Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
This research is Trending!
September 21, 2026Cardiovascular ResearchOpen Access

High AI-derived splenic ratio is linked to ~19% greater MACE risk.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Inadequate pharmacologic stress may limit the diagnostic and prognostic accuracy of myocardial perfusion imaging, and the splenic ratio has emerged as a potential imaging biomarker for stress adequacy.

Is high AI-derived splenic ratio associated with an increased risk of major adverse cardiovascular events in patients undergoing regadenoson stress PET MPI?

Population

16,650 patients from six sites in the REFINE PET registry undergoing 82Rb-PET MPI with regadenoson stress

Comparison

High AI-derived splenic ratio vs lower splenic ratio stratified by decile groups

Design

Retrospective multicentre cohort study using fully automated AI algorithms

Follow-up

Median 3.4 years

Key result

High AI-derived splenic ratio was associated with an increased risk of major adverse cardiovascular events (HR 1.19; 95% CI 1.06-1.34; P=0.005).

Authors

GRGiselle RamirezNDNaga DharmavaramASAakash Shanbhag

Discussion

Loading...

Member takes

Overview

High splenic ratio was associated with elevated MACE risk independent of ischemia; hypothesis-generating for incremental PET risk stratification beyond standard metrics.

Key Points

  • Determine the prognostic value of an artificial intelligence-derived splenic ratio for predicting major adverse cardiovascular events in patients undergoing regadenoson-stress cardiac PET.
  • Retrospectively analyzed 16,650 patients across six sites from the REFINE PET registry undergoing clinically indicated 82Rb-PET myocardial perfusion imaging with a median follow-up of 3.4 years.
  • Used automated AI algorithms to measure the splenic ratio (splenic uptake at stress versus rest) and stratified patients into decile groups.
  • Conducted survival analyses using Kaplan–Meier and Cox proportional hazards models adjusted for clinical risk factors, myocardial flow reserve, and ischemia.
  • Patients with a high splenic ratio in the testing cohort (n = 950) demonstrated a higher risk of major adverse cardiovascular events (HR 1.19, 95% CI 1.06–1.34, P = 0.005).
  • Among patients with preserved myocardial flow reserve (MFR ≥2; n = 8067), high splenic ratio remained independently associated with adverse outcomes (HR 1.43, 95% CI 1.20–1.70, P < 0.001).
  • In patients with preserved myocardial flow reserve and no ischemia (MFR ≥2, SDS <2; n = 6508), high splenic ratio was also independently associated with adverse events (HR 1.54, 95% CI 1.26–1.88, P < 0.001).

Study Design

Type

Cohort (n=16,650)

Multicenter

Yes

Structured PICO

Is high AI-derived splenic ratio associated with an increased risk of major adverse cardiovascular events in patients undergoing regadenoson stress PET MPI?

P
Population
16,650 patients undergoing clinically indicated 82Rb-PET myocardial perfusion imaging with regadenoson stress testing, followed for a median of 3.4 years.
E
Exposure
High artificial intelligence (AI)-derived splenic ratio (SR) (ratio of splenic uptake at stress vs. rest)
C
Comparator
Lower splenic ratio (patients stratified by SR into decile groups)
O
Outcome
Major adverse cardiovascular events (MACE)composite

Main Result

Hazard Ratio: 1.19 (95% CI 1.06–1.34)

p-value: p=0.005

Elevated AI-derived splenic ratio during regadenoson stress PET MPI is an independent prognostic biomarker for MACE, providing risk stratification even in patients with preserved myocardial flow reserve and no ischemia.

Trending Research#1 this week

Recent publication with media coverage on spleen's role in CAD; high expert commentary at ESC.

Social attention
85
Preprint velocity
60
News coverage
90
Conference
80
Expert commentary
85

Cite This Study

Ramirez et al. (2026) conducted a cohort in Clinically indicated myocardial perfusion imaging (n=16,650). High splenic ratio (SR) vs. Lower splenic ratio was evaluated on major adverse cardiovascular events (MACE) (HR 1.19, 95% CI 1.06-1.34, p=0.005). High AI-derived splenic ratio was associated with an increased risk of major adverse cardiovascular events (HR 1.19; 95% CI 1.06-1.34; P=0.005).

synapsesocial.com/papers/6ab088ca16abbdcb618ff236https://doi.org/10.1093/cvr/cvag184
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Comparing various AI approaches to traditional quantitative assessment of the myocardial perfusion in [82Rb] PET for MACE prediction2024 · 2 citations
  2. 2Prognostic implications of myocardial perfusion imaging by 82-rubidium positron emission tomography in male and female patients with angina and no perfusion defects2022 · 18 citations
  3. 3Artificial intelligence–derived stress ejection fraction in stress cardiac magnetic resonance with dipyridamole: bridging past insights with future innovations2024
  4. 4Going beyond summed stress scores: Correlating global and territorial coronary flow reserve by single photon emission tomography with routine myocardial perfusion imaging2024 · 3 citations
  5. 5Association of Summed Rest Score on Technetium‐99m Sestamibi With Exercise Capacity and Incident Adverse Outcomes in Hospitalized Patients With Nonischemic Cardiomyopathy: A Retrospective Analysis2026