Truace
Subscribe
TRV-2026-2347Certified recordPeer-reviewed

Performance of artificial intelligence versus clinician left-ventricular segmentation of cardiac MRI for mortality prediction: a retrospective, multicentre, prognostic study

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 a…

Health · Good Space — documented gain · certified 2026-11-03 · v1 · article view · machine-readable

Current reading — gain

In 27,382 cardiac MRI patients, AI-derived ejection fraction fit mortality data better and discriminated marginally better than clinician-derived values (C index 0.669 vs 0.637).

What this doesn’t fix

The study was retrospective, and the authors state that the AI's potential for first-line measurement with clinician oversight should be investigated in prospective studies.

Evidence

Reader signal

How should this claim be treated?

Cite this record

Truvace Impact Record TRV-2026-2347, v1: “Performance of artificial intelligence versus clinician left-ventricular segmentation of cardiac MRI for mortality prediction: a retrospective, multicentre, prognostic study.” Truvace, 2026-11-03. /record/TRV-2026-2347 (accessed at citation time). sha256 b7a0aa7d816ffe22…

Calibration history

Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.

  1. Certifiedv1b7a0aa7d816f…

    Certified into the record

Verify this record
How to verify without trusting this page

Fetch the canonical text of any version from /api/record/TRV-2026-2347 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.