coronary heart disease. Decisions about testing or care require clinical interpretation and evidence on benefits, harms and appropriate follow-up.

How the AI Scan Assessment Works

The study used CCTA imaging, which produces images of the coronary arteries, alongside AI analysis from CaRi-Heart to quantify coronary perivascular inflammation. CaRi-Plaque was included to assess plaque and stenosis. Biograph says CaRi-Heart has received FDA De Novo marketing authorization and describes it as the first and only solution authorized to quantify coronary inflammation from routine CCTA; CaRi-Plaque has FDA clearance for AI-assisted plaque and stenosis analysis. Those regulatory descriptions are from the company’s announcement.

Biograph frames the work as an effort to look beyond conventional cardiovascular screening. The central reported observation is that inflammation was detected in some participants without visible plaque, while the routine metrics examined did not identify those individuals. The study’s results are presented as an early research finding, rather than proof of a new screening standard.

““More than 42% of asymptomatic, conventionally low-risk adults had elevated coronary inflammation.””

— Biograph study statement

Limits of the Reported Findings

The announcement does not provide the participant count, detailed methods, follow-up period or full statistical results needed to assess the strength and generalizability of the findings. It also does not report whether participants later developed cardiovascular disease, or whether treatment based on the inflammation assessment changed outcomes. A preprint is available, but the supplied material does not say whether the work has undergone peer review.

The reported absence of correlation with selected blood tests and a risk calculator should be read within the study’s design and participant group. It does not establish that those tools fail to predict cardiovascular risk generally. It also remains unclear what thresholds define elevated and very high inflammation in this study, and what clinical action, if any, should follow a positive result.

Validation and Outcome Studies Ahead

The next evidence needed is independent research that reports full methods and participant characteristics, tests the finding in broader populations, and follows participants over time. Such work would help determine whether AI-measured coronary inflammation predicts cardiovascular events beyond existing risk assessments. Researchers would also need to test whether care guided by the result improves outcomes and establish how clinicians should interpret it.

For now, Biograph’s announcement presents the study as a signal for further investigation, not as proof that routine screening should change. Readers considering cardiovascular testing should discuss its role and any results with a qualified health professional.

Key Questions

What did the study report?

Biograph reported elevated coronary inflammation in 42.9% of participants in its study of asymptomatic, conventionally low-risk adults assessed with AI analysis of coronary CT angiography.

Does the 42.9% figure apply to everyone?

No. It is the reported proportion among the study participants. The announcement does not provide enough information about the sample or recruitment to establish how representative the group is of the wider population.

Did routine tests detect the inflammation?

Biograph said selected measures—including cholesterol markers, HbA1c, hs-CRP and the AHA PREVENT-ASCVD calculator—did not identify which participants had coronary inflammation in this study. That finding does not mean those measures are useless for other assessments.

Does coronary inflammation on the scan mean heart disease is certain?

No. The report does not establish that the scan finding predicts future disease in an individual. Its prognostic value and whether care guided by the result improves health outcomes remain open questions.

Source: hn