CardioX neural network is structured as an interconnected group of smaller neural networks, which estimate 2 parameters: systolic and diastolic blood pressure.
We have acquired hundreds of thousands of ECG records of both men and women, aged from 15 to 93 y.o. Along with ECG, the records contain a person's Blood Pressure readings taken at the same time as ECG, as well as a number of individual metrics, such as gender, age, physical health, etc.
Neural Network analyzes a short ECG interval to estimate AI BP (AI estimated blood pressure).
The process of selecting data and creating machine learning models starts with basic processing of the existing data. First, we eliminate all irrelevant and questionable records. Then, we remove all noise from ECG signals and straighten the isoline.
Once we cleaned up ECG signals, we moved on to developing teaching models for neural networks.
Along with patients' individual metrics, like age and gender, we also use over 50 other parameters that were calculated during ECG signal analysis.