Accepted for/Published in: JMIR Infodemiology
Date Submitted: Aug 5, 2021
Open Peer Review Period: Jul 25, 2021 - Sep 19, 2021
Date Accepted: Dec 7, 2021
(closed for review but you can still tweet)
Integrating Search Engine Query Data into Patient Volume Forecasting of an Adult Emergency Department: Infodemiology Study of Google Trends.
ABSTRACT
Background:
Online health information-seeking behaviors raise opportunities to inform healthcare service operations. Google Trends search query data has been used to study public health topics such as seasonal influenza, suicide, and prescription drug abuse; however, there is a paucity of literature evaluating the application of Google Trends data to improve daily patient forecasting models of Emergency Departments.
Objective:
This investigation assessed the ability of Google Trends search query data to improve the performance of adult Emergency Department daily volume prediction models.
Methods:
Google Trends search query data of cardinal symptoms and healthcare facilities was collected from Chicago, IL (7/2015-6/2017). Correlations were calculated between Google Trends search query data and Emergency Department daily patient volumes from a tertiary-care, adult hospital in Chicago. A baseline multiple linear regression model of Emergency Department daily volume with traditional predictors was augmented with Google Trends search query data; model performance was measured by the mean absolute error and mean absolute percentage error.
Results:
Substantial correlations between Emergency Department daily volume and Google Trends search query data included: “hospital” (r=0.54), “combined” (r=0.50), and “Northwestern Memorial Hospital” (r=0.34). The final baseline model yielded a mean absolute percentage error of 6.67%, whereas the final Google Trends augmented model included the predictors “Combined 3-day moving average” and “Hospital 3-day moving average” and yielded a mean absolute percentage error of 6.42% - an improvement of 3.1%.
Conclusions:
Incorporating Google Trends search query data into prediction models of adult Emergency Department daily volume modestly improved model performance compared to traditional models for an adult tertiary-care hospital. Further development of advanced models with comprehensive search query terms and complimentary data sources may improve prediction performance and could be an avenue for further research.
Citation
Per the author's request the PDF is not available.
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.