Dharmavaram Naga L, Ramirez Giselle, Shanbhag Aakash, Miller Robert Jh, Kavanagh Paul B, Yi Jirong, Lemley Mark, Builoff Valerie, Marcinkiewicz Anna, Dey Damini, Hainer Jon, Wopperer Samuel, Knight Stacey, Le Viet T, Mason Steve, Alexanderson Erick, Carvajal-Juarez Isabel, Packard René Rs, Rosamond Thomas L, Al-Mallah Mouaz H, Slipczuk Leandro N, Travin Mark I, Acampa Wanda, Einstein Andrew J, Chareonthaitawee Panithaya, Berman Daniel S, Di Carli Marcelo F, Slomka Piotr J
Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, Cardiology, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USA.
Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA.
medRxiv. 2025 Jun 28:2025.06.27.25330278. doi: 10.1101/2025.06.27.25330278.
Inadequate pharmacologic stress may limit the diagnostic and prognostic accuracy of myocardial perfusion imaging (MPI). The splenic ratio (SR), a measure of stress adequacy, has emerged as a potential imaging biomarker.
To evaluate the prognostic value of artificial intelligence (AI)-derived SR in a large multicenter Rb-PET cohort undergoing regadenoson stress testing.
We retrospectively analyzed 10,913 patients from three sites in the REFINE PET registry with clinically indicated MPI and linked clinical outcomes. SR was calculated using fully automated algorithms as the ratio of splenic uptake at stress versus rest. Patients were stratified by SR into high (≥90th percentile) and low (<90th percentile) groups. The primary outcome was major adverse cardiovascular events (MACE). Survival analysis was conducted using Kaplan-Meier and Cox proportional hazards models adjusted for clinical and imaging covariates, including myocardial flow reserve (MFR ≥2 vs. <2).
The cohort had a median age of 68 years, with 57% male patients. Common risk factors included hypertension (84%), dyslipidemia (76%), diabetes (33%), and prior coronary artery disease (31%). Median follow-up was 4.6 years. Patients with high SR (n=1,091) had an increased risk of MACE (HR 1.18, 95% CI 1.06-1.31, p=0.002). Among patients with preserved MFR (≥2; n=7,310), high SR remained independently associated with MACE (HR 1.44, 95% CI 1.24-1.67, p<0.0001).
Elevated AI-derived SR was independently associated with adverse cardiovascular outcomes, including among patients with preserved MFR. These findings support SR as a novel, automated imaging biomarker for risk stratification in Rb PET MPI.
药物负荷不足可能会限制心肌灌注成像（MPI）的诊断和预后准确性。脾比值（SR）作为一种衡量负荷充足性的指标，已成为一种潜在的成像生物标志物。
评估人工智能（AI）衍生的SR在接受雷加昔布负荷试验的大型多中心Rb-PET队列中的预后价值。
我们回顾性分析了REFINE PET注册研究中来自三个地点的10913例患者，这些患者进行了临床指征的MPI检查并关联了临床结局。使用全自动算法计算SR，即负荷期与静息期脾脏摄取量的比值。根据SR将患者分为高（≥第90百分位数）和低（<第90百分位数）两组。主要结局是主要不良心血管事件（MACE）。使用Kaplan-Meier法和Cox比例风险模型进行生存分析，并对包括心肌血流储备（MFR≥2与<2）在内的临床和影像协变量进行校正。
该队列的中位年龄为68岁，男性患者占57%。常见危险因素包括高血压（84%）、血脂异常（76%）、糖尿病（33%）和既往冠状动脉疾病（31%）。中位随访时间为4.6年。高SR患者（n = 1091）发生MACE的风险增加（HR 1.18，95%CI 1.06 - 1.31，p = 0.002）。在MFR保留（≥2；n = 7310）的患者中，高SR仍然与MACE独立相关（HR 1.44，95%CI 1.24 - 1.67，p < 0.0001）。
AI衍生的SR升高与不良心血管结局独立相关，包括MFR保留的患者。这些发现支持SR作为Rb PET MPI风险分层的一种新型自动成像生物标志物。
