Prognostic impact of artificial intelligence-based fully automated global circumferential strain in patients undergoing stress CMR

Abstract

Aims To determine whether fully automated artificial intelligence-based global circumferential strain (GCS) assessed during vasodilator stress cardiovascular (CV) magnetic resonance (CMR) can provide incremental prognostic value. Methods and results Between 2016 and 2018, a longitudinal study included all consecutive patients with abnormal stress CMR defined by the presence of inducible ischaemia and/or late gadolinium enhancement. Control subjects with normal stress CMR were selected using a propensity score-matching. Stress-GCS was assessed using a fully automatic machine-learning algorithm based on featured-tracking imaging from short-axis cine images. The primary outcome was the occurrence of major adverse clinical events (MACE) defined as CV mortality or nonfatal myocardial infarction. Cox regressions evaluated the association between stress-GCS and the primary outcome after adjustment for traditional prognosticators. In 2152 patients [66 ± 12 years, 77% men, 1:1 matched patients (1076 with normal and 1076 with abnormal CMR)], stress-GCS was associated with MACE [median follow-up 5.2 (4.8–5.5) years] after adjustment for risk factors in the propensity-matched population [adjusted hazard ratio (HR), 1.12 (95% CI, 1.06–1.18)], and patients with normal CMR [adjusted HR, 1.35 (95% CI, 1.19–1.53), both P < 0.001], but not in patients with abnormal CMR (P = 0.058). In patients with normal CMR, an increased stress-GCS showed the best improvement in model discrimination and reclassification above traditional and stress CMR findings (C-statistic improvement: 0.14; NRI = 0.430; IDI = 0.089, all P < 0.001; LR-test P < 0.001). Conclusion Stress-GCS is not a predictor of MACE in patients with ischaemia, but has an incremental prognostic value in those with a normal CMR although the absolute event rate remains low.

An update on cardiovascular disorders in systemic lupus erythematosus

“…Future perspectives include the use of artificial intelligence in accelerating the process of imaging, scar analysis with prediction of major arrhythmic events, and obtaining global circumferential strain, which may have prognostic value in patients with normal CMR. 118,119 However, it should be highlighted that, before considering introducing these solutions in patients with SLE, the algorithm ought to be optimized for this group, which is often underrepresented in the trials. The role of echocardiography cannot be ignored since, as in other populations, it can assess cardiac systolic and diastolic functions, valve abnormalities and contractility disorders and estimate the pulmonary hypertension probability.…”

A fully automated stress regional strain score as a prognostic marker of cardiovascular events in patients with normal CMR

“…The definitions of ischemia and LGE were based on established criteria ( 1 , 2 ). A fully automated machine learning algorithm was trained using a dense UNet on 3,000 CMR studies from the UK Biobank resource and validated on unseen CMR studies to assess the stress-GCS of each myocardial segment from short-axis cine images acquired at stress ( 3 ). All details of the AI software methodology have already been recorded ( 3 ).…”

“…A fully automated machine learning algorithm was trained using a dense UNet on 3,000 CMR studies from the UK Biobank resource and validated on unseen CMR studies to assess the stress-GCS of each myocardial segment from short-axis cine images acquired at stress ( 3 ). All details of the AI software methodology have already been recorded ( 3 ). To calculate the RSS ( 4 ), each segment was rated from 0 to 2 points according to the Ecc value of each layer to grade the LV regional myocardial function for the 16-segment model as follows: (i) 0 points if Ecc was more than −10% for severe regional dysfunction; (ii) 1 point if Ecc was between −17 and −10% for moderate regional dysfunction; and (iii) 2 points if Ecc was <−17% for good regional function.…”

“…Stress cardiovascular magnetic resonance (CMR) imaging has emerged as an accurate and cost-effective modality without ionizing radiation for risk stratification using ischemia and late gadolinium enhancement (LGE) as prognostic markers (1). Beyond these traditional stress CMR findings, recent studies have highlighted the incremental prognostic value of global longitudinal or circumferential strain using feature-tracking imaging measured during vasodilator stress (2), especially in patients with normal stress CMR, defined by the absence of ischemia and LGE, regardless of the LVEF value or the presence of wall motion abnormalities (3). Recent studies have shown that the regional circumferential myocardial strain (Ecc) could be a more accurate predictor of cardiovascular events than the LVEF value or global Ecc (4,5).…”