TY - JOUR
T1 - Predicting dengue outbreaks using approximate entropy algorithm and pattern recognition
AU - Chen, Chia Chern
AU - Chang, Hsien Chang
N1 - Funding Information:
We thank the Center for Disease Control for provisioning the DF case registry for public use. We thank the National Nano Device Laboratory (NDL99-C06S-058) and Southern Taiwan Nanotechnology Research Center for supplying the equipment for this study. This study was supported by the Multidisciplinary Center of Excellence for Clinical Trial and Research (DOH100-TD-B-111-002) under the NSC Grant No. NSC 99-2628-B-006-001-MY3 .
PY - 2013/7
Y1 - 2013/7
N2 - Objectives: The prediction of dengue outbreaks is a critical concern in many countries. However, the setup of an ideal prediction system requires establishing numerous monitoring stations and performing data analysis, which are costly, time-consuming, and may not achieve the desired results. In this study, we developed a novel method for predicting impending dengue fever outbreaks several weeks prior to their occurrence. Methods: By reversing moving approximate entropy algorithm and pattern recognition on time series compiled from the weekly case registry of the Center for Disease Control, Taiwan, 1998-2010, we compared the efficiencies of two patterns for predicting the outbreaks of dengue fever. Results: The sensitivity of this method is 0.68, and the specificity is 0.54 using Pattern A to make predictions. Pattern B had a sensitivity of 0.90 and a specificity of 0.46. Patterns A and B make predictions 3.1±2.2 weeks and 2.9±2.4 weeks before outbreaks, respectively. Conclusions: Combined with pattern recognition, reversed moving approximate entropy algorithm on the time series built from weekly case registry is a promising tool for predicting the outbreaks of dengue fever.
AB - Objectives: The prediction of dengue outbreaks is a critical concern in many countries. However, the setup of an ideal prediction system requires establishing numerous monitoring stations and performing data analysis, which are costly, time-consuming, and may not achieve the desired results. In this study, we developed a novel method for predicting impending dengue fever outbreaks several weeks prior to their occurrence. Methods: By reversing moving approximate entropy algorithm and pattern recognition on time series compiled from the weekly case registry of the Center for Disease Control, Taiwan, 1998-2010, we compared the efficiencies of two patterns for predicting the outbreaks of dengue fever. Results: The sensitivity of this method is 0.68, and the specificity is 0.54 using Pattern A to make predictions. Pattern B had a sensitivity of 0.90 and a specificity of 0.46. Patterns A and B make predictions 3.1±2.2 weeks and 2.9±2.4 weeks before outbreaks, respectively. Conclusions: Combined with pattern recognition, reversed moving approximate entropy algorithm on the time series built from weekly case registry is a promising tool for predicting the outbreaks of dengue fever.
UR - http://www.scopus.com/inward/record.url?scp=84878363072&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84878363072&partnerID=8YFLogxK
U2 - 10.1016/j.jinf.2013.03.012
DO - 10.1016/j.jinf.2013.03.012
M3 - Article
C2 - 23558245
AN - SCOPUS:84878363072
SN - 0163-4453
VL - 67
SP - 65
EP - 71
JO - Journal of Infection
JF - Journal of Infection
IS - 1
ER -
