Tags

Type your tag names separated by a space and hit enter

Subregional Nowcasts of Seasonal Influenza Using Search Trends.
J Med Internet Res. 2017 11 06; 19(11):e370.JM

Abstract

BACKGROUND

Limiting the adverse effects of seasonal influenza outbreaks at state or city level requires close monitoring of localized outbreaks and reliable forecasts of their progression. Whereas forecasting models for influenza or influenza-like illness (ILI) are becoming increasingly available, their applicability to localized outbreaks is limited by the nonavailability of real-time observations of the current outbreak state at local scales. Surveillance data collected by various health departments are widely accepted as the reference standard for estimating the state of outbreaks, and in the absence of surveillance data, nowcast proxies built using Web-based activities such as search engine queries, tweets, and access of health-related webpages can be useful. Nowcast estimates of state and municipal ILI were previously published by Google Flu Trends (GFT); however, validations of these estimates were seldom reported.

OBJECTIVE

The aim of this study was to develop and validate models to nowcast ILI at subregional geographic scales.

METHODS

We built nowcast models based on autoregressive (autoregressive integrated moving average; ARIMA) and supervised regression methods (Random forests) at the US state level using regional weighted ILI and Web-based search activity derived from Google's Extended Trends application programming interface. We validated the performance of these methods using actual surveillance data for the 50 states across six seasons. We also built state-level nowcast models using state-level estimates of ILI and compared the accuracy of these estimates with the estimates of the regional models extrapolated to the state level and with the nowcast estimates published by GFT.

RESULTS

Models built using regional ILI extrapolated to state level had a median correlation of 0.84 (interquartile range: 0.74-0.91) and a median root mean square error (RMSE) of 1.01 (IQR: 0.74-1.50), with noticeable variability across seasons and by state population size. Model forms that hypothesize the availability of timely state-level surveillance data show significantly lower errors of 0.83 (0.55-0.23). Compared with GFT, the latter model forms have lower errors but also lower correlation.

CONCLUSIONS

These results suggest that the proposed methods may be an alternative to the discontinued GFT and that further improvements in the quality of subregional nowcasts may require increased access to more finely resolved surveillance data.

Authors+Show Affiliations

Department of Environmental Health Sciences, Columbia University, New York, NY, United States.Department of Computer Science, Columbia University, New York, NY, United States.Department of Environmental Health Sciences, Columbia University, New York, NY, United States.

Pub Type(s)

Journal Article
Research Support, N.I.H., Extramural

Language

eng

PubMed ID

29109069

Citation

Kandula, Sasikiran, et al. "Subregional Nowcasts of Seasonal Influenza Using Search Trends." Journal of Medical Internet Research, vol. 19, no. 11, 2017, pp. e370.
Kandula S, Hsu D, Shaman J. Subregional Nowcasts of Seasonal Influenza Using Search Trends. J Med Internet Res. 2017;19(11):e370.
Kandula, S., Hsu, D., & Shaman, J. (2017). Subregional Nowcasts of Seasonal Influenza Using Search Trends. Journal of Medical Internet Research, 19(11), e370. https://doi.org/10.2196/jmir.7486
Kandula S, Hsu D, Shaman J. Subregional Nowcasts of Seasonal Influenza Using Search Trends. J Med Internet Res. 2017 11 6;19(11):e370. PubMed PMID: 29109069.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Subregional Nowcasts of Seasonal Influenza Using Search Trends. AU - Kandula,Sasikiran, AU - Hsu,Daniel, AU - Shaman,Jeffrey, Y1 - 2017/11/06/ PY - 2017/02/10/received PY - 2017/08/15/accepted PY - 2017/06/13/revised PY - 2017/11/8/entrez PY - 2017/11/8/pubmed PY - 2018/3/20/medline KW - classification and regression trees KW - human influenza KW - infodemiology KW - infoveillance KW - nowcasts KW - surveillance SP - e370 EP - e370 JF - Journal of medical Internet research JO - J. Med. Internet Res. VL - 19 IS - 11 N2 - BACKGROUND: Limiting the adverse effects of seasonal influenza outbreaks at state or city level requires close monitoring of localized outbreaks and reliable forecasts of their progression. Whereas forecasting models for influenza or influenza-like illness (ILI) are becoming increasingly available, their applicability to localized outbreaks is limited by the nonavailability of real-time observations of the current outbreak state at local scales. Surveillance data collected by various health departments are widely accepted as the reference standard for estimating the state of outbreaks, and in the absence of surveillance data, nowcast proxies built using Web-based activities such as search engine queries, tweets, and access of health-related webpages can be useful. Nowcast estimates of state and municipal ILI were previously published by Google Flu Trends (GFT); however, validations of these estimates were seldom reported. OBJECTIVE: The aim of this study was to develop and validate models to nowcast ILI at subregional geographic scales. METHODS: We built nowcast models based on autoregressive (autoregressive integrated moving average; ARIMA) and supervised regression methods (Random forests) at the US state level using regional weighted ILI and Web-based search activity derived from Google's Extended Trends application programming interface. We validated the performance of these methods using actual surveillance data for the 50 states across six seasons. We also built state-level nowcast models using state-level estimates of ILI and compared the accuracy of these estimates with the estimates of the regional models extrapolated to the state level and with the nowcast estimates published by GFT. RESULTS: Models built using regional ILI extrapolated to state level had a median correlation of 0.84 (interquartile range: 0.74-0.91) and a median root mean square error (RMSE) of 1.01 (IQR: 0.74-1.50), with noticeable variability across seasons and by state population size. Model forms that hypothesize the availability of timely state-level surveillance data show significantly lower errors of 0.83 (0.55-0.23). Compared with GFT, the latter model forms have lower errors but also lower correlation. CONCLUSIONS: These results suggest that the proposed methods may be an alternative to the discontinued GFT and that further improvements in the quality of subregional nowcasts may require increased access to more finely resolved surveillance data. SN - 1438-8871 UR - https://www.unboundmedicine.com/medline/citation/29109069/Subregional_Nowcasts_of_Seasonal_Influenza_Using_Search_Trends_ L2 - https://www.jmir.org/2017/11/e370/ DB - PRIME DP - Unbound Medicine ER -