Prognostic significance of artificial intelligence-quantified late gadolinium enhancement on cardiac magnetic resonance in hypertrophic cardiomyopathy

Q: What is the clinical evidence from this study?

Study design: Cohort. Population: Hypertrophic cardiomyopathy (n=142). Intervention: High AI-quantified late gadolinium enhancement (≥ 15%) vs. Low late gadolinium enhancement (< 15%). Primary outcome: Composite of cardiovascular death (including sudden cardiac death) and SCD-equivalent events (adjusted HR 4.67, 95% CI 1.43-15.30, p=0.011).

Q: What does this research mean for the field?

High AI-quantified late gadolinium enhancement burden (≥15%) on cardiac magnetic resonance is independently associated with an increased risk of cardiovascular death and sudden cardiac death-equivalent events in patients with hypertrophic cardiomyopathy. Novelty: ClaimNovelty.CONFIRMATORY. Consensus alignment: ConsensusAlignment.NEUTRAL.

Young-Sang Jeong; Jong-Il Park; Kang-Un Choi; Jong‐Ho Nam; Chan‐Hee Lee; Jang‐Won Son; Ung Kim; Jong‐Seon Park; Eunjung Kong

doi:10.3904/kjim.2026.065

September 1, 2026The Korean Journal of Internal MedicineOpen Access

Prognostic significance of artificial intelligence-quantified late gadolinium enhancement on cardiac magnetic resonance in hypertrophic cardiomyopathy

View Full Paper

Ask AI

Bookmark

Share

Key result

High AI-quantified late gadolinium enhancement (≥15%) was independently associated with an increased risk of cardiovascular death and SCD-equivalent events (adjusted HR 4.67).

Figures

Why the study?

The prognostic value of artificial intelligence-based late gadolinium enhancement quantification using cardiovascular magnetic resonance in hypertrophic cardiomyopathy patients was not established.

Does artificial intelligence-quantified high late gadolinium enhancement (≥ 15%) predict adverse cardiovascular outcomes in patients with hypertrophic cardiomyopathy?

Key Points

To evaluate the prognostic value of artificial intelligence-based quantification of late gadolinium enhancement using cardiovascular magnetic resonance in patients with hypertrophic cardiomyopathy.
Retrospectively analyzed 142 patients with hypertrophic cardiomyopathy (mean age 58.5 ± 13.7 yr; 72.5% men) who underwent cardiac magnetic resonance at Yeungnam University Medical Center between 2015 and 2023.
Quantified late gadolinium enhancement extent using an AI-based segmentation algorithm with a 6-standard deviation method, categorizing patients by high (≥ 15%) versus low (< 15%) burden.
Tracked patients over a median follow-up of 59 months for a primary composite outcome of cardiovascular death, including sudden cardiac death and sudden cardiac death-equivalent events.
The primary outcome occurred in 21.2% (7/33) of patients in the high late gadolinium enhancement group compared with 4.6% (5/109) in the low group (p = 0.0067).
Late gadolinium enhancement burden ≥ 15% independently predicted the primary outcome after adjustment for age and left ventricular ejection fraction (adjusted HR 4.67, 95% CI 1.43–15.30, p = 0.011).
An exploratory receiver operating characteristic cutoff of 8% (area under the curve 0.821) demonstrated primary outcome rates of 18.2% in the ≥ 8% group versus 0% in the < 8% group (p < 0.001).

Study Design

Type

Cohort (n=142)

Multicenter

No

Structured PICO

Does artificial intelligence-quantified high late gadolinium enhancement (≥ 15%) predict adverse cardiovascular outcomes in patients with hypertrophic cardiomyopathy?

P

Population

142 adults with hypertrophic cardiomyopathy evaluated with AI-quantified cardiac MRI, followed for a median of 59 months.

E

Exposure

High late gadolinium enhancement (LGE ≥ 15%) quantified using a commercially available deep learning-based artificial intelligence (AI) segmentation algorithm (Myomics) on 3.0-T cardiac PET-MR images.

C

Comparator

Low late gadolinium enhancement (LGE < 15%) quantified using the same AI-based algorithm.

O

Outcome

Composite of cardiovascular death (including sudden cardiac death [SCD], heart failure-related death, and cardiogenic shock-related death) and SCD-equivalent events (aborted SCD, sustained ventricular tachycardia/ventricular fibrillation, or appropriate ICD shock).composite

Main Result

Hazard Ratio: 4.67 (95% CI 1.43–15.3)

Absolute Event Rate: 21.2% vs 4.6%

p-value: p=0.011

Limitations

Retrospective, single-center design introduces selection bias and limits generalizability.
Small sample size and limited statistical power, especially for the absence of events in patients with LGE < 8%.
Potential for overfitting and optimism bias since the 8% cutoff was derived and evaluated within the same cohort.
Ambulatory ECG data for NSVT assessment were not uniformly available.
Exclusion of patients unable to undergo CMR due to severe clinical conditions or early death.
Lack of direct head-to-head comparison with manual LGE assessment.
Absence of events in patients with LGE < 8% should be interpreted cautiously due to limited statistical power and sample size.
Optimal cutoff derived and evaluated within the same cohort raises possibility of overfitting and optimism bias.
NSVT was only analyzed descriptively in a subset due to missing ambulatory ECG data and excluded from multivariable analysis.
No direct head-to-head comparison with manual LGE assessment to confirm incremental accuracy.

Implication

Automated AI-based quantification of late gadolinium enhancement ≥ 15% is an independent predictor of adverse cardiovascular outcomes in patients with hypertrophic cardiomyopathy, offering an objective and reproducible biomarker for risk stratification.

Abstract

BACKGROUND/AIMS: This study aimed to evaluate the prognostic value of artificial intelligence (AI)-based late gadolinium enhancement (LGE) quantification using cardiovascular magnetic resonance (CMR) in patients with hypertrophic cardiomyopathy (HCM). METHODS: We retrospectively analyzed 142 patients with HCM (mean age 58.5 ± 13.7 yr; 72.5% men) who underwent CMR at Yeungnam University Medical Center between 2015 and 2023. LGE was quantified using an AI-based segmentation algorithm with a 6-standard deviation method. Patients were stratified into a high LGE group (≥ 15%) and a low LGE group (< 15%). The primary outcome was a composite of cardiovascular death, including sudden cardiac death (SCD) and SCD-equivalent events. RESULTS: Over a median follow-up of 59 months, the high LGE group experienced a higher incidence of the primary outcome compared with the low LGE group (21.2% vs. 4.6%, p = 0.0067). After adjustment for age and left ventricular ejection fraction, a high AI-quantified LGE burden (≥ 15%) remained independently associated with the primary outcome (adjusted hazard ratio 4.67, 95% confidence interval 1.43-15.30, p = 0.011). Receiver operating characteristic analysis determined an optimal LGE cutoff of 8% for predicting the primary outcome (area under the curve 0.821). Patients with LGE ≥ 8% exhibited markedly increased rates of the primary outcome (18.2% vs. 0%, p < 0.001) and SCD/SCD-equivalent events (13.6% vs. 0%, p = 0.00074). CONCLUSION: AI-based quantitative assessment of LGE is an independent predictor of adverse cardiovascular outcomes in patients with HCM and may represent a clinically meaningful imaging biomarker for risk stratification.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Jeong et al. (2026) conducted a cohort in Hypertrophic cardiomyopathy (n=142). High AI-quantified late gadolinium enhancement (≥ 15%) vs. Low late gadolinium enhancement (< 15%) was evaluated on Composite of cardiovascular death (including sudden cardiac death) and SCD-equivalent events (adjusted HR 4.67, 95% CI 1.43-15.30, p=0.011). High AI-quantified late gadolinium enhancement (≥15%) was independently associated with an increased risk of cardiovascular death and SCD-equivalent events (adjusted HR 4.67).

synapsesocial.com/papers/6ad0fcf33afa093ea9ad00fc https://doi.org/10.3904/kjim.2026.065

Topics

Hypertrophic cardiomyopathy

Cardiac MRI

Artificial intelligence in cardiology

View Full Paper

Ask AI

Bookmark

Share

Prognostic significance of artificial intelligence-quantified late gadolinium enhancement on cardiac magnetic resonance in hypertrophic cardiomyopathy

Figures

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

Topics

Prognostic significance of artificial intelligence-quantified late gadolinium enhancement on cardiac magnetic resonance in hypertrophic cardiomyopathy

Figures

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

More on Hypertrophic cardiomyopathy

More from The Korean Journal of Internal Medicine

Topics

Keep reading

More related papers

More on Hypertrophic cardiomyopathy

More from The Korean Journal of Internal Medicine