The Application of Artificial Intelligence in Public Health Surveillance in Portugal: An Exploratory Study of Expert Perspectives

ObjectiveThis paper describes the lessons learned from operation and maintenance of the public health surveillance (PHS) component of five pilot city drinking water contamination warning systems (CWS) including: Cincinnati, New York, San Francisco, Philadelphia, and Dallas.IntroductionThe U.S. Environmental Protection Agency (EPA) designed a program to pilot multi-component contamination warning systems (CWSs), known as the “Water Security initiative (WSi).” The Cincinnati pilot has been fully operational since January 2008, and an additional four pilot utilities will have their own, custom CWSs by the end of 2012. A workshop amongst the pilot cities was conducted in May 2012 to discuss lessons learned from the design, implementation, operation, maintenance, and evaluation of each city’s PHS component.MethodsWhen evaluating potential surveillance tools to integrate into a drinking water contamination warning system, it is important to consider design decisions, dual use applications/considerations, and the unique capabilities of each tool. The pilot cities integrated unique surveillance tools, which included a combination of automated event detection tools and communication and coordination procedures into their respective PHS components. The five pilots performed a thorough, technical evaluation of each component of their CWS, including PHS.ResultsFour key lessons learned were identified from implementation of the PHS component in the five pilot cities. First, improved communication and coordination between public health and water utilities was emphasized as an essential goal even if it were not feasible to implement automated surveillance systems. The WSi pilot project has helped to strengthen this communication pathway through the process of collaborating to develop the component, and through the need to investigate PHS alerts.Second, the approximate location of specific cases associated with PHS alerts was found to be an essential feature that allowed a cross-comparison to water pressure zones when attempting to locate the source of possible contamination. More specific location data (e.g., latitude and longitude) leads to a more efficient investigation, however, just narrowing the case location down to a specific hydraulic region within the water distribution system is extremely useful.Third, the ability to quickly visualize spatial distribution of cases via a visual interface was reported to be valuable to investigators during alert investigations. Most pilots implemented a CWS dashboard, in the form of a central graphical display, which presents the alerts and was used by the water utility and public health to obtain an understanding of geospatial relationships between cases, alerts and water pressure zones.Finally, public health and water utility representatives from several of the WSi pilots acknowledged that their automated surveillance tools currently have limited capabilities for detection of chemical contaminants (which may result in a sudden onset of symptoms), with the main deficiency being the timeliness of the alerts relative to the window of opportunity to respond in a meaningful and effective manner. While they currently focus on detection of traditional waterborne diseases, these tools could potentially be adapted to also detect chemical contaminants.ConclusionsThe results of the pilots have demonstrated that it is important to construct and formalize standard operating procedures, so that public health personnel and water utilities have a standard communication protocol. As a basic step to a PHS component, it is important to establish a relationship between utilities and public health. In addition to the efforts of the WSi pilots, research is currently being conducted by the U.S. EPA to analyze health seeking behavior of symptomatic individuals, because all PHS tools rely on data generated from behavior pursued by the affected population during a public health incident. Results from analysis of both emergency department data and poison control center follow-up phone data are currently underway.

Rarely does one get to be a participant in the frontier of a new discipline or area of research. But since 9/11 the field of syndromic surveillance has provided public health researchers and practitioners just such an opportunity. Some of the $5 billion in funds awarded by the Centers for Disease Control and Prevention (CDC) during fiscal years 2002– 2007 to states, territories, and several large local jurisdictions to enhance public health capacities to detect, respond to, and recover from bioterrorism events have been allocated to expanding or improving surveillance systems [1]. These expansions have included developing public health capabilities in the area of biosurveillance and its sub-field, syndromic surveillance. The aim of these new systems is to use near ‘real-time’ data and automated tools to detect and characterize outbreaks (natural or intentional) before conventional methods. Several systems have become popular for use by state and local health jurisdictions in conducting these syndromic surveillance activities, including the Early Aberration Reporting System (EARS), BioSense, and the Electronic Surveillance System for the Early Notification of Community Based Epidemics (ESSENCE II) [2--4]. In the initial years of implementing syndromic surveillance systems, state and local health departments used the applications primarily to detect bioterrorism-related events [5]. However, due to developing needs, the public health community has applied biosurveillance more broadly to other situations, including influenza and fire-related illness surveillance, as well as to affirm the absence of outbreaks after a disaster [6]. In Monterey County, California, we have had similar needs and particularly wanted a program that we could use for local purposes. We began using EARS in 2005 because of its flexibility for developing syndrome definitions and applied it to a variety of situations, from daily ongoing surveillance for influenza-like illness to emerging situations such as respiratory syndromes potentially associated with an aerial spraying of pesticide (Monterey County, unpublished data). The field is young, and Fricker (this issue) is timely in his advocacy for the standardization of terms and methods used for biosurveillance and particularly syndromic surveillance. Public health practitioners should support such standardization and have outlined areas for further research and evaluation [7]. An equally pressing issue is the statistical methods that are currently used for biosurveillance. Fricker does an admirable job of summarizing how methodologies from the field of industrial statistical process control have been adapted for use in detecting attacks by terrorists on the health of a population. A comprehensive understanding of bioterrorism is relatively recent in the literature and, for research purposes, the number of modern bioterrorist events that resulted in actual cases have been few [8]. However, there has been an apparent recent increase in the use of biological agents with 40 of 56 confirmed criminal cases and 19 of 27 confirmed terrorist cases in the 20th century occurring in the 1990s [8]. While these provide a relative paucity of events for modeling purposes and for developing effective syndromic surveillance methods, they underscore the necessity of surveillance methods that can be used to improve time to event detection and to help ensure that a bioterrorist attack is detected. This is likely why there appears to be general support in public health for an expansion of syndromic and other public health surveillance systems. The majority of public health jurisdictions surveyed in the United States use some form of syndromic surveillance [5]. Internationally, the World Health Organization revised the International Health Regulations in 2007 to include the concept of syndromic surveillance as part of an expanded traditional disease notification system. May et al. [9] provide a review of its uses in developing nations. There is a national recognition of the potential usefulness and importance for developing syndromic surveillance systems. In December 2009, proposed regulations were released by the Centers for Medicare and Medicaid Services in the United States defining ‘meaningful use’ of electronic health records (EHR). In addition, the Office of the National Coordinator for Health Information Technology released an interim final rule describing the required certification standards

ObjectiveTo evaluate capacity of the BioSense ESSENCE platform and pre-defined overdose queries to identify emergency department admissions related to opioid overdose, in compliance with 2018 mandatory overdose reporting laws in IllinoisIntroductionAccuracy in identifying drug-related emergency department admissions is critical to understanding local burden of disease and assessing effectiveness of drug abuse prevention and overdose-reduction initiatives. In 2018 the Illinois Department of Public Health (IDPH) began implementation of a mandatory opioid overdose reporting law, applicable to all hospital emergency departments (ED). The mandate requires reporting of patient demographics, causal substance and antagonist ED administration within 48 hours of presentation. This reporting is not name-based.IDPH currently utilizes a near real-time syndromic surveillance (SyS) reporting system for all hospital ED, capturing most of the mandated criteria. Leveraging this existing system facilitates adherence to the mandate while imposing minimal additional burden of reporting on local hospitals. The Division of Patient Safety and Quality at IDPH has thus chosen to evaluate the completeness of overdose reporting and compliance with the opioid overdose mandate that have resulted from use of the current syndromic surveillance system.MethodsMulti-level internal and external validation methods are being employed to evaluate the accuracy of opioid overdose reporting through syndromic surveillance.An initial internal evaluation compared overdoses captured using hospital discharge data (HDD) and SyS data. This analysis compared daily overdose counts in the two datasets from 166 Illinois facilities, from admissions from April 1 through June 30 2017, inclusive. The opioid overdose query from HDD referenced ICD-10 poisoning codes; SyS utilized the preset Opioid Overdose Version 1 (v1.0) query in the ESSENCE Tool from the CDC’s National Syndromic Surveillance Program’s BioSense Platform. Daily and quarterly overdose counts by surveillance method were compared and visualized by facility.Three facilities were chosen for a secondary, case-level data comparison based on: magnitude of overdose discrepancies, overall overdose burden, and availability of linked data elements. Individual overdose visits were matched across SyS and HDD datasets based on: date of birth, sex and approximate date of admit. Cases identified in SyS but missing from (1) discharge diagnosis query and (2) discharge database overall were quantified. Cases identified by HDD that were (3) not identified in the SyS overdose query or (4) missing from the SyS database entirely were also counted.ResultsFrom April 1 to June 30 2017, among the 166 providers analyzed, the HDD query identified 2,998 opioid overdose-related visits; SyS identified 3,266 (268 cases or 8.9% difference) (Figure 1, r=0.724).A total of 25 (15%) of facilities had equivalent overdose visit counts between datasets: all were among those with low case burden (13 or fewer overdose visits per facility over the quarter). Among facilities with a higher number of overdose presentations, differences in quarterly case counts (SyS minus HDD) ranged from –56 to 120.Discrepant counts were found in 85% of centers (Figure 2). HDD captured a larger number of overdoses in 93 facilities (56%). SyS captured a larger number of overdoses in 48 facilities (29%). The ten facilities with highest syndromic caseload accounted for 33% of overall case burden (1069); the ten with the highest discharge counts accounted for 29% (897 cases). However, the top ten facilities by surveillance type were notably different: the 2nd and 3rd highest using syndromic surveillance ranked 30th and 41st using discharge surveillance over the same period. The center with 5th highest caseload by discharge criteria ranked 38th using syndromic surveillance.In secondary case-level analyses: across datasets from three facilities, both HDD and SyS captured 43.5% of overdoses, while 56% were only in SyS data and 0.5% were only in HDD. Discrepancies in the all-visit (“denominator”) datasets were found, requiring follow-up with facilities directly.ConclusionsNext steps in these evaluations include further characterization of cases missed differentially by syndromic and discharge surveillance. An external validation phase will engage facility staff to query the Electronic Medical Record directly. Hospital personnel will review and confirm opioid overdose events captured by SyS and hospital facilities will investigate and resolve discrepancies in data quality.These analyses have the potential to inform more accurate definitions for opioid-related overdose seen in emergency departments. Such improved surveillance can aid allocation of medication (naloxone and naltrexone), promotion of intervention (i.e. methadone-assisted treatment programs), and drug abuse prevention. Engagement of facility staff in public health surveillance has resulted in 187 hospital-registered users for the BioSense Platform to date, demonstrating the ability of surveillance improvement efforts to foster public health partnership. Finally, optimizations of automated hospital surveillance systems can help reduce the burden of reporting overdoses and ED morbidity in general, to encourage time spent on monitoring and response.

The COVID-19 pandemic has prompted an unprecedented global research effort to better understand this virus and to identify promising treatments. In this essay, the authors note that defining activities as public health surveillance has important implications, because such activities do not require further ethical oversight, informed consent, or protections for vulnerable persons or communities.

COVID-19 Highlights Critical Need for Public Health Data Modernization to Remain a Priority.

Heterogeneity and Interoperability in Local Public Health Information Systems.

ObjectiveReview concept of situation awareness (SA) as it relates to public health surveillance, epidemiology and preparedness [1]. Outline hierarchical levels and organizational criteria for SA [2]. Initiate consensus building process aimed at developing a working definition and measurable outcomes and metrics for SA as they relate to syndromic surveillance practice and evaluation.IntroductionA decade ago, the primary objective of syndromic surveillance was bioterrorism and outbreak early event detection (EED) [3]. Syndromic systems for EED focused on rapid, automated data collection, processing and statistical anomaly detection of indicators of potential bioterrorism or outbreak events. The paradigm presented a clear and testable surveillance objective: the early detection of outbreaks or events of public health concern. Limited success in practice and limited rigorous evaluation, however, led to the conclusion that syndromic surveillance could not reliably or accurately achieve EED objectives. At the federal level, the primary rationale for syndromic surveillance shifted away from bioterrorism EED, and towards all-hazards biosurveillance and SA [4–6]. The shift from EED to SA occurred without a clear evaluation of EED objectives, and without a clear definition of the scope or meaning of SA in practice. Since public health SA has not been clearly defined in terms of operational surveillance objectives, statistical or epidemiological methods, or measurable outcomes and metrics, the use of syndromic surveillance to achieve SA cannot be evaluated.MethodsThis session is intended to provide a forum to discuss SA in the context of public health disease surveillance practice. The roundtable will focus on defining SA in the context of public health syndromic and epidemiologic surveillance. While SA is often noted in federal level documents as a primary rationale for biosurveillance [1, 4–6], it is rarely defined or described in operational detail. One working definition presents SA as “real-time analysis and display of health data to monitor the location, magnitude, and spread of an outbreak”, yet it does not elaborate on the methods, systems or evaluation requirements for SA in public health or biosurveillance [3]. In terms of translating SA into public health surveillance practice [1], we will discuss and define the requirements of public health SA based on its development and practice in other areas [2]. The proposed theoretical framework and evaluation criteria adapted and applied to public health SA [2] follow:- Level 1: Perceive relevant surveillance data and epidemiological information.- Level 2: Integrate surveillance and non-surveillance data in conjunction with operator goals to provide understanding of the meaning of the information.- Level 3: Through perceiving (Level 1) and integrating and understanding (Level 2) provide prediction of future events and system states to allow for timely and effective public health decision making.ResultsSample questions for discussion: What is the relevance of syndromic surveillance and biosurveillance in the SA framework? Where does it fit within the current public health surveillance environment? To achieve the roundtable discussion objectives, the participants will work towards a consensus definition of SA for public health, and will outline measureable outcomes and metrics for evaluation of syndromic surveillance for public health SA.

Social Media Posts and Search Engine Queries as the Canary in the Coal Mine for Public Health Surveillance

Artificial intelligence (AI) refers to the process in which computers, rather than human intelligence, perform tasks, such as early warning of an epidemic. This editorial aimed to describe the potential applications of digital health and the challenges faced by the health system of Iran concerning the application of artificial intelligence and innovative technology in public health surveillance and early warning of epidemics. The use of new technologies at national and subnational levels for early warning of public health threats requires a suitable platform within the context of disease surveillance systems. The Iran health system currently utilizes a syndromic approach and event-based surveillance to monitor acute respiratory infections. However, the structure of Iran's national communicable disease surveillance system has faced challenges due to the inability to share and exchange data at the level of primary health care data sources. Accordingly, application and integration of AI should be considered as Iran’s health priority to promote infrastructure and technology requirements, including compatibility, interoperability, and strategies for ethical and responsible use by public health authorities. Since pandemics and epidemics have not been limited to the previous ones, such as COVID-19, influenza, SARS, dengue fever, and similar threats, operations planning is required for the integration of artificial intelligence tools to prepare and respond to biological threats promptly by the Iranian Ministry of Health, stakeholders, and other parties.

Background: Artificial Intelligence (AI) is increasingly revolutionizing public health surveillance, particularly in regions with constrained healthcare infrastructure. This scoping review examines the application of AI in public health surveillance across Africa, identifying existing implementations, challenges, and opportunities. AI technologies such as machine learning, natural language processing, and predictive analytics enhance epidemic intelligence by analyzing vast datasets from diverse sources, including electronic health records, social media, and environmental sensors. These AI-driven tools provide early warnings for outbreaks, improve disease surveillance, and facilitate timely public health responses. Methods: A systematic search of databases, including Pubmed, Google Scholar, Researchgate, Web of Science, Scopus, Scientific Research, African Journal of Health Informatics, International Journal of Infectious Diseases, ScienceDirect, African Journal of Biotechnology, PloS One, The Lancet, JMIMR, BMJ, and BMC. The search covers publications from January 2010 to February 2025, spanning for 15 years. A total of 1411 articles. An additional 44 records were identified through other sources after removing 201 duplicates; 1254 unique articles were screened based on titles and abstracts. One thousand one hundred and twenty-seven (1127) records were excluded as they did not meet the inclusion criteria. Then, 127 full-text articles were assessed for eligibility, and 54 full-text articles were excluded for various reasons: study in non-African location (52) Not focused on AI applications (12), challenges and opportunities, Insufficient Data (9) Finally, 54 studies were included in the qualitative synthesis. Results: Following a rigorous selection process, 54 studies were included in the qualitative synthesis. Most studies (83.33%) were published as peer-reviewed journal articles, while technical reports and theses were less common, with five (9.26%) and four (7.41%) studies, respectively. The primary focus of these studies varied: 39 (72.22%) explored AI applications in disease detection and prediction, 25 (46.30%) examined AI applications in disease surveillance, 18 (33.33%) highlighted challenges in AI adoption for healthcare, and 15 (27.78%) focused on real-time surveillance and reporting in Africa. Findings reveal that AI is actively utilized in African public health systems for disease prediction, outbreak surveillance, and resource allocation. However, several challenges hinder its full potential, including inadequate infrastructure, data privacy concerns, limited access to high-quality datasets, and a shortage of AI-trained healthcare professionals. Despite these barriers, AI presents great opportunities for strengthening health security in Africa by improving diagnostic accuracy, optimizing healthcare interventions, and enhancing real-time epidemiological analysis. Conclusion: Artificial intelligence presents a transformative opportunity for health surveillance in Africa, particularly in diagnostics and disease prediction. AI-powered tools, such as mobile diagnostic applications and predictive models, enhance healthcare accessibility in resource-limited settings by analyzing vast datasets for early disease detection. Successful implementations, including AI-driven malaria mapping and tuberculosis detection through chest X-ray analysis, HIV, cholera, Ebola, measles, Zika virus, and malaria, enabling targeted screening interventions, personalized treatment plans, and efficient resource allocation, demonstrate AI’s potential to improve public health outcomes. Despite challenges such as infrastructure limitations and data privacy concerns, AI continues to revolutionize disease monitoring and response. By leveraging machine learning for targeted interventions and efficient resource allocation, AI holds promise for a future of more proactive and effective healthcare across the continent of Africa.

Twitter has become a dominant source of public health data and a widely used method to investigate and understand public health-related issues internationally. By leveraging big data methodologies to mine Twitter for health-related data at the individual and community levels, scientists can use the data as a rapid and less expensive source for both epidemiological surveillance and studies on human behavior. However, limited reviews have focused on novel applications of language analyses that examine human health and behavior and the surveillance of several emerging diseases, chronic conditions, and risky behaviors. The primary focus of this scoping review was to provide a comprehensive overview of relevant studies that have used Twitter as a data source in public health research to analyze users' tweets to identify and understand physical and mental health conditions and remotely monitor the leading causes of mortality related to emerging disease epidemics, chronic diseases, and risk behaviors. A literature search strategy following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extended guidelines for scoping reviews was used to search specific keywords on Twitter and public health on 5 databases: Web of Science, PubMed, CINAHL, PsycINFO, and Google Scholar. We reviewed the literature comprising peer-reviewed empirical research articles that included original research published in English-language journals between 2008 and 2021. Key information on Twitter data being leveraged for analyzing user language to study physical and mental health and public health surveillance was extracted. A total of 38 articles that focused primarily on Twitter as a data source met the inclusion criteria for review. In total, two themes emerged from the literature: (1) language analysis to identify health threats and physical and mental health understandings about people and societies and (2) public health surveillance related to leading causes of mortality, primarily representing 3 categories (ie, respiratory infections, cardiovascular disease, and COVID-19). The findings suggest that Twitter language data can be mined to detect mental health conditions, disease surveillance, and death rates; identify heart-related content; show how health-related information is shared and discussed; and provide access to users' opinions and feelings. Twitter analysis shows promise in the field of public health communication and surveillance. It may be essential to use Twitter to supplement more conventional public health surveillance approaches. Twitter can potentially fortify researchers' ability to collect data in a timely way and improve the early identification of potential health threats. Twitter can also help identify subtle signals in language for understanding physical and mental health conditions.

Background: Joint Action on Strengthened International Health Regulations and Preparedness in the EU (SHARP JA) was implemented from 2019 to 2023. Work package 8 of this project dealt with training and local exercises, and exchange of working practices. Methods and Objectives: The objective of this paper is to present the trainings conducted during the SHARP JA with the aim to strengthen implementation of international health regulations (IHR) for serious cross-border health threats in the JA partner countries. Method of this paper was a review of published and unpublished reports and training materials developed under the WP8 activities. Results: The following trainings were conducted - IHR Basic Online-Training, In(tra)-Action Reviews (IAR) in an Online Setting, Online Tabletop exercise on Risk communication - "Vaccination Exercise", International Tabletop Exercise Points of Entry - Control Measures, Contact Tracing, Public Health Disaster Recovery Training, Workshop on Public Health Surveillance - lessons learned from COVID-19/Public Health Emergencies Detection and Surveillance, Training on the EU Common Ship Sanitation Database - Digital tool for supporting International Health Regulations implementation at Points of Entry, Chemical Safety and Chemical Threats. In total, 21 workshops/ trainings, 3 national exercises, and 2 study visits were organised in online and on-site settings with total number of 943 participants from 31 countries. The target audience for the trainings were the public health professionals from different sectors, actively involved in the implementation of IHR core capacities, risk communication experts, field epidemiologists from different sectors, laboratory experts, representatives of local, intermediate and national level authorities, National focal points for the IHR, persons working at a competent authority at a country central level (Ministry of Health, National Public Health Institute or other) dealing with chemical safety, etc. Conclusions: WP8 conducted online and on-site basic and advanced trainings that contributed to strengthening the competencies of public health professionals in the JA-SHARP partner countries.

What do hemorrhoids, One Direction, and Big Bird all have in common? According to Google Trends, they were among 2012's most popular Internet search terms with the highest sustained traffic. What do hemorrhoids, One Direction, and Big Bird all have in common? According to Google Trends, they were among 2012's most popular Internet search terms with the highest sustained traffic. Google Trends (www.google.com/trends/) is a Web-based tool available to all Internet users that estimates the search volume of a specific term or topic relative to the total number of Web searches over a period of time. Users can create graphs of search volume, updated daily, based on data from specific countries or worldwide. One potential application of this tremendous volume of Web searches is for better insights into the health information sought by patients around the world.■Search engine surveillance tools like Google Trends can help identify public health issues as they emerge.■While more research is needed on the value of search engine data, it is likely to play a role in the future of public health. ■Search engine surveillance tools like Google Trends can help identify public health issues as they emerge.■While more research is needed on the value of search engine data, it is likely to play a role in the future of public health. Syndromic surveillance has recently emerged as a means to detect outbreaks through symptom monitoring, even before confirmed diagnoses are available. Adequate surveillance usually requires careful coordination of several teams and agencies to communicate threats, organize responses, and interface with multiple stakeholders, including the public. This requires time, manpower, financial resources, and a stable infrastructure for effective execution. Public health surveillance tools can provide real-time information to monitor emerging threats. These surveillance tools can help prevent major outbreaks by tracking diseases, monitoring their spread, and aiding in planning for rapid and effective response. As Internet utilization continues to grow around the world, the search terms used in a certain geographic area can provide potential insights into emerging health trends. Using the Internet, individuals can search from home for answers about medical questions that may render them weak and unable to travel, or that may carry heavy social stigma or embarrassment. Understanding health trends can provide clues into the experience of a population and enable local governments and response teams to counter any threats in a timely and effective manner. ■Global Public Health Intelligence Network (Public Health Agency of Canada): www.phac-aspc.gc.ca/gphin/■HealthMap (Boston Children's Hospital): www.healthmap.org■Program for Monitoring Emerging Diseases (International Society for Infectious Diseases): www.promedmail.org In 2008, Canada experienced an outbreak of listeriosis resulting from deli meat contaminated with Listeria bacteria. Although the public health declaration occurred in August, search-term surveillance revealed a rise in searches for "listeriorisis" as early as July.1.Wilson K. Brownstein J.S. Early detection of disease outbreaks using the Internet.CMAJ. 2009; 180: 829-831Crossref PubMed Scopus (194) Google Scholar This case is just one example of the potential role of search-term surveillance. Tools like Google Trends can provide nearly real-time data that may allow researchers and health officials to identify epidemics as they emerge, particularly in developing countries that lack robust public health infrastructure and financial resources for surveillance.2.Carneiro H.A. Mylonakis E. Google trends: a Web-based tool for real-time surveillance of disease outbreaks.Clin Infect Dis. 2009; 49: 1557-1564Crossref PubMed Scopus (454) Google Scholar Recently, public health groups have used Google Trends as a surveillance tool for early identification of outbreaks and potential health threats. In 2008, Google launched Flu Trends (www.google.org/flutrends/) to specifically track and predict real-time flu outbreaks in countries around the world, including the United States. This tool monitors search queries on Google to identify the presence of influenza symptoms, categorizing flu activity as minimal, low, moderate, high, or intense compared with past flu activity. Compared with retrospective surveillance data from CDC, Google Flu Trends accurately detected emerging cases of influenza almost 2 weeks prior to the agency's published reports.2.Carneiro H.A. Mylonakis E. Google trends: a Web-based tool for real-time surveillance of disease outbreaks.Clin Infect Dis. 2009; 49: 1557-1564Crossref PubMed Scopus (454) Google Scholar Though search engine surveillance tools seem promising, this technology is still developing and is not without its limitations. Google Trends data do not use standardized search criteria and can be overestimated, as reflected in its estimated 2013 influenza outbreak numbers, which were nearly double those calculated by CDC. Actual raw data will be needed in order to carry out more robust and meaningful analysis and comparison with other surveillance data, such as those from CDC. Nonetheless, Google Trends, in addition to other search engine surveillance tools, may have an increasingly important role in the early detection of outbreaks and timely communication with the public.

Objective: This panel will:● Discuss the importance of identifying and developing success stories● Highlight successes from state and local health departments to show how syndromic surveillance activities enhance situational awareness and address public health concerns● Encourage discussion on how to further efforts for developing and disseminating success storiesIntroduction: Syndromic surveillance uses near-real-time emergency department and other health care data for enhancing public health situational awareness and informing public health activities. In recent years, continued progress has been made in developing and strengthening syndromic surveillance activities. At the national level, syndromic surveillance activities are facilitated by the National Syndromic Surveillance Program (NSSP), a collaboration among state and local health departments, the CDC, other federal organizations, and other organizations that enabled collection of syndromic surveillance data in a timely manner, application of advanced data monitoring and analysis techniques, and sharing of best practices. This panel will highlight the importance of success stories. Examples of successes from state and local health departments will be presented and the audience will be encouraged to provide feedback.Description: ●Success stories – acknowledging and informing syndromic surveillance practiceThis presentation will discuss the importance of success stories for NSSP focused on increasing syndromic surveillance representativeness, improving data quality, and strengthening syndromic surveillance practices among grant recipients and partners. From the beginning of the program, the identification of success stories has been an important part of the efforts to develop knowledge base that better guide syndromic surveillance program activities.●NJ and BioSense – Making The Connection The New Jersey Department of Health (NJDOH) uses Health Monitoring’s EpiCenter as its primary ED data for syndromic surveillance. This data is also submitted to CDC’s NSSP BioSense Platform. In April 2017, a spike in ED Visits of Interest was identified by a CDC NSSP subject matter expert and brought to the attention of NJDOH’s data analyst. Data showed an increase in “Exposure” and “School Exposure” chief complaints in two contiguous counties. News reports showed the visits resulted from a dormitory fire at a university in the area. The NSSP and NJDOH staff collaboration integrated data from both NJDOH’s EpiCenter and CDC’s BioSense Platform for further investigation. This activity shows BioSense Platform’s potential as an additional syndromic surveillance tool because of its different classifications and keyword groupings.●Evaluation and Performance Measures at the Utah Department of HealthSyndromic surveillance related evaluation activities at the Utah Department of Health requires collaboration between subject matter experts and system users from the UT-NSSP workgroup. The progress is examined quarterly and outcomes compared with the short-, mid-, and long-term outcomes listed in the NSSP logic model to ensure activities are in sync with the program’s overall goals. Throughout the budget year, a variety of tools were used to keep track of the progress. During this session, challenges and successes, lessons learned, and effective strategies will be discussed.●NSSP R tool Data Download Useful in NHThe New Hampshire Department of Health and Human Services (NH DHHS) uses the state-wide Automated Hospital Emergency Department Data (AHEDD) system as its primary syndromic surveillance system. A copy of this data is submitted to CDC’s NSSP BioSense Platform. In July of 2017, NH worked with the NSSP vendor, CDC staff, a jurisdictional expert, NH Division of Information Technology staff, and an external vendor to create an “R” software download in CSV format and home-based NSSP Cognos report. This allowed NH DHHS staff to compare these data to the home-based data and ultimately, it proved to be an important step in the NSSP data quality assessment process.●Achieving success to improve data quality through collaborative Community of Practice partnerships The Data Quality Committee is a forum to identify, discuss, and attempt to address syndromic surveillance data quality issues. Maintaining data quality for the chief complaint field is a priority as it can impact the creation and refinement in the successful application of a syndrome definition for one of the fundamental data elements. An issue was observed in the Arizona data in the BioSense Platform, where chief complaint was being truncated at 200 characters. Through efforts to build relationships from the committee in the Community of Practice, Arizona was able to discover the root causes for the issue, assess if it affected other jurisdictions, and work with the partners to find a feasible resolution. This talk will discuss how this collaborative approach helped improve data quality.How the Moderator Intends to Engage the Audience in Discussions on the Topic: The moderator will introduce the session and the panelists, and will invite questions and comments from the audience.

BackgroundAs service provision and patient behaviour varies by day, healthcare data used for public health surveillance can exhibit large day of the week effects. These regular effects are further complicated by the impact of public holidays. Real-time syndromic surveillance requires the daily analysis of a range of healthcare data sources, including family doctor consultations (called general practitioners, or GPs, in the UK). Failure to adjust for such reporting biases during analysis of syndromic GP surveillance data could lead to misinterpretations including false alarms or delays in the detection of outbreaks.The simplest smoothing method to remove a day of the week effect from daily time series data is a 7-day moving average. Public Health England developed the working day moving average in an attempt also to remove public holiday effects from daily GP data. However, neither of these methods adequately account for the combination of day of the week and public holiday effects.MethodsThe extended working day moving average was developed. This is a further data-driven method for adding a smooth trend curve to a time series graph of daily healthcare data, that aims to take both public holiday and day of the week effects into account. It is based on the assumption that the number of people seeking healthcare services is a combination of illness levels/severity and the ability or desire of patients to seek healthcare each day. The extended working day moving average was compared to the seven-day and working day moving averages through application to data from two syndromic indicators from the GP in-hours syndromic surveillance system managed by Public Health England.ResultsThe extended working day moving average successfully smoothed the syndromic healthcare data by taking into account the combined day of the week and public holiday effects. In comparison, the seven-day and working day moving averages were unable to account for all these effects, which led to misleading smoothing curves.ConclusionsThe results from this study make it possible to identify trends and unusual activity in syndromic surveillance data from GP services in real-time independently of the effects caused by day of the week and public holidays, thereby improving the public health action resulting from the analysis of these data.