Singapore infectious disease tracking by Google search mining
The frequency of internet searches has been shown to demonstrate effectiveness in predicting disease incidence. However, previous studies have mainly focused on larger regions such as the United States and China, and few have researched on Singapore. By analysing Google search query data, we examine...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/68935 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-68935 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-689352023-02-28T18:04:23Z Singapore infectious disease tracking by Google search mining Ong, Yan Chun Sebastian Maurer-Stroh School of Biological Sciences A*STAR Bioinformatics Institute DRNTU::Science The frequency of internet searches has been shown to demonstrate effectiveness in predicting disease incidence. However, previous studies have mainly focused on larger regions such as the United States and China, and few have researched on Singapore. By analysing Google search query data, we examined the relationship between search volume for infectious diseases (influenza, dengue fever and hand, foot and mouth disease (HFMD)) and actual disease occurrence in Singapore. Interestingly, influenza counts had high correlations with hfmd- and dengue-related search terms. We constructed linear models using data from 2012-2014 to predict incidence for testing period 2015-May 2016; the best-performing models had correlations of 0.805 for influenza, 0.783 for dengue, and 0.919 for HFMD for the test period. Among them, models for influenza and HFMD demonstrated predictive abilities, and may prove useful in complementing traditional surveillance methods. Bachelor of Science in Biomedical Sciences 2016-08-15T02:17:19Z 2016-08-15T02:17:19Z 2016 Final Year Project (FYP) http://hdl.handle.net/10356/68935 en Nanyang Technological University 130 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Science |
spellingShingle |
DRNTU::Science Ong, Yan Chun Singapore infectious disease tracking by Google search mining |
description |
The frequency of internet searches has been shown to demonstrate effectiveness in predicting disease incidence. However, previous studies have mainly focused on larger regions such as the United States and China, and few have researched on Singapore. By analysing Google search query data, we examined the relationship between search volume for infectious diseases (influenza, dengue fever and hand, foot and mouth disease (HFMD)) and actual disease occurrence in Singapore. Interestingly, influenza counts had high correlations with hfmd- and dengue-related search terms. We constructed linear models using data from 2012-2014 to predict incidence for testing period 2015-May 2016; the best-performing models had correlations of 0.805 for influenza, 0.783 for dengue, and 0.919 for HFMD for the test period. Among them, models for influenza and HFMD demonstrated predictive abilities, and may prove useful in complementing traditional surveillance methods. |
author2 |
Sebastian Maurer-Stroh |
author_facet |
Sebastian Maurer-Stroh Ong, Yan Chun |
format |
Final Year Project |
author |
Ong, Yan Chun |
author_sort |
Ong, Yan Chun |
title |
Singapore infectious disease tracking by Google search mining |
title_short |
Singapore infectious disease tracking by Google search mining |
title_full |
Singapore infectious disease tracking by Google search mining |
title_fullStr |
Singapore infectious disease tracking by Google search mining |
title_full_unstemmed |
Singapore infectious disease tracking by Google search mining |
title_sort |
singapore infectious disease tracking by google search mining |
publishDate |
2016 |
url |
http://hdl.handle.net/10356/68935 |
_version_ |
1759855440023257088 |