AI-enabled opportunistic measurement of liver steatosis in coronary artery calcium scans predicts cardiovascular events and all-cause mortality: an AI-CVD study within the Multi-Ethnic Study of Atherosclerosis (MESA)

Naghavi, M; Atlas, K; Reeves, A; Zhang, C; Wasserthal, J; Atlas, T; Henschke, CI; Yankelevitz, DF; Zulueta, JJ; Budoff, MJ; Branch, AD; Ma, N; Yip, R; Fan, W; Roy, SK; Nasir, K; Molloi, S; Fayad, Z; McConnell, MV; Kakadiaris, I; Maron, DJ; Narula, J; Williams, K; Shah, PK; Abela, G; Vliegenthart, R; Levy, D; Wong, ND

doi:10.1136/bmjdrc-2024-004760

Lipids & metabolic liver disease

Artificial intelligence (AI)-enabled opportunistic measurement of liver steatosis in coronary artery calcium scans predicts cardiovascular events and all-cause mortality: an AI-CVD study within the Multi-Ethnic Study of Atherosclerosis (MESA)

BMJ Open Diabetes Res CarePublished 12 Apr 2025Prospective cohort study

Main finding · Incident CVDResultHazard ratio 1.43 95% CI 1.08–1.89

Read the original article ↗PubMed

Cite

Authors' conclusion

AI-enabled liver steatosis measurement in CAC scans provides opportunistic and actionable information for early detection of individuals at elevated risk of CVD events and mortality, without additional radiation.

Study context

Population: Asymptomatic individuals in the Multi-Ethnic Study of Atherosclerosis (52% female, age 62±10 years) with coronary artery calcium (CAC) scans
Participants: 5,702 individuals

Exposure: Highest vs lowest quartile of liver attenuation index on CAC scans
Outcome: Incident CVD and mortality
Follow-up: 15 years

Methodological detailsAI-enabled opportunistic measurement, Cox proportional hazards regression adjusted for CVD risk factors and Agatston CAC score

AI-enabled opportunistic measurement
Cox proportional hazards regression adjusted for CVD risk factors and Agatston CAC score

Main finding

Incident CVD

Hazard ratio

1.43

95% CI 1.08–1.89

By group

Q419%CI 17%–22%

Q112%CI 10%–14%

Q4vs Q1

HR 1.43 (95% CI 1.08–1.89)

As reported in the abstract

Observational data: associations, not effects.

Further findings

Outcome	← Lower risk with Q4 ←→ Higher risk with Q4 →	HR (95% CI)
All-cause mortalityIndependent of CVD risk factors	0.20.5125	1.36 (1.10–1.67)
StrokeIndependent of CVD risk factors	0.20.5125	1.77 (1.09–2.88)
	0.20.5125Hazard ratio (log scale)

Events accrued · 15 years

CVD events: 751
Deaths: 1343

Liver attenuation index (LAI) by sex

LAI in females, mean±SD: 38±15%
LAI in males, mean±SD: 43±13%

Original publication

AI-enabled opportunistic measurement of liver steatosis in coronary artery calcium scans predicts cardiovascular events and all-cause mortality: an AI-CVD study within the Multi-Ethnic Study of Atherosclerosis (MESA). BMJ Open Diabetes Res Care. Published 12 April 2025. doi:10.1136/bmjdrc-2024-004760

Read the original article ↗

Composed by AI from the published abstract and checked against it. How Briefs are made →