Saijo Y, Zheng R, Okushi Y
… +6 more, Nomura Y, Hirata Y, Inoue H, Yamada H, Kusunose K, Sata M
Eur Heart J Digit Health
· 2026 Jul · PMID 42388419
·
Full text
AIMS: Global longitudinal strain (GLS) is essential for the early detection of cancer therapy-related cardiac dysfunction (CTRCD). A fully automated echocardiographic analysis system using artificial intelligence (AI) ma...AIMS: Global longitudinal strain (GLS) is essential for the early detection of cancer therapy-related cardiac dysfunction (CTRCD). A fully automated echocardiographic analysis system using artificial intelligence (AI) may improve workflow efficiency in cardio-oncology. We sought to evaluate the feasibility and diagnostic performance of a fully automated AI-based echocardiographic system in breast cancer patients receiving cardiotoxic chemotherapy. METHODS AND RESULTS: In this prospective observational study, patients with breast cancer undergoing anthracyclines and/or HER2-targeted therapy between January 2022 and June 2025 were enrolled. Transthoracic echocardiography was performed at baseline and every 12 weeks. GLS was measured manually by two experts and automatically by a fully automated AI-based analysis system. A total of 92 patients (456 echocardiographic studies) were analysed. AI-derived GLS values were significantly lower than expert measurements (17.7 ± 2.9% vs. 18.4 ± 2.8%, = 0.007). Correlation and agreement between the two methods were moderate ( = 0.64, intraclass correlation coefficient = 0.63). On linear mixed-effects modelling, longitudinal changes in GLS were not significantly different between methods ( = 0.72). GLS-based CTRCD was detected in 31.5% of patients by experts and 34.8% by AI ( = 0.58), with similar detection timing ( = 0.47). Diagnostic agreement was substantial (κ = 0.68, < 0.001). CONCLUSION: The fully automated AI-based echocardiographic system demonstrated acceptable agreement and diagnostic performance for GLS assessment and showed a similar ability to track temporal relative GLS changes and identify CTRCD. However, systemic underestimation of absolute GLS values may contribute to threshold-based classification discordance in borderline cases.
Raikhelkar J, Bai Z, Beecy AN
… +20 more, Richter I, Liu F, Nizam NB, Kishore V, Kelsey C, vanMaanen D, Ruhl J, Tesfuzigta N, Lancet E, Leb J, Legasto A, Elias P, Poterucha T, Kumaraiah D, Prince M, Wang F, Sayer G, Estrin D, Sabuncu M, Uriel N
Eur Heart J Digit Health
· 2026 Jul · PMID 42388418
·
Full text
AIMS: Heart failure (HF), a major global health challenge, affects millions worldwide and poses substantial healthcare and economic burdens. It is estimated that a large proportion of those with early systolic dysfunctio...AIMS: Heart failure (HF), a major global health challenge, affects millions worldwide and poses substantial healthcare and economic burdens. It is estimated that a large proportion of those with early systolic dysfunction remain asymptomatic at a stage when guideline-directed medical therapies have been shown to prevent disease progression. To develop an artificial intelligence (AI) model capable of predicting abnormal left ventricular ejection fraction (EF) directly from static, non-gated, non-contrast chest computed tomography (CT) scans as a form of opportunistic screening. METHODS AND RESULTS: Using a multi-institutional dataset of 34 058 paired non- contrast CT images and echocardiogram reports from two academic centres, we trained our model of classification for predicting left-ventricle ejection fraction (LVEF) categories: abnormal EF (EF < 50%) vs. normal on 25 948 studies. We validated the model on 8110 paired chest CT and echocardiogram results from a separate institution. The model achieved an area under the receiver operating characteristic (AUROC) curve of 0.786 on the hold-out test set and 0.762 on external validation to detect an abnormal EF (<50%). Beyond strong predictive performance, the AI model surpassed expert radiologists in both accuracy and efficiency and provided interpretable visualizations highlighting imaging features linked to reduced LVEF. CONCLUSION: In this study, we developed and validated an AI model capable of predicting abnormal LVEF directly from static, non-gated, non-contrast chest CT scans, a novel application for an imaging modality typically used for unrelated indications as a form of opportunistic screening. This technology holds significant promise for early detection of systolic HF, reducing the diagnostic gap, and improving outcomes in asymptomatic HF patients.
Chiou T, Minga I, Subashchandran V
… +21 more, Singulane CC, Patel AR, Zareba KM, Lu E, Goyal A, Singh J, Elliott MD, Nadig V, Fernandes F, Vieira ML, Fadl S, Trankle C, Shah DJ, Gabr EM, Poonawalla M, Mirales F, Sarswat N, Pursnani A, Patel H, Addetia K, Slivnick J
AIMS: While cardiac magnetic resonance (CMR) provides prognostic value in transthyretin cardiac amyloidosis (ATTR-CA), current ATTR-CA staging relies on serum biomarkers. We evaluated the incremental value of incorporati...AIMS: While cardiac magnetic resonance (CMR) provides prognostic value in transthyretin cardiac amyloidosis (ATTR-CA), current ATTR-CA staging relies on serum biomarkers. We evaluated the incremental value of incorporating CMR parameters into the National Amyloidosis Center (NAC) staging and assessed their utility in guiding evaluation for advanced heart failure (HF) therapies and emerging disease-modifying treatments. METHODS AND RESULTS: We retrospectively analyzed a multicenter cohort of 266 ATTR-CA patients who underwent CMR between 2007-2023. Cox regressions were used to assess time to death. A baseline model was constructed using the NAC stage. CMR predictor variables were selected a priori based on clinical relevance and non-collinearity, then refined using stepwise backward elimination regression with NAC stage control; variables retained in ≥60% of 1,000 bootstrapped samples were included. Internal validation was performed via bootstrapping, with performance reported as Harrell's C-statistic and calibration slope. Decision curve analysis evaluated clinical utility.85 patients (32%) died over a median follow up of 20 months (IQR 8-35). Extracellular volume (ECV ≥59%, HR 2.45, 95% CI 1.2-5.2, p = 0.020) and indexed left atrial volume (LAVi ≥54 ml/m2, HR 2.00, 95% CI 1.1-3.7, p = 0.026) were independently associated with mortality after NAC adjustment and improved prognostic accuracy across all biomarker stages. When risk prediction was framed around initiation of advanced HF or emerging disease-modifying therapies, incorporating CMR alongside NAC staging facilitated identification of 28 additional high-risk patients per 1,000. CONCLUSION: CMR-derived ECV and LAVi were associated with incremental prognostic value in ATTR-CA beyond biomarker staging and may inform clinical risk stratification.
Surkova E, Gimelli A, Giannopoulos AA
… +13 more, Marsan NA, Baggiano A, Cikes M, Baritussio A, Ramkisoensing AA, Dweck MR, Gonzalez-Del-Hoyo M, Aguero J, Bertrand PB, Fontana M, Inciardi R, Lu MT, Delgado V
Cardiovascular imaging is integral to modern clinical trials of new pharmaceuticals or devices, enabling refined eligibility, mechanistic insight, and sensitive assessment of treatment response and safety. Potential hete...Cardiovascular imaging is integral to modern clinical trials of new pharmaceuticals or devices, enabling refined eligibility, mechanistic insight, and sensitive assessment of treatment response and safety. Potential heterogeneity in data acquisition, analysis, and reporting may affect reproducibility and interpretability across multicentre settings. Rigorous standardization and fit-for-purpose validation of imaging endpoints can improve statistical efficiency, reduce trial duration and cost, and strengthen generated evidence. This Scientific Statement outlines a reference framework for the implementation of cardiovascular imaging in clinical trials. We provide considerations on use of imaging parameters as eligibility criteria in clinical trials, for efficacy signals evaluation, and for assessment of safety. We define principles for clinical, analytical, and operational validation of imaging endpoints, and discuss concepts of minimal clinically important change and minimal detectable change. Additionally, we discuss feasibility considerations for use of cardiovascular imaging endpoints in multicentre clinical trials where differences in equipment and local experience may exist. We delineate standards for harmonization, centralized analysis, and quality control in clinical trials, as well as challenges and opportunities of the integration of artificial intelligence within core-lab workflows. Lastly, we identify gaps in knowledge, challenge of preclinical-clinical translatability and highlight training needs and innovation priorities.
Ou Z, Xie L, Xiao H
… +10 more, Cui B, Wang K, Ma Y, Zhao M, Qiu Y, Zhang Y, Zhang Z, Qian D, Liu B, Zhao X
Eur Heart J Imaging Methods Pract
· 2026 Jan · PMID 42376680
·
Full text
AIMS: Macrophages play a crucial role in coronary artery plaque development and can be quantified as circumferential arc features via optical coherence tomography (OCT). However, the prognostic implications of macrophage...AIMS: Macrophages play a crucial role in coronary artery plaque development and can be quantified as circumferential arc features via optical coherence tomography (OCT). However, the prognostic implications of macrophage arc characteristics remain underexplored. METHODS AND RESULTS: In this multicentre, retrospective study, consecutive patients with coronary artery disease (CAD) undergoing OCT between January 2017 and April 2023 were enrolled. The macrophage arc was evaluated using maximum arc, mean arc, and mean arc score (MAS) in the target vessel. Among 1025 patients (1173 vessels), 61 (5.9%) experienced major adverse cardiovascular events (MACEs). Receiver operating characteristic analysis identified optimal predictive thresholds: maximum arc ≥ 157.5°, mean arc ≥ 97.88°, and MAS ≥ 2.27 (all < 0.001). Elevated mean arc [hazard ratio (HR) = 7.628, < 0.0001], maximum arc (HR = 6.902, < 0.0001), and MAS (HR = 6.704, < 0.0001) were independently associated with MACEs. When combined with thin-cap fibroatheroma (TCFA) status, these parameters demonstrated enhanced predictive power: mean arc ≥ 97.88° + TCFA (HR = 8.779, < 0.0001), maximum arc ≥ 157.5° + TCFA (HR = 8.149, < 0.0001), and MAS ≥ 2.27 + TCFA (HR = 7.509, < 0.0001). Notably, among TCFA-negative patients, a mean arc ≥ 97.88° showed markedly improved predictive capacity for MACEs (HR = 6.685, < 0.001), as did maximum arc ≥ 157.5° (HR = 4.490, < 0.001) and MAS ≥ 2.27 (HR = 5.126, < 0.001). CONCLUSION: Macrophage arc parameters are strongly associated with long-term cardiovascular risk, serving as novel OCT-derived biomarkers for patients with CAD.
Eur Heart J Case Rep
· 2026 Jun · PMID 42376164
·
Full text
BACKGROUND: Multisystem thromboembolism is a rare but potentially fatal phenomenon that can develop in patients with underlying hypercoagulability and rapidly progress to multiorgan failure if not promptly identified. Co...BACKGROUND: Multisystem thromboembolism is a rare but potentially fatal phenomenon that can develop in patients with underlying hypercoagulability and rapidly progress to multiorgan failure if not promptly identified. Concurrent arterial and venous embolic events should raise suspicion for paradoxical embolism, particularly in patients with a patent foramen ovale (PFO). CASE SUMMARY: A 63-year-old male with a history of malignancy, renal transplant on tacrolimus, and limited mobility presented with dyspnoea and abdominal discomfort. During initial evaluation, he developed acute chest pain, with ECG demonstrating acute posterior myocardial infarction (MI) requiring emergent percutaneous coronary intervention. A CT angiogram subsequently revealed bilateral pulmonary emboli (PE) with right heart strain. After percutaneous management of both PE and MI, he developed worsening lactic acidosis and multiorgan failure. A repeat abdominal CT demonstrated acute mesenteric ischaemia with extensive pneumatosis intestinalis. Transthoracic echocardiography with bubble study revealed a PFO with right-to-left shunt, suggesting paradoxical embolism as the aetiology of simultaneous PE, MI, and mesenteric ischaemia. DISCUSSION: This case illustrates a presentation of possible PFO-mediated multisystem thrombosis across coronary, pulmonary, and mesenteric circulations. Persistent or unexplained lactic acidosis following treatment of known thrombotic events should prompt urgent abdominal imaging, particularly in intubated or non-communicative patients who cannot report pain out of proportion from physical examination. Early recognition of paradoxical embolism is essential in preventing delays in diagnosing occult mesenteric ischaemia, a complication with high mortality when detected late.
Eur Heart J Case Rep
· 2026 Jun · PMID 42370232
·
Full text
BACKGROUND: Transcatheter aortic valve replacement (TAVR) for native aortic regurgitation (AR) remains technically challenging due to the absence of annular calcification and difficulties in achieving stable anchoring. M...BACKGROUND: Transcatheter aortic valve replacement (TAVR) for native aortic regurgitation (AR) remains technically challenging due to the absence of annular calcification and difficulties in achieving stable anchoring. Mechanical complications such as anchoring strut fracture are rare but may have implications for long-term valve durability. CASE SUMMARY: A 64-year-old man with severe symptomatic native AR underwent transapical TAVR using a 29-mm self-expanding J-Valve system. Routine echocardiography and gated CT on postoperative day 7 identified an isolated fracture of the right coronary sinus anchoring strut without migration, leaflet dysfunction, or haemodynamic compromise. No balloon post-dilatation was performed. Serial multimodal imaging over nearly 3 years demonstrated persistent structural stability, preserved valve function, and marked left-ventricular reverse remodelling. DISCUSSION: This case provides long-term multimodal imaging follow-up of isolated anchoring strut fracture after TAVR for native AR. Early fracture detection and absence of calcification support a deployment-related stress mechanism rather than late cyclic fatigue. Although this favourable evolution suggests that isolated fracture does not necessarily result in immediate structural valve dysfunction, prognostic conclusions cannot be generalized. Careful, individualized imaging surveillance remains essential.
Eur Heart J Case Rep
· 2026 Jun · PMID 42370231
·
Full text
BACKGROUND: The Micra transcatheter pacing system provides a leadless alternative for patients requiring ventricular pacing. When a leadless device reaches end of service or fails prematurely, a second device is commonly...BACKGROUND: The Micra transcatheter pacing system provides a leadless alternative for patients requiring ventricular pacing. When a leadless device reaches end of service or fails prematurely, a second device is commonly implanted. CASE SUMMARY: We report a 91-year-old man with premature Micra AV battery depletion 28 months after implantation. During the second implantation, mechanically mediated device-device interaction caused intermittent oversensing. Oversensing was resolved by increasing the sensing threshold, which avoided device repositioning or retrieval. DISCUSSION: Suspected mechanically mediated interaction between sequential Micra devices may cause oversensing and pacing inhibition. In patients with clinically stable condition and adequate intrinsic R-wave amplitude, programming optimization may be considered before invasive revision; however, future management should account for cumulative right ventricular device burden.