Predicting the development of hypertension using machine learning models in the remote cardiomonitoring subsystem
One of the tasks of personalized medicine is to build a new organizational model for providing medical care to patients, based on the selection of individual medical, diagnostic and preventive agents that are optimally suitable for the peculiarities of the body.
Modern artificial intelligence methods allow you to solve problems of this type.
Purpose. The aim of the study is to construct and apply predictive logistic regression models and decision tree using machine learning techniques to identify patients at high risk of hypertension without the need for invasive clinical procedures.
Materials and methods. A formed data set consisting of 395 patient records of Voronezh City Clinical Clinic No. 1 is used. Each record contains patient parameters: patient sex; patient age; body mass index; waist circumference; hip circumference; tobacco smoking status; alcohol use status; systolic pressure; diastolic pressure. Machine learning methods are used to build prognostic models.
Results. Two models for predicting the development of hypertension are constructed, characterized by high indicators of classification accuracy: a logistic regression model designed to calculate the patient’s individual risk (accuracy 96%), and a decision tree model designed to predict the patient’s possible disease with hypertension and explain the reasons why this disease can occur (accuracy 94%).
Findings. The expediency of using machine learning methods in constructing prognostic models for assessing the state of patients is shown, the possibility of creating a recommendation block based on the obtained models in the remote cardiomonitoring subsystem is indicated.