Related Experiment Video
Updated: Dec 19, 2025
Ultrasound Based Assessment of Coronary Artery Flow and Coronary Flow Reserve Using the Pressure Overload Model in Mice
Published on: April 13, 2015
Defining heterogeneity of epicardial functional stenosis with low coronary flow reserve by unsupervised machine
Rikuta Hamaya1,2, Masahiro Hoshino1, Taishi Yonetsu3
1Division of Cardiovascular Medicine, Tsuchiura Kyodo General Hospital, Ibaraki, Japan.
Insights
Low coronary flow reserve (CFR) is heterogeneous. Unsupervised machine learning identified three subgroups with distinct physiological traits and prognoses, guiding personalized treatment for epicardial coronary artery disease.
Area of Science:
- Cardiology
- Medical Imaging
- Computational Biology
Background:
- Low coronary flow reserve (CFR) is linked to poor prognosis but represents a heterogeneous condition.
- Understanding the physiological traits and clinical implications of different low CFR patterns is crucial for effective management.
Purpose of the Study:
- To define sub-phenotypes of epicardial coronary artery disease with low CFR using unsupervised machine learning.
- To investigate the physiological characteristics and clinical outcomes associated with these identified subgroups.
Main Methods:
- Hierarchical clustering was applied to data from 364 patients with low CFR (less than median) and fractional flow reserve ≤ 0.8.
- Analysis included detailed coronary flow physiology and vessel-oriented composite outcomes (VOCO).
Main Results:
- Three distinct physiological subgroups (PS) were identified: PS1 (high resting flow, LAD lesions), PS2 (low hyperemic flow, LAD lesions), and PS3 (non-LAD lesions, similar resting flow to PS1 but lower hyperemic Pd).
- Survival outcomes (VOCO) differed significantly between clusters (p=0.005), with PS3 exhibiting the highest VOCO rate.
- A significant interaction between percutaneous coronary intervention (PCI) and PSs was observed, suggesting differential treatment effects.
Conclusions:
- Unsupervised machine learning offers valuable insights into low CFR conditions.
- High resting flow with low hyperemic pressure in epicardial lesions may indicate a poor prognosis.
- Low hyperemic flow in the left anterior descending artery lesions might benefit from elective PCI.
Abstract:
Low CFR is associated with poor prognosis, whereas it is a heterogeneous condition according to the actual coronary flow, such as high resting or low hyperemic coronary flow, which should have different physiological traits and clinical implications. This study aimed to detect and define the sub-phenotypes of vessels with low coronary flow reserve (CFR) epicardial disease by unsupervised machine-learning methods. Hierarchical clustering was applied to 376 vessels from 364 patients with CFR less than the median and fractional flow reserve ≤ 0.8 from a global, multicenter registry. Detailed features of coronary flow physiology and survivals from vessel-oriented composite outcomes (VOCO) were assessed according to the clusters. Clustering defined three distinct physiological subgroups (PS). PS1 (n = 151) were characterized by high resting coronary flow, dominantly left anterior descending artery (LAD) lesions. PS2 (n = 131) were, in contrast, low hyperemic coronary flow, mainly LAD lesions. PS3 (n = 82) mostly consisted of non-LAD lesions with similar flow status to PS1 except for the low hyperemic Pd. Survivals from VOCO were significantly different according to the clusters (p = 0.005) and PS3 had the highest rate of VOCO. In a COX proportional model predicting VOCO, there was a significant interaction between PCI and PSs, suggesting potentially different effects of PCI on outcome between PS1 and PS2. The unsupervised machine-learning approaches provided unique insights into low CFR condition. Among low CFR epicardial lesions, high resting flow with low hyperemic Pd might be related to poor prognosis, and low hyperemic flow in LAD could benefit from elective PCI. CLINICAL TRIAL REGISTRATION INFORMATION: https://clinicaltrials.gov/ct2/show/NCT03690713 , NCT03690713.
