Human-learned lessons about machine learning in public health surveillance

Presented December 13, 2018.

For public health surveillance, is machine learning worth the effort? What methods are relevant? Do you need special hardware? This talk was motivated by these and other questions asked by ISDS members. It will focus on providing practical—and slightly opinionated—advice about how to determine whether machine learning could be a useful tool for your problem.


December 21, 2018

Beyond aberration detection, coping with multiple exceedances in a national syndromic surveillance service

Public Health England uses data from four national syndromic surveillance systems to support public health programmes and identify unusual activity. Each system monitors a wide range of respiratory, gastrointestinal and other syndromes at a local, regional and national level. As a result, over 12,000 ‘signals’ (combining syndrome and geography) need to be assessed each day to identify aberrations. In this webinar I will describe how the ‘big data’ collected daily are translated into useful information for public health surveillance.

March 15, 2017

The Burden of Seasonal Respiratory Pathogens on a New National Telehealth System

Seasonal rises in respiratory illnesses are a major burden on primary care services. Public Health England (PHE), in collaboration with NHS 111, coordinate a national surveillance system based upon the daily calls received at the NHS 111 telehealth service. Daily calls are categorized according to the clinical ‘pathway’ used by the call handler to assess the presenting complaints of the caller e.g. cold/flu, diarrhoea, rash.


September 21, 2017

Susceptibility Profile of Drug-Resistant Streptococcus pneumoniae Based on ELR

Since November 2014, the Houston Health Department has been receiving antimicrobial resistance information for Streptococcus pneumoniae from a safety net hospital via electronic laboratory reporting (ELR). Antimicrobial characteristics and vaccination rates of pneumococcal disease are of public health interest due to potential implications in treatment and prevention. Ten states participate in the CDC’s Active Bacterial Core surveillance (ABCs) program. Texas, which represents a different and diverse demographic compared to other states, is not an ABCs participating state.

September 19, 2017

Adjustment for Baseline Level of Dengue Cases Due to Increased Testing in Singapore

Dengue is endemic in Singapore, with epidemics of increasing magnitude occurring on a six-year cycle in 1986/7, 1992, 1998, 2004/5, 2007 and 2013. The incidence per 100,000 population ranged from 87.2 to 105.6 in 2009-20121 , and surged to 410.6 in 2013. The mean weekly number of dengue cases over a five-year period provides an indication of the baseline level. We illustrate an adjustment that has been made to the computation of the baseline level due to increased testing for dengue in 2013.


October 23, 2017

An ISDS-Based Initiative for Conventions for Biosurveillance Data Analysis Methods

Twelve years into the 21st century, after publication of hundreds of articles and establishment of numerous biosurveillance systems worldwide, there is no agreement among the disease surveillance community on most effective technical methods for public health data monitoring. Potential utility of such methods includes timely anomaly detection, threat corroboration and characterization, follow-up analysis such as case linkage and contact tracing, and alternative uses such as providing supplementary information to clinicians and policy makers.

January 24, 2018

Challenges and Opportunities in Routine Time Series Analysis of Surveillance Data

ECDC long term strategies for surveillance include analysis of trends of communicable disease of public health importance for European Union countries to guide public health actions. The European Surveillance System (TESSy) holds data on 49 communicable diseases reported by 30 countries for at least the past five years. To simplify time related analysis using surveillance data, ECDC launched a project to enable descriptive and routine TSA without the need for complex programming.


May 21, 2018

Collaborative Automation Reliably Remediating Erroneous Conclusion Threats (CARRECT)

Analyses produced by epidemiologists and public health practitioners are susceptible to bias from a number of sources including missing data, confounding variables, and statistical model selection. It often requires a great deal of expertise to understand and apply the multitude of tests, corrections, and selection rules, and these tasks can be time-consuming and burdensome. To address this challenge, Aptima began development of CARRECT, the Collaborative Automation Reliably Remediating Erroneous Conclusion Threats system.

May 22, 2018

Statistical Models for Biosurveillance of Multiple Organisms

There has been much research on statistical methods of prospective outbreak detection that are aimed at identifying unusual clusters of one syndrome or disease, and some work on multivariate surveillance methods. In England and Wales, automated laboratory surveillance of infectious diseases has been undertaken since the early 1990’s. The statistical methodology of this automated system is described in. However, there has been little research on outbreak detection methods that are suited to large, multiple surveillance systems involving thousands of different organisms.


July 02, 2018

Using the Flow of People in Cluster Detection and Inference

The traditional SaTScan algorithm[1],[2] uses the euclidean dis- tance between centroids of the regions in a map to assemble a con- nected (in the sense that two connected regions share a physical border) sets of regions. According to the value of the respective log- arithm of the likelihood ratio (LLR) a connected set of regions can be classified as a statistically significant detected cluster.

July 17, 2018


Contact Us

National Syndromic
Surveillance Program

Centers for Disease
Control and Prevention

The National Syndromic Surveillance Program (NSSP) is a collaboration among states and public health jurisdictions that contribute data to the BioSense Platform, public health practitioners who use local syndromic surveillance systems, CDC programs, other federal agencies, partner organizations, hospitals, healthcare professionals, and academic institutions.

Site created by Fusani Applications