A Systematic Review of Machine Learning and IoT Applied to the Prediction and Monitoring of Cardiovascular Diseases
Problem
Cardiovascular disease is the leading cause of death worldwide (~17.9 million deaths/year), and early detection, prediction and monitoring are needed.
Why it matters
Early prediction and real-time monitoring of cardiovascular disease could reduce deaths at massive scale.
What the AI did
A systematic review of 164 papers found machine learning (neural networks, random forest, XGBoost, k-NN, SVM) and IoT/IoMT technologies used to detect, predict or monitor cardiovascular disease.
Results
Neural networks achieved accuracy over 90% in the reviewed studies (82 IoT/IoMT proposals, 85 ML proposals reviewed).
Impact
The review concludes IoT/IoMT technologies can predict cardiovascular diseases in real time.
Record
| Venue | Healthcare |
|---|---|
| Published | 2023 |
| Work type | review |
| Authors | Alejandra Cuevas-Chávez, Yasmín Hernández, Javier Ortiz-Hernández, Eduardo Sánchez-Jiménez, Gilberto Ochoa‐Ruiz, Joaquín Pérez-Ortega, Gabriel González |
| Citations | 55 (OpenAlex, at import time) |
| References | 216 |
| Model or method | neural networks, random forest, XGBoost, k-NN, SVM |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/healthcare11162240 |
| Open access | gold |
| Keywords | cardiovascular disease, machine learning, IoT, systematic review, prediction, monitoring |
Importance rating
existential / global scale
Abstract states cardiovascular disease is the leading cause of death worldwide, claiming an estimated 17.9 million lives each year; early detection and monitoring could reduce deaths at massive scale.