Artificial intelligence-enabled coronary plaque quantification for personalized risk assessment and lipid-lowering therapy: Insights from the FISH&CHIPS study ✰ .
Level 4 - case-series / case-control
Observational cohort combined with mathematical simulation/decision modeling.
PubMed 42006406 · doi:10.1016/j.ajpc.2026.101452
What was done
Researchers analyzed 7,899 adult patients undergoing clinically indicated coronary computed tomographic angiography (CCTA) across two UK sites in the FISH&CHIPS study. AI-enabled quantitative coronary plaque analysis (AI-CPA) measured total plaque volume (TPV), categorizing patients with plaque (n = 6,054) into DECIDE risk stages 1 to 4 (1–100, 101–250, 251–750, and >750 mm³, respectively). Authors modeled 10-year estimated risk reduction in cardiovascular death or non-fatal myocardial infarction and numbers needed to treat (NNT) based on treat-to-target LDL-C goals of <100, <70, <55, and <40 mg/dL across stages 1–4, respectively.
What was found
In the 6,054 patients with plaque (mean age 59.4 ± 11.7 years, 42.7% women), the modeled overall 10-year relative risk reduction was 19.1% with an NNT of 61. By plaque stage: - Stage 1: 10-year relative risk reduction 1.5%, NNT = 1,686 - Stage 2: 10-year relative risk reduction 18.2%, NNT = 59 - Stage 3: 10-year relative risk reduction 24.2%, NNT = 27 - Stage 4: 10-year relative risk reduction 33.8%, NNT = 11
Why it matters
This study demonstrates that AI-based coronary plaque quantification can stratify cardiovascular risk and could theoretically guide individualized intensity of lipid-lowering therapy.
Limits
Clinical benefit and NNT values were mathematically modeled rather than prospectively observed in an interventional trial. The abstract reports no empirical follow-up event data, treatment adherence rates, adverse events, or cost-effectiveness metrics, and the population was restricted to symptomatic patients from two UK sites.
Cited by
- supports Cleerly's AI-enabled coronary computed tomography angiography (CCTA) analysis can predict heart attacks up to five years in advance by quantifying soft coronary plaque.