ВИКОРИСТАННЯ МЕТОДУ МОНТЕ-КАРЛО ДЛЯ МАРКОВСЬКИХ ЛАНЦЮГІВ ДЛЯ ПРОГНОЗУВАННЯ ПОШИРЕНОСТІ ІШЕМІЧНОЇ ХВОРОБИ СЕРЦЯ В УКРАЇНІ release_jv5e2ld5xnafzfp4qzdvfvaa5m

by M. A. Ivanchuk, P. R. Ivanchuk

Published in Medična Informatika ta Inženerìâ by Ternopil State Medical University.

2018  

Abstract

In medical forecasting, there are often challenges in which it is necessary to assess the risk that is continuous for a long time, and important events can occur more than once. One of the ways of solving problems of this type is the use of Markov models.Markov models suggest that the patient is always in one of the finite numbers of discrete states of health, called the Markov states. All events are modeled as a transition from one state to another. In order for the Markov chain to end, it must contain at least one absorbing state from which the patient can't pass into other states. In medical models, such a condition is the death of the patient, as this is the only condition from which the patient can't escape. The purpose of this work is to build a Markov chain for predicting the prevalence of coronary heart disease in UkraineTo test the predictive quality, the model was built since 1996. The data obtained for the model for 1996-2012 were compared with known epidemiological data. The average prediction error is 3.2 %. We predict an increase in the incidence of coronary heart disease to 35 041.2 per 100 000 population in 2025.
In application/xml+jats format

Archived Files and Locations

application/pdf   559.2 kB
file_xu2wpg6npzbu3gjdny3nqno2dy
ojs.tdmu.edu.ua (web)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2018-02-20
Container Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  1996-1960
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 11338372-989f-4286-a0ed-3bdd2c902a89
API URL: JSON