Accepted for/Published in: JMIR Public Health and Surveillance
Date Submitted: May 22, 2020
Date Accepted: Sep 1, 2020
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Nowcasting Sexually Transmitted Infections in Chicago: Use of Google Trends to build and evaluate a predictive model
ABSTRACT
Background:
Sexually transmitted infections (STIs) pose a significant public health challenge in the United States. Traditional surveillance systems suffer from data quality issues, underreporting of cases, and delays in reporting which results in missed prevention opportunities to respond to trends in disease. Search engine data has the potential to be an efficient and economical enhancement to the established surveillance reporting system for STIs.
Objective:
In this study we developed and trained a predictive model using reported STI case data from Chicago, Illinois and investigated the predictive capacity, timeliness, and ability to target interventions to sub-populations using Google Trends data.
Methods:
De-identified STI case data for chlamydia, gonorrhea and primary and secondary syphilis from 2011-2017 were obtained from the Chicago Department of Public Health (CDPH). The dataset included race/ethnicity, age and birth sex of cases. Google Correlate was used to identify the top 100 correlated search terms with “STD symptoms,” and an auto-crawler was established using Google Health Application Programming Interface (API) to collect search volume for each term. Elastic Net Regression was used to evaluate prediction accuracy and cross correlation analysis was used to identify timeliness of prediction. Subgroup elastic net regression analysis was performed for race, sex and age.
Results:
Actual and predicted STI rates correlate moderately in 2011, but highly from 2012 to 2017 for both gonorrhea and chlamydia. For primary and secondary syphilis high correlation is found in four of the seven years modeled. Model performance was the most accurate (highest correlation, lowest MAE) for gonorrhea. Subgroup analyses improved model fit across disease and year. Regression models using search terms selected from cross correlation analysis improved prediction accuracy and timeliness across disease and year.
Conclusions:
Integrating now-casting with Google Trends into surveillance activities has the potential to enhance prediction and timeliness of outbreak detection and response as well as to target intervention to sub-populations. Future studies should prospectively examine the utility of Google Trends applied to STI surveillance and response. Clinical Trial: does not apply
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.