Cardiovascular Event Prediction by Machine Learning
importance 8/10
ai assisted
Artificial Intelligence in Healthcare cardiology stage: research
Problem
Standard cardiovascular risk scores may miss complex patterns in large, heterogeneous patient data, limiting event prediction accuracy.
Why it matters
Cardiovascular disease is a leading cause of death; better prediction enables earlier intervention.
What the AI did
Random survival forests (a machine learning technique) were applied to 735 variables from 6,814 MESA participants to predict 6 cardiovascular outcomes over 12 years.
Results
Abstract truncated before explicit performance metrics; comparison to standard risk scores was the objective.
Record
| Venue | Circulation Research |
|---|---|
| Published | 2017 |
| Work type | article |
| Authors | Bharath Ambale‐Venkatesh, Xiaoying Yang, Colin O. Wu, Kiang Liu, William Gregory Hundley, Robyn L. McClelland, Antoinette S. Gomes, Aaron R. Folsom et al. |
| Citations | 637 (OpenAlex, at import time) |
| References | 45 |
| Model or method | Random survival forests |
| Organization | MESA (Multi-Ethnic Study of Atherosclerosis) |
| Primary source | https://doi.org/10.1161/circresaha.117.311312 |
| Open access | green |
| Keywords | machine learning, cardiovascular prediction, random survival forests, MESA, risk stratification |
Importance rating
8
major — millions of lives, an industry or a field
Cardiovascular outcome prediction across a large multi-ethnic cohort; better risk prediction broadly affects patient care, but abstract gives no mortality/impact scale.