Key result
Machine learning integrating clinical, ultrasound, and radiomic features predicts 5-year MACE.
Why the study?
Carotid plaque characteristics have complex interdependencies for which machine learning may provide predictive modeling to assess risk of major adverse cardiovascular events.
Does a machine learning model integrating clinical, manual ultrasound, and radiomic features predict 5-year MACE in patients undergoing carotid ultrasound?
Cohort (n=493)
Does a machine learning model integrating clinical, manual ultrasound, and radiomic features predict 5-year MACE in patients undergoing carotid ultrasound?
p-value: p=2 x 10
Integrating clinical data, manual ultrasound measurements, and radiomic features into machine learning models provides strong predictive power for 5-year major adverse cardiovascular events.
Signals ongoing cardiovascular risk warranting vigilance; leaves open prospective validation of ultrasound markers.
No takes yet. Share an insight, caveat, or question.
Hu et al. (2026) conducted a cohort in Cardiovascular risk (n=493). Machine learning models integrating clinical, manual FOVUS, and radiomic features was evaluated on Major adverse cardiovascular events (MACE) (p=2 x 10). An x-gradient boost machine learning model integrating clinical, manual ultrasound, and radiomic features significantly predicted major adverse cardiovascular events over 5 years.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: