Machine learning for predicting cardiac events: what does the future hold?
Problem
Traditional statistical models cannot predict individual-level risk of cardiovascular events such as heart failure and arrhythmias.
Why it matters
Cardiovascular disease burden is rising; individual-level risk prediction could enable earlier prevention.
What the AI did
This is a literature review summarizing machine learning methods and comparing their performance to statistical models for predicting cardiovascular events.
Results
Abstract states current evidence supports superiority of ML methods over statistical-based models in predicting cardiovascular events.
Impact
Evidence is a review of prior literature; no new validated model or benchmark is presented.
Record
| Venue | Expert Review of Cardiovascular Therapy |
|---|---|
| Published | 2020 |
| Work type | article |
| Authors | Brijesh D. Patel, Partho P. Sengupta |
| Citations | 46 (OpenAlex, at import time) |
| References | 52 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1080/14779072.2020.1732208 |
| Open access | green |
| Keywords | machine learning, cardiovascular events, risk prediction, review, individual-level risk |
Importance rating
significant — thousands to millions affected
Abstract notes rising number of cardiovascular disease patients and need for individual-level risk prediction of major adverse events, heart failure, arrhythmias; review only, no new model or scale stated.