Skip to main content

Surveillance Systems

Description

Infectious diseases present with multifarious factors requiring several efforts to detect, prevent, and break the chain of transmission. Recently, machine learning has shown to be promising for automated surveillance leading to rapid and early interventions, and extraction of phenotypic features of human faces. In addition, mobile devices have become a promising tool to provide on-the-ground surveillance, especially in remote areas and geolocation mapping. Pacific Northwest National Laboratory (PNNL) combines machine learning with mobile technology to provide a groundbreaking prototype of disease surveillance without the need for internet, just a camera. In this android application, VisionDx, a machine learning algorithm analyses human face images and within milliseconds notifies the user with confidence level whether or not the person is sick. VisionDx comes with two modes, photo and video, and additional features of history, map, and statistics. This application is the first of its kind and provides a new way to think about the future of syndromic surveillance.

Objective: Automated syndromic surveillance using mobile devices is an emerging public health focus that has a high potential for enhanced disease tracking and prevention in areas with poor infrastructure. Pacific Northwest National Laboratory sought to develop an Android mobile application for syndromic biosurveillance that would i) use the phone camera to take images of human faces to detect individuals that are sick through a machine learning (ML) model and ii) collect image data to increase training data available for ML models. The initial prototype use case is for screening and tracking the health of soldiers for use by the Department of Defense’s Disease Threat Reduction Agency.

Submitted by elamb on
Description

In the past 15 years, public health surveillance has undergone a revolution driven by advances in information technology (IT) with vast improvements in the collection, analysis, visualization, and reporting of health data. Mobile technologies and open source software have played a key role in advancing surveillance techniques, particularly in resource-limited settings. Johns Hopkins University Applied Physics Laboratory (JHU/APL) is an internationally recognized leader in the area of electronic disease surveillance. In addition to the Electronic Surveillance System for the Early Notification of Community-based Epidemics (ESSENCE) used by several state and local jurisdictions and the CDC in the U.S., JHU/APL has also developed the Suite for Automated Global Electronic bioSurveillance (SAGES). SAGES is a collection of modular, open-source software tools designed to meet the challenges of electronic disease surveillance in resource-limited settings. JHU/APL is working with the Peruvian Navy health system to improve their electronic disease surveillance capabilities. The Peruvian Navy currently uses a SAGES-based system called Alerta DISAMAR that was implemented several years ago in an effort supported by the Armed Forces Health Surveillance Branch, and in collaboration with the Naval Medical Research Unit No. 6 (NAMRU-6). The system uses both web-based and IVR-based (interactive voice response) data collection from several Navy health facilities in Peru. For the present effort, JHU/APL is implementing a new SMS-based data collection capability for the Peruvian Navy.

Objective: To introduce SMS-based data collection into the Peruvian Navy’s public health surveillance system for increased reporting rates and timeliness, particularly from remote areas, as well as improve capabilities for analysis of surveillance data by decision makers.

Submitted by elamb on
Description

Drug overdose deaths are increasing nationally and in Minnesota (MN). This is only a fraction of the overall burden that recreational drug use exacts on emergency departments (ED) and hospitals. In addition to opioids and other drugs, three outbreaks of synthetic cannabinoids and cathinones have occurred in MN recently. ICD codes do not adequately identify patients treated for drug use. Also, toxicology data for these patients are limited: routine toxicology testing is not performed at hospitals as results are not timely enough to be useful for clinical care. Even when such testing is performed, hospital laboratories are unable to detect newer synthetic drugs. In order to more quickly respond to clusters of substance use, identify substances causing atypical symptoms or severe illness, and understand the burden of overdoses and substance use in MN, the MN Department of Health (MDH) developed the MN Drug Overdose and Substance Abuse Pilot Surveillance System (MNDOSA). MNDOSA data collection began in November 2017 and includes two pilot sites in Northeastern MN, and one in the Twin Cities Metropolitan Area.

Objective: Implement a novel surveillance system for recreational substance use, including toxicology testing, to enable situational awareness and more accurately assess the health care burden related to recreational substance use.

Submitted by elamb on
Description

IIS have effectively increased vaccination rates through targeted engagement and outreach, often with clinicians and patients. Little has been published around IIS use for generating meaningful population health measures. To leverage IIS data for sub-county population health measures, new tools are required to make IIS data easily accessed for this distinct use case. Human papillomavirus (HPV), the most common sexually transmitted infection in the United States, has a highly effective (97%) vaccine to prevent infection when administered to individuals 9-26 years old. According to the National Immunization Survey, only 47% of Colorado females 13-17 years had completed the HPV vaccine series in 2011. In 2012, Denver metropolitan health departments were awarded a three year grant to support the Alliance for HPV Free Colorado, where media and clinic coaching were used to improve HPV vaccination coverage among adolescents (11-17 years) in Adams, Arapahoe, Denver, Douglas, and Jefferson counties. Recent HPV vaccination schedule changes from three to two required doses highlighted further challenges in monitoring vaccination UTD rates.

Objective: To describe a business intelligence system designed to reprocess and utilize an immunization information system's (IIS) data to visualize, and track population trends in immunization coverage in an urban population.

Submitted by elamb on
Description

Civil Registration system (CRS) in India has been in vogue for more than 100 years now. The registration of Birth and Deaths Act, 1969 came into force in 1970. Even after 4 decades of the enactment of the act, there are wide inter-state and intra-state variations. India is the second largest populated country in the world after China. Whereas as the level of registration of birth and deaths varies from (84.4 and 69.3) registrations. In India, more than 250 thousand of registration centers are involved in central registration system and estimated births per years are 26 million, and the corresponding figure for death is 8 million (Sethi 2016).

Objective: To see the level and trend of the vital registration system in India and its states form 2005-2015. To identify factors influencing civil registration in India.

Submitted by elamb on
Description

Adverse Childhood Experiences (ACEs) have been linked to a variety of detrimental health and social outcomes. In the last 20 years, the association between ACEs with several adult health risk behaviors, conditions, and diseases including suicides, and substance abuse, mental health disturbances and impaired memory, nervous, endocrine and immune systems impairments, and criminal activities have been studied. One of the challenges in studying and timely diagnosis of ACEs is that the links between specific childhood experiences and their health outcomes are not totally clear. Similarly, an integrated dataset builtfrom multiple sources is often required for effective ACEs surveillance. The SPACES project aims at providing a semantic infrastructure to facilitate data sharing and integration and answer causal queries to improve ACEs surveillance.

Objective: We introduce the Semantic Platform for Adverse Childhood Experiences (ACEs) Surveillance (SPACES). It facilitates the access to the relevant integrated information, enables discovering the causality pathways and assists researchers, clinicians, public health practitioners, social workers, and health organization in studying the ACEs, identifying the trends, as well as planning and implementing preventive and therapeutic strategies.

Submitted by elamb on
Description

Healthcare systems are often evaluated using comparative health care rankings. Simulations have shown that maximally inequitable health care systems can perform well in published, influential health care system rankings by excelling in non-equity categories, resulting in highly ranked yet grossly inequitable healthcare systems. Recently, despite below average equity rankings, the healthcare systems of Australia and New Zealand ranked among the top four in The Commonwealth Fund's international comparative study Mirror, Mirror 20172. Equity rankings should logically limit non-equity rankings given the insignificance of healthcare system improvements to those lacking adequate healthcare coverage. We analyzed whether an equity-limited ranking methodology would limit overall rankings for significantly inequitable healthcare systems while maintaining the general findings of the Commonwealth Fund study.

Objective: Describe the diverse determinants of national health and how they are compositely graded in health care system rankings. Articulate intrinsic reasons why equity should not be subsumed within other evaluative categories. Design an equity-limited ratings framework for limiting maximum ratings of inequitible healthcare systems.

Submitted by elamb on
Description

Utah has a centralized State Health Department and 12 Local Health Departments situated throughout the state. Coordination of outbreaks or events that crosses jurisdictions has been historically difficult. Utah has not had a functional NEDSS-compliant database until 2009 and still does not have an Outbreak Management System (OMS). A survey was sent to Local Health Departments to assess their perception of need for real-time knowledge of current outbreak/events, with the majority indicating that current processes were inadequate.

Objective

The aim of this project was to create a secured web-based application that would run within the PH Access communication framework at the Utah Department of Health. This applicationFEpi Issue TrackerFwould provide State and Local Health Departments with an environment that can be used to monitor actions during an event. We created a tracking system that functions as a combination dashboard/ notification system to permit timely and effective communication of epidemiology events. This tracking system, Epi Issue Tracker, is used by all 12 Local Health Departments and the State Department of Health to share information across the state. There have been 830 issues/outbreaks entered into Epi Issue Tracker since January 2009, with 647 updates posted for those issues/outbreaks.

Submitted by Magou on
Description

Homelessness in general is a major issue in the US today. The risk factors of homelessness are myriad, including inadequate income, lack of affordable housing, mental health and substance abuse issues, lack of social support, and nonadherence to treatment/follow-up appointments. Early identification of these factors from clinical documents may help detect or even predict homelessness cases, allowing adequate intervention and prevention measures.

Objective

 We demonstrate a semi-automated approach to induce and curate lexical domain knowledge for identification of evidence and risk factors for homelessness found in VA clinical documents. This domain knowledge can be used to support training and evaluation of automated methods such as Natural Language Processing (NLP) systems for detection and prediction of homelessness among veterans. This could serve as a proxy for public health and other surveillance involving homeless individuals. Similar methods could be used to identify other conditions of interest.

Submitted by Magou on
Description

Modern information and communication technologies have increasingly prominent roles in health care systems. To capitalize on attainable benefits, it is essential to thoroughly and purposefully weave them into the existing business processes. The challenges of doing so can be exacerbated by specific local circumstances of developing countries. We

share our experiences from fielding a system designed to support real-time collection and analysis of public health data in rural areas of Sri Lanka and India. Its strong transformational potential has been proven, however, success of the ultimate field use requires overcoming multiple organizational and utility challenges.

 

Objective

We review challenges faced during the initial period of implementation of a Real-Time Biosurveillance Program in developing countries.

Submitted by hparton on