Researchers use search engines, social media to predict syphilis trends

April 16, 2018 by Enrique Rivero, University of California, Los Angeles
Credit: CC0 Public Domain

UCLA-led research finds that internet search terms and tweets related to sexual risk behaviors can predict when and where syphilis trends will occur.

Two studies from the UCLA-based University of California Institute for Prediction Technology, in collaboration with the Centers for Disease Control and Prevention, or CDC, found an association between certain risk-related terms that Google and Twitter users researched or tweeted about and subsequent trends that were reported to the CDC. The researchers were able to pinpoint these cases at state or county levels, depending on the platform used.

"Many of the most significant public health problems in our society today—HIV and sexually transmitted infections, opioid abuse and cancer—could be prevented if we had better data on when and where these issues were occurring," said Sean Young, founder and director of the UCLA Center for Digital Behavior and the UC Institute for Prediction Technology. "These two studies suggest that social media and internet search data might help to fix this problem by predicting when and where future syphilis cases may occur. This could be a tool that government agencies such as the CDC might use," added Young, who is also an associate professor of family medicine at the David Geffen School of Medicine at UCLA.

One study, to be published in the peer-reviewed journal Epidemiology, investigated the association between state-level search queries on Google with primary and secondary syphilis cases—the earliest and most transmissible stages in the sexually transmitted infection—that were subsequently reported in these states.

For this study, the researchers compiled data for 25 keywords and phrases (such as "find sex" and "STD") collected on Google Trends from Jan. 1, 2012, to Dec. 31, 2014. They also obtained weekly county-level syphilis data from the CDC covering the same time period for all 50 states, merged that data by state and collated them with the weekly Google Trends data they had collected.

The research incorporated a type of statistical computer science model called machine learning, which can look through large amounts of data to find patterns and predict those patterns. This artificial intelligence-based machine looked at the relationship between people's syphilis-related searches on Google and actual rates of syphilis over a period of time. After learning that pattern, it tested whether it could accurately predict future syphilis cases by using just the syphilis-related Google search terms.

Researchers found that the model predicted 144 weeks of syphilis counts for each state with 90 percent accuracy, allowing them to predict state-level trends in syphilis before they would have occurred.

Researchers from the institute found the same held true with Twitter. In a study published in Preventive Medicine, they took county-level Twitter data from May 26 to Dec. 9, 2012, amounting to 8,538 geo-located tweets. As with the Google Trends analysis, the researchers compiled a list of words associated with .

They reviewed weekly county-level cases of primary and secondary syphilis and early latent syphilis (infection within the previous 12 months, with no symptoms evident) that likely occurred over the previous 12 months. The cases were from the 50 states and Washington, D.C., and were reported to the CDC from 2012 to 2013. The 2012 data were included because a county's previous syphilis rates are likely to predict future rates, and they wanted to determine how the Twitter-based method would perform matched with the previous year's data.

They found that counties having higher risk-related tweets in 2012 were associated with a 2.7 percent jump in primary and secondary and a 3.6 percent boost in early latent syphilis cases in 2013. By comparison, counties that reported higher numbers of syphilis cases in 2012 were associated with increases of 0.6 percent and 0.4 percent of primary/secondary and early latent syphilis cases, respectively, in 2013, suggesting that the Twitter-based model performed as well as simply using previous year's syphilis data. This is important because Twitter data are extremely inexpensive and suggest that social media data are low-cost alternatives for predicting syphilis.

Both studies have certain limitations. For the Google paper, they include the likelihood that many primary and cases are not reported; the findings were biased toward Google users, who account for about 64 percent of search engine users; and the Google Trends data are a random sampling of all data and not the full dataset, which might have affected how the model worked. In the Twitter study's case, data were based on Twitter users, which is a select sample of people; the researchers reviewed data only for 2012 and 2013, when data from a longer time span would be needed to develop appropriate public health responses; and some areas with high numbers of syphilis cases may have had public health messaging via that contained relevant keywords that were captured in the data the researchers examined.

Explore further: First ever state-level primary and secondary syphilis report shows highest cases among MSM

More information: Sean D. Young et al, Using Search Engine Data as a Tool to Predict Syphilis, Epidemiology (2018). DOI: 10.1097/EDE.0000000000000836

Related Stories

First ever state-level primary and secondary syphilis report shows highest cases among MSM

November 2, 2017
Researchers from Emory's Rollins School of Public Health and the Centers for Disease Control and Prevention (CDC) released the first ever report of state-level rates of primary and secondary (P&S) syphilis by race/ethnicity ...

CDC: syphilis rates up among U.S. men who have sex with men

April 7, 2017
(HealthDay)—Syphilis rates among men who have sex with men (MSM) have increased significantly in the past two decades, according to research published in the April 7 issue of the U.S. Centers for Disease Control and Prevention's ...

As newborn syphilis cases rise, maternal screening urged

February 6, 2018
(HealthDay)—Newborn syphilis cases have shot up in the United States in recent years, so an expert panel is reaffirming the need to screen all pregnant women for the infection.

Health officials warn of blinding cases of syphilis on West Coast

March 12, 2015
(HealthDay)—Health care providers on the West Coast need to look out for syphilis that can cause blindness, public health officials say.

Syphilis cuts CD4 counts, ups viral load in HIV-infected men

July 26, 2012
(HealthDay) -- Syphilis is associated with a transient decrease in the CD4 cell count and with an increase in viral load (VL) in HIV-infected men, according to a study published online July 23 in the Archives of Internal ...

Syphilis infections on the rise in Europe

May 18, 2016
New data released in ECDC's Annual Epidemiological report show that since 2010, the overall syphilis rates have been going up across Europe, particularly among men. In 2014, the reported syphilis numbers were six times higher ...

Recommended for you

PET scans to optimize tuberculosis meningitis treatments and personalize care, study finds

December 6, 2018
Although relatively rare in the United States, and accounting for fewer than 5 percent of tuberculosis cases worldwide, TB of the brain—or tuberculosis meningitis (TBM)—is often deadly, always hard to treat, and a particular ...

Silicosis is on the rise, but is there a therapeutic target?

December 6, 2018
Researchers from the CNRS, the University of Orléans, and the company Artimmune, in collaboration with Turkish clinicians from Atatürk University, have identified a key mechanism of lung inflammation induced by silica exposure, ...

Infectivity of different HIV-1 strains may depend on which cell receptors they target

December 6, 2018
Distinct HIV-1 strains may differ in the nature of the CCR5 molecules to which they bind, affecting which cells they can infect and their ability to enter cells, according to a study published December 6 in the open-access ...

Protecting cell powerhouse paves way to better treatment of acute kidney injury

December 6, 2018
For the first time, scientists have described the body's natural mechanism for temporarily protecting the powerhouses of kidney cells when injury or disease means they aren't getting enough blood or oxygen.

New study uncovers why Rift Valley fever is catastrophic to developing fetuses

December 5, 2018
Like Zika, infection with Rift Valley fever virus can go unnoticed during pregnancy, all the while doing irreparable—often lethal—harm to the fetus. The results of a new study, led by researchers at the University of ...

Study highlights potential role of bioaerosol sampling to address airborne biological threats

December 5, 2018
As a leading global city with a high population density, Singapore is vulnerable to the introduction of biological threats. Initiating an early emergency response to such threats calls for the rapid identification of the ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.