Deep Learning for Risk Analysis of Specific Cardiovascular Diseases Using Environmental Data and Outpatient Records
2016 IEEE 16th International Conference on Bioinformatics and Bioengineering (BIBE) (2016)
Oct. 31, 2016 to Nov. 2, 2016
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/BIBE.2016.75
Cardiovascular diseases are known to be a category of diseases related to heart or blood vessels and ranked the top two and three among ten leading causes of death in Taiwan in 2011, respectively. In this study, environmental and outpatient records within Taichung Area are utilized for risk analysis of four specific categories of cardiovascular diseases using deep learning approach. Autoencoder and Softmax are employed for feature extraction and classification. The output of Softmax for each sample is interpreted as the risk of these four specific categories of cardiovascular diseases. Further analysis is done to unveil the trends with respect to the factors of gender, age, region, and month.
Cardiovascular diseases, Heart, Monitoring, Machine learning, Air pollution, Neurons
H. C. Hsiao, S. H. Chen and J. J. Tsai, "Deep Learning for Risk Analysis of Specific Cardiovascular Diseases Using Environmental Data and Outpatient Records," 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering (BIBE), Taichung, Taiwan, 2016, pp. 369-372.