BibTex format
@article{Joy:2027:10.1016/j.landig.2026.101042,
author = {Joy, G and Punjabi, K and Searle, G and Abdulelah, Z and Gantur, T and Pierce, I and Thornton, GD and Meredith, B and Shiwani, H and Curtis, M and Cashin, S and Augusto, JB and Miranda, I and Fontana, M and Kellman, P and Howard, JP and Shun-Shin, M and Treibel, TA and Manisty, C and Orini, M and Schelbert, EB and Hughes, AD and Moon, JC and Davies, RH},
doi = {10.1016/j.landig.2026.101042},
journal = {Lancet Digit Health},
title = {Performance of artificial intelligence versus clinician left-ventricular segmentation of cardiac MRI for mortality prediction: a retrospective, multicentre, prognostic study.},
url = {http://dx.doi.org/10.1016/j.landig.2026.101042},
year = {2027}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - BACKGROUND: Ejection fraction, a key measure of cardiac function, is used in health care for clinical decision making and risk stratification. We hypothesised that a deep-learning artificial intelligence (AI) segmentation of ejection fraction obtained from cardiac MRI (CMR) outperforms expert clinician segmentation for the prediction of all-cause mortality. METHODS: In this retrospective, multicentre, prognostic study, we studied a cohort of 27 382 consecutive patients who underwent cardiac MRI (CMR) in the UK and the USA. Patients were referred for CMR from nine hospitals to Barts Heart Centre (BHC), London. Patients were identified from the reporting archive at BHC as having undergone a CMR between Oct 1, 2014 and Dec 31, 2019. A further cohort of patients was also identified from University of Pittsburgh Medical Centre (UPMC), Pittsburgh, PA, USA, as having undergone a CMR between June 1, 2010 and March 31, 2016. Mortality data were obtained from national and local databases. AI segmentation was done on all CMR studies, and Cox proportional hazards models were fitted to compare the prognostic value of AI-measured versus clinician-measured left-ventricular volume metrics. Model fit was compared using the Akaike Information Criterion (AIC), discrimination using C indices and the incremental value of AI over clinician segmentation using likelihood-ratio tests of nested models. FINDINGS: 27 382 patients received a baseline CMR (26 106 patients from BHC and 1276 from UPMC). The median follow-up was 5·6 years (IQR 4·4-6·9), during which 3458 (13%) of 27 382 patients died. AI ejection fraction showed better model fit (AIC 57 936 vs 58 097, ΔAIC 161 favouring AI) and marginally better discrimination (C index 0·669 vs 0·637; ΔC 0·033 [95% CI 0·026-0·041]). AI ejection fraction significantly improved model fit when added to clinician ejection fraction (χ2=168
AU - Joy,G
AU - Punjabi,K
AU - Searle,G
AU - Abdulelah,Z
AU - Gantur,T
AU - Pierce,I
AU - Thornton,GD
AU - Meredith,B
AU - Shiwani,H
AU - Curtis,M
AU - Cashin,S
AU - Augusto,JB
AU - Miranda,I
AU - Fontana,M
AU - Kellman,P
AU - Howard,JP
AU - Shun-Shin,M
AU - Treibel,TA
AU - Manisty,C
AU - Orini,M
AU - Schelbert,EB
AU - Hughes,AD
AU - Moon,JC
AU - Davies,RH
DO - 10.1016/j.landig.2026.101042
PY - 2027///
TI - Performance of artificial intelligence versus clinician left-ventricular segmentation of cardiac MRI for mortality prediction: a retrospective, multicentre, prognostic study.
T2 - Lancet Digit Health
UR - http://dx.doi.org/10.1016/j.landig.2026.101042
UR - https://www.ncbi.nlm.nih.gov/pubmed/42971896
ER -