Open Journal of Applied Sciences

Volume 6, Issue 3 (March 2016)

ISSN Print: 2165-3917   ISSN Online: 2165-3925

Google-based Impact Factor: 0.78  Citations  h5-index & Ranking

Hidden Markov Models and Self-Organizing Maps Applied to Stroke Incidence

HTML  XML Download Download as PDF (Size: 437KB)  PP. 158-168  
DOI: 10.4236/ojapps.2016.63017    3,422 Downloads   3,835 Views   Citations


Several studies were devoted to investigate the effects of meteorological factors on the occurrence of stroke. Regression models had been mostly used to assess the correlation between weather and stroke incidence. However, these methods could not describe the process proceeding in the back-ground of stroke incidence. The purpose of this study was to provide a new approach based on Hidden Markov Models (HMMs) and self-organizing maps (SOM), interpreting the background from the viewpoint of weather variability. Based on meteorological data, SOM was performed to classify weather patterns. Using these classes by SOM as randomly changing “states”, our Hidden Markov Models were constructed with “observation data” that were extracted from the daily data of emergency transport at Nagoya City in Japan. We showed that SOM was an effective method to get weather patterns that would serve as “states” of Hidden Markov Models. Our Hidden Markov Models provided effective models to clarify background process for stroke incidence. The effectiveness of these Hidden Markov Models was estimated by stochastic test for root mean square errors (RMSE). “HMMs with states by SOM” would serve as a description of the background process of stroke incidence and were useful to show the influence of weather on stroke onset. This finding will contribute to an improvement of our understanding for links between weather variability and stroke incidence.

Cite this paper

Morimoto, H. (2016) Hidden Markov Models and Self-Organizing Maps Applied to Stroke Incidence. Open Journal of Applied Sciences, 6, 158-168. doi: 10.4236/ojapps.2016.63017.

Cited by

[1] Automatic estimation of differential evolution parameters using Hidden Markov Models
Evolutionary Intelligence, 2018
[2] International Journal of Biomedical Data Mining
[3] Bayesian Analysis Links Weather, Cerebral Infarction and Gen e Expression
[4] Bayesian Analysis Links Weather, Cerebral Infarction and Gene Expression
International Journal of Collaborative Research on Internal Medicine & Public Health, 2017
[5] Association Analysis Identifies Risk of Ischemic Heart Disease When Temperature Increases
[6] Hidden Markov Models to Estimate the Lagged Effects of Weather on Stroke and Ischemic Heart Disease
[7] Exploring linkages between weather factors and the risk of cerebral infarction through the application of Bayesian networks
International Journal of Engineering and Applied Sciences (IJEAS), 2016
[8] Use of Hidden Markov Models to Identify Background States Behind Risks of Cerebral Infarction and Ischemic Heart Disease
Journal of Mathematics Research, 2016

Copyright © 2020 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.