Improving epidemic surveillance and response: big data is dead, long live big data

Buckee, Caroline O.

doi:10.1016/s2589-7500(20)30059-5

Cited by 51 publications

(39 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the officially reported daily case counts as the outcome, our work shows that sick posts significantly predict daily cases up to 14 days ahead of official statistics. This finding confirms prior research that social media data can be usefully applied to nowcasting and forecasting emerging infectious diseases such as COVID-19 [ 22 , 34 ].…”

Section: Discussionsupporting

confidence: 89%

“…One of the greatest challenges of digital disease surveillance is identifying true disease signals, especially when facing the deluge of social media activity that resulted from COVID-19 mitigation measures [ 12 , 34 - 36 ]. Our finding that sick posts have greater predictive power than other COVID-19 posts shows that not all social media data are equally informative.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study

Shen¹,

Chen²,

Luo³

et al. 2020

J Med Internet Res

143

108

View full text Add to dashboard Cite

Background Coronavirus disease (COVID-19) has affected more than 200 countries and territories worldwide. This disease poses an extraordinary challenge for public health systems because screening and surveillance capacity is often severely limited, especially during the beginning of the outbreak; this can fuel the outbreak, as many patients can unknowingly infect other people. Objective The aim of this study was to collect and analyze posts related to COVID-19 on Weibo, a popular Twitter-like social media site in China. To our knowledge, this infoveillance study employs the largest, most comprehensive, and most fine-grained social media data to date to predict COVID-19 case counts in mainland China. Methods We built a Weibo user pool of 250 million people, approximately half the entire monthly active Weibo user population. Using a comprehensive list of 167 keywords, we retrieved and analyzed around 15 million COVID-19–related posts from our user pool from November 1, 2019 to March 31, 2020. We developed a machine learning classifier to identify “sick posts,” in which users report their own or other people’s symptoms and diagnoses related to COVID-19. Using officially reported case counts as the outcome, we then estimated the Granger causality of sick posts and other COVID-19 posts on daily case counts. For a subset of geotagged posts (3.10% of all retrieved posts), we also ran separate predictive models for Hubei province, the epicenter of the initial outbreak, and the rest of mainland China. Results We found that reports of symptoms and diagnosis of COVID-19 significantly predicted daily case counts up to 14 days ahead of official statistics, whereas other COVID-19 posts did not have similar predictive power. For the subset of geotagged posts, we found that the predictive pattern held true for both Hubei province and the rest of mainland China regardless of the unequal distribution of health care resources and the outbreak timeline. Conclusions Public social media data can be usefully harnessed to predict infection cases and inform timely responses. Researchers and disease control agencies should pay close attention to the social media infosphere regarding COVID-19. In addition to monitoring overall search and posting activities, leveraging machine learning approaches and theoretical understanding of information sharing behaviors is a promising approach to identify true disease signals and improve the effectiveness of infoveillance.

show abstract

Section: Discussionsupporting

confidence: 89%

Section: Discussionmentioning

confidence: 99%

Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study

Shen¹,

Chen²,

Luo³

et al. 2020

J Med Internet Res

143

108

View full text Add to dashboard Cite

show abstract

“…45 The lack of accurate and available data to underpin epidemic forecasting in emerging outbreaks has been highlighted. 53 We found no literature using an ontological approach for COVID-19 surveillance. There are domain ontologies related to coronavirus published on BioPortal.…”

Section: Comparison With Previous Literaturementioning

confidence: 94%

COVID-19 Surveillance in a Primary Care Sentinel Network: In-Pandemic Development of an Application Ontology (Preprint)

Lusignan¹,

Liyanage²,

McGagh³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND

Creating an ontology for coronavirus disease 2019 (COVID-19) surveillance should help ensure transparency and consistency. Ontologies formalise conceptualisations at either domain or application level. Application ontologies cross domains and are specified through testable use cases. Our use case was extension of the role of the Oxford Royal College of General Practitioners (RCGP) Research and Surveillance Centre (RSC) to monitor the current pandemic and become an in-pandemic research platform.

OBJECTIVE

To develop an application ontology for COVID-19 which can be deployed across the various use case domains of the Oxford- RCGP RSC research and surveillance activities.

METHODS

We described our domain-specific use case. The actor was the RCGP RSC sentinel network; the system the course of the COVID-19 pandemic; the outcomes the spread and effect of mitigation measures. We used our established three-step method to develop the ontology, separating ontological concept development from code mapping and data extract validation. We developed a coding system–independent COVID-19 case identification algorithm. As there were no gold standard pandemic surveillance ontologies, we conducted a rapid Delphi consensus exercise through the International Medical Informatics Association (IMIA) Primary Health Care Informatics working group and extended networks.

RESULTS

Our use case domains included primary care, public health, virology, clinical research and clinical informatics. Our ontology supported: (1) Case identification, microbiological sampling and health outcomes at both an individual practice and national level; (2) Feedback through a dashboard; (3) A national observatory, (4) Regular updates for Public Health England, and (5) Transformation of the sentinel network to be a trial platform. We have identified a total of 8,627 people with a definite COVID-19 status, 4,240 with probable, and 59,147 people with possible COVID-19, within the RCGP RSC network (N=5,056,075).

CONCLUSIONS

The underpinning structure of our ontological approach has coped with multiple clinical coding challenges. At a time when there is uncertainty about international comparisons, clarity about the basis on which case definitions and outcomes are made from routine data is essential.

show abstract

“…Instead, the dynamics of mobility are more easily studied via mobile Big Data that are mostly collected and processed by private companies. Not surprisingly, in the recent months, there have been several calls for privately owned large-scale mobile Big Data to be shared for public health purposes (Buckee, 2020;Ienca and Vayena, 2020;Oliver et al, 2020). While we agree with these calls, we would extend them and argue that availability of these types of data should extend beyond the needs of health sector and this particular pandemic of COVID-19.…”

Section: Improving Mobile Big Data Systems To Promote Social Goodmentioning

confidence: 99%

COVID-19 is spatial: Ensuring that mobile Big Data is used for social good

et al. 2020

View full text Add to dashboard Cite

The mobility restrictions related to COVID-19 pandemic have resulted in the biggest disruption to individual mobilities in modern times. The crisis is clearly spatial in nature, and examining the geographical aspect is important in understanding the broad implications of the pandemic. The avalanche of mobile Big Data makes it possible to study the spatial effects of the crisis with spatiotemporal detail at the national and global scales. However, the current crisis also highlights serious limitations in the readiness to take the advantage of mobile Big Data for social good, both within and beyond the interests of health sector. We propose two strategical pathways for the future use of mobile Big Data for societal impact assessment, addressing access to both raw mobile Big Data as well as aggregated data products. Both pathways require careful considerations of privacy issues, harmonized and transparent methodologies, and attention to the representativeness, reliability and continuity of data. The goal is to be better prepared to use mobile Big Data in future crises.

show abstract

Improving epidemic surveillance and response: big data is dead, long live big data

Cited by 51 publications

References 10 publications

Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study

Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study

COVID-19 Surveillance in a Primary Care Sentinel Network: In-Pandemic Development of an Application Ontology (Preprint)

COVID-19 is spatial: Ensuring that mobile Big Data is used for social good

Contact Info

Product

Resources

About