Abstract 4145601: Prevalence and Distribution of Retinal and Deep Learning-Based Versus Actual Coronary Artery Calcium Scores: A Large South Korean Population Aged 21-90 Years

Introduction: Reti-CVD, a novel cardiovascular risk stratification tool derived from deep learning and retinal photography, offers a promising alternative to CT scan-measured Coronary Artery Calcium (CAC) scores in predicting cardiovascular events. This study investigates the profile of Reti-CVD scores using data from three medical centers in South Korea: GC iMED Gangbuk&Gangnam branches and Philip Medical Center. Hypothesis: Reti-CVD scores can effectively stratify cardiovascular risk across different age groups and genders and correlate with actual CAC scores, demonstrating their utility as predictive markers for cardiovascular risk. Methods: Data from 598,831 retinal images from Philip Medical Center and 74,859 from GC iMED Gangbuk&Gangnam branches were analyzed for Reti-CVD. The overall dataset consists of 45,858 individuals aged 21-90 years. The distribution of Reti-CVD and CAC scores across various age groups, segmented into ten-year increments, was examined. For 4,685 individuals with available follow-up data, longitudinal changes in Reti-CVD scores over an approximate two-year period were assessed using Pearson’s correlation analysis. Results: In both Reti-CVD and CAC distributions, each age group exhibited distinct score ranges, with increasing cardiovascular risk as age increased, as shown in Figures 1 and 2. Men had consistently higher scores, indicating gender differences. The longitudinal study further revealed a significant positive correlation between baseline and follow-up Reti-CVD scores (Correlation Coefficient: 0.158, p-value < 2.2e-16). Discussion: Reti-CVD score analysis in relation to age and gender exhibited similar trends to CAC scores, offering insights into cardiovascular risk profiles and enabling percentile assessments within specific gender and age groups. The correlation between baseline and follow-up scores emphasizes Reti-CVD's potential as a longitudinal cardiovascular risk marker, suggesting the need for closer monitoring and intervention strategies for those with higher initial scores.

Authors

Institutions

Publication Details

Journal
Circulation
Published
2024-11-12
DOI
https://doi.org/10.1161/circ.150.suppl_1.4145601
Primary Topic
Retinal Imaging and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Abstract 4145601: Prevalence and Distribution of Retinal and Deep Learning-Based Versus Actual Coronary Artery Calcium Scores: A Large South Korean Population Aged 21-90 Years

Sahil Thakur, Beom Hee Choi, Márcio Sommer Bittencourt, Isabela M. Benseñor et al.
Circulation
Retinal Imaging and Analysis
article

Abstract 4145601: Prevalence and Distribution of Retinal and Deep Learning-Based Versus Actual Coronary Artery Calcium Scores: A Large South Korean Population Aged 21-90 Years

Sahil Thakur, Beom Hee Choi, Márcio Sommer Bittencourt, Isabela M. Benseñor, Gabriel Jung, Hyeonmin Kim, Ronaldo Correa Fabiano, Cheong Hoon Seo, Jun Hwan Cho, Tyler Hyungtaek Rim, Tien Yin Wong, Yong Yu Tan, Giuliano Generoso, Chan Joo Lee, Sungha Park, Ching‐Yu Cheng, Yunnie Cho
article en

Abstract

Introduction: Reti-CVD, a novel cardiovascular risk stratification tool derived from deep learning and retinal photography, offers a promising alternative to CT scan-measured Coronary Artery Calcium (CAC) scores in predicting cardiovascular events. This study investigates the profile of Reti-CVD scores using data from three medical centers in South Korea: GC iMED Gangbuk&Gangnam branches and Philip Medical Center. Hypothesis: Reti-CVD scores can effectively stratify cardiovascular risk across different age groups and genders and correlate with actual CAC scores, demonstrating their utility as predictive markers for cardiovascular risk. Methods: Data from 598,831 retinal images from Philip Medical Center and 74,859 from GC iMED Gangbuk&Gangnam branches were analyzed for Reti-CVD. The overall dataset consists of 45,858 individuals aged 21-90 years. The distribution of Reti-CVD and CAC scores across various age groups, segmented into ten-year increments, was examined. For 4,685 individuals with available follow-up data, longitudinal changes in Reti-CVD scores over an approximate two-year period were assessed using Pearson’s correlation analysis. Results: In both Reti-CVD and CAC distributions, each age group exhibited distinct score ranges, with increasing cardiovascular risk as age increased, as shown in Figures 1 and 2. Men had consistently higher scores, indicating gender differences. The longitudinal study further revealed a significant positive correlation between baseline and follow-up Reti-CVD scores (Correlation Coefficient: 0.158, p-value < 2.2e-16). Discussion: Reti-CVD score analysis in relation to age and gender exhibited similar trends to CAC scores, offering insights into cardiovascular risk profiles and enabling percentile assessments within specific gender and age groups. The correlation between baseline and follow-up scores emphasizes Reti-CVD's potential as a longitudinal cardiovascular risk marker, suggesting the need for closer monitoring and intervention strategies for those with higher initial scores.

CirculationVol. 150(Suppl_1)
Singapore National Eye Center (SG), Severance Hospital (KR), Seoul National University Hospital (KR), University of Pittsburgh Medical Center (US), Hospital Universitário da Universidade de São Paulo (BR), Hospital São Paulo (BR)
Openalex Percentile: Top 66%
Retinal Imaging and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.