CT and MRI radiomics in cardiovascular risk prediction: a systematic review and meta-analysis by the EuSoMII Radiomics Auditing Group - Scorecard - MDSpire
Advertisement
CT and MRI radiomics in cardiovascular risk prediction: a systematic review and meta-analysis by the EuSoMII Radiomics Auditing Group
Clinical Scorecard: Radiomics from CT and MRI for Assessing Cardiovascular Risk: A Comprehensive Review and Meta-Analysis by the EuSoMII Radiomics Auditing Group
At a Glance
Category
Detail
Condition
Cardiovascular disease risk assessment
Key Mechanisms
Extraction of mineable imaging features from CT and MRI scans (radiomics) to reveal subtle patterns for diagnosis and prediction of cardiovascular events
Target Population
Patients undergoing cardiac CT or MRI imaging for cardiovascular risk evaluation
Care Setting
Cardiology imaging and diagnostic settings utilizing CT and MRI modalities
Key Highlights
Radiomics enables high-throughput extraction of imaging biomarkers not visible to the naked eye, supporting cardiovascular disease diagnosis and prognosis.
Methodological quality of cardiac radiomics studies remains low, with previous median Radiomics Quality Score (RQS) at 19.4%, limiting clinical adoption.
The EuSoMII introduced the METRICS score in 2024 to systematically assess and improve methodological quality and reproducibility in radiomics research.
Guideline-Based Recommendations
Diagnosis
Use radiomics-based feature extraction from cardiac CT and MRI to enhance prediction of cardiovascular events.
Apply systematic quality assessment tools like METRICS to evaluate radiomics study robustness before clinical implementation.
Management
Incorporate radiomics biomarkers into AI models to support personalized cardiovascular risk stratification.
Address methodological heterogeneity by adhering to standardized radiomics protocols and quality scoring systems.
Monitoring & Follow-up
Perform ongoing quality assessment of radiomics studies using METRICS to ensure reproducibility and reliability.
Use meta-analytic approaches to synthesize diagnostic accuracy data (e.g., pooled AUC) for continuous evaluation of radiomics performance.
Risks
Low methodological quality and heterogeneity in radiomics studies may lead to unreliable predictions and hinder clinical translation.
Potential publication bias and lack of standardized reporting can affect the validity of radiomics-based cardiovascular risk models.
Patient & Prescribing Data
Patients undergoing cardiac CT or MRI for cardiovascular risk assessment
Radiomics-derived imaging biomarkers can improve prediction of cardiovascular events, but clinical adoption requires high-quality, reproducible studies assessed by tools like METRICS.
Clinical Best Practices
Utilize validated radiomics quality assessment tools (e.g., METRICS) to ensure methodological rigor in cardiac imaging studies.
Standardize radiomics feature extraction and analysis protocols to reduce heterogeneity across studies.
Incorporate meta-analytic and statistical methods to evaluate diagnostic accuracy and identify potential biases in radiomics research.
Engage multidisciplinary expert panels in study design and quality assessment to enhance reproducibility and clinical relevance.
