Engineering Papers⌕ Search

Engineering topics

Charles, Lauren E.

Publications and source records attributed to Charles, Lauren E..

Predicting Kyasanur forest disease in resource-limited settings using event-based surveillance and transfer learning

In recent years, the reports of Kyasanur forest disease (KFD) breaking endemic barriers by spreading to new regions and crossing state boundaries is alarming. Effective disease surveillance and reporting systems are lacking for this emerging zoonosis, hence hindering control and prevention efforts. We compared time-series models using weather data with and without Event-Based Surveillance (EBS) information, i.e., news media reports and internet search trends, to predict monthly KFD cases in humans. We fitted Extreme Gradient Boosting (XGB) and Long Short-Term Memory models at the national and regional levels. We utilized the rich epidemiological data from endemic regions by applying Transfer Learning (TL) techniques to predict KFD cases in new outbreak regions where disease surveillance information was scarce. Overall, the inclusion of EBS data, in addition to the weather data, substantially increased the prediction performance across all models. The XGB method produced the best predictions at the national and regional levels. The TL techniques outperformed baseline models in predicting KFD in new outbreak regions. Novel sources of data and advanced machine-learning approaches, e.g., EBS and TL, show great potential towards increasing disease prediction capabilities in data-scarce scenarios and/or resource-limited settings, for better-informed decisions in the face of emerging zoonotic threats.

60 APPLIED LIFE SCIENCES↗

A Comparison of Infectious Disease Forecasting Methods across Locations, Diseases, and Time

Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

59 BASIC BIOLOGICAL SCIENCES↗

Digital Biosurveillance for Zoonotic Disease Detection in Kenya

Infectious disease surveillance is crucial for early detection and situational awareness of disease outbreaks. Digital biosurveillance monitors large volumes of open-source data to flag potential health threats. This study investigates the potential of digital surveillance in the detection of the top five priority zoonotic diseases in Kenya: Rift Valley fever (RVF), anthrax, rabies, brucellosis, and trypanosomiasis. Open-source disease events reported between August 2016 and October 2020 were collected and key event-specific information was extracted using a newly developed disease event taxonomy. A total of 424 disease reports encompassing 55 unique events belonging to anthrax (43.6%), RVF (34.6%), and rabies (21.8%) were identified. Most events were first reported by news media (78.2%) followed by international health organizations (16.4%). News media reported the events 4.1 (±4.7) days faster than the official reports. There was a positive association between official reporting and RVF events (odds ratio (OR) 195.5, 95% confidence interval (CI); 24.01–4756.43, p < 0.001) and a negative association between official reporting and local media coverage of events (OR 0.03, 95% CI; 0.00–0.17, p = 0.030). This study highlights the usefulness of local news in the detection of potentially neglected zoonotic disease events and the importance of digital biosurveillance in resource-limited settings.

59 BASIC BIOLOGICAL SCIENCES↗

A Sheaf Theoretical Approach to Uncertainty Quantification of Heterogeneous Geolocation Information

Integration of multiple, heterogeneous sensors is a challenging problem across a range of applications. Prominent among these are multi-target tracking, where one must combine observations from different sensor types in a meaningful and efficient way to track multiple targets. Because different sensors have differing error models, we seek a theoretically justified quantification of the agreement among ensembles of sensors, both overall for a sensor collection, and also at a fine-grained level specifying pairwise and multi-way interactions among sensors. We demonstrate that the theory of mathematical sheaves provides a unified answer to this need, supporting both quantitative and qualitative data. Furthermore, the theory provides algorithms to globalize data across the network of deployed sensors, and to diagnose issues when the data do not globalize cleanly. We demonstrate and illustrate the utility of sheaf-based tracking models based on experimental data of a wild population of black bears in Asheville, North Carolina. A measurement model involving four sensors deployed among the bears and the team of scientists charged with tracking their location is deployed. This provides a sheaf-based integration model which is small enough to fully interpret, but of sufficient complexity to demonstrate the sheaf’s ability to recover a holistic picture of the locations and behaviors of both individual bears and the bear-human tracking system. A statistical approach was developed in parallel for comparison, a dynamic linear model which was estimated using a Kalman filter. This approach also recovered bear and human locations and sensor accuracies. When the observations are normalized into a common coordinate system, the structure of the dynamic linear observation model recapitulates the structure of the sheaf model, demonstrating the canonicity of the sheaf-based approach. However, when the observations are not so normalized, the sheaf model still remains valid.

97 MATHEMATICS AND COMPUTING↗

Before the Battlefield: Competition Spurs Warfighter Innovations

In an effort funded by the Defense Threat Reduction Agency’s (DTRA) Joint Science and Technology Office, Pacific Northwest National Laboratory’s Dr. Lauren Charles and Mr. Michael Henry run an Intern-based Biosurveillance Ecosystem (BSVE) Web Application Development Contest. The competition topics target specific gaps in data collection, integration, analysis, and visualization of essential information needed for situational awareness of chemical and biological threats. The 10-week long summer internship program leverages the creativity and talent of graduate students as well as exposes bright, young professionals to the field of biosurveillance. For this past summer’s competition, Dr. Charles decided to try something different. She devised a new way to inspire innovation and gain higher quality results for the development of novel applications to aid in chemical and biological situational awareness. To this end, Dr. Charles developed and instantiated an Innovation Bootcamp Program aimed at training the student interns how to work effectively in interdisciplinary teams and quickly tackle new challenging problems while still producing top quality products. This new program was founded on three main components for success: people, tools, and application.

Innovation, Innovation, Biosurveillance, Intern Co↗

Sensalert: A Real-time Group and Individual Health Tracking Application

Sensalert is a wearable health tracking application that enables monitoring of a target population’s health status in real-time. The application integrates health monitoring parameters from wearable sensors, e.g., temperature and heart rate, with relevant environmental parameters, e.g., weather and topography, and calculates the corresponding physiological strain index for each point in time. The objective of this application is to provide early warning, support decision making, and increase situational awareness by displaying comprehensive information and providing alerts at the right time and place. This application is the first of its kind being developed for integration into the Defense Threat Reduction Agencies Bio Surveillance Ecosystem (BSVE). We present the user requirements and design principles for developing this type of application. We hope this work helps and inspires future research in the area of wearable technologies for surveillance.

Huang, Zhuanyi↗

Machine Learning for Identifying Relevance to Biosurveillance in Multilingual Text

Objective: The objective is to develop an ensemble of machine learning algorithms to identify multilingual, online articles that are relevant to biosurveillance. Language morphology varies widely across languages and must be accounted for when designing algorithms. Here, we compare the performance of a word embedding-based approach and a topic modeling approach with machine learning algorithms to determine the best method for Chinese, Arabic, and French languages. Introduction: Global biosurveillance is an extremely important, yet challenging task. One form of global biosurveillance comes from harvesting open source online data (e.g. news, blogs, reports, RSS feeds). The information derived from this data can be used for timely detection and identification of biological threats all over the world. However, the more inclusive the data harvesting procedure is to ensure that all potentially relevant articles are collected, the more data that is irrelevant also gets harvested. This issue can become even more complex when the online data is in a non-native language. Foreign language articles not only create language-specific issues for Natural Language Processing (NLP), but also add a significant amount of translation costs. Previous work shows success in the use of combinatory monolingual classifiers in specific applications, e.g., legal domain [1]. A critical component for a comprehensive, online harvesting biosurveillance system is the capability to identify relevant foreign language articles from irrelevant ones based on the initial article information collected, without the additional cost of full text retrieval and translation.

Machine learning↗

Wearable Sensor Application for Integrated Early Warning and Health Surveillance

Objective: The Wearable Sensor Application developed by Pacific Northwest National Laboratory (PNNL) provides an early warning system for stressors to individual and group health using physiologic and environmental indicators. The application integrates health monitoring parameters from wearable sensors, e.g., temperature and heart rate, with relevant environmental parameters, e.g., weather and landscape data, and calculates the corresponding physiological strain index. The information is presented to the analyst in a group and individual view with real-time alerting of abnormal health parameters. This application is the first of its kind being developed for integration into the Defense Threat Reduction Agency's Biosurveillance Ecosystem (BSVE).Introduction: Wearable devices are a low cost, minimally invasive way to monitor health. Sensor data provides real-time physiological indictors of an individual’s health status without the requirement of health care professionals or facilities. Information gleamed from wearable sensors can be used to better understand physiological stressors and prodromal symptoms. In addition, this data can be used to monitor individuals that are in high risk of health-related problems.However, raw data from wearable sensors can be overwhelming to process and laborious to monitor for an individual and, even more so, for a group of individuals. Often specific combination of ranges of sensor readings are indicative of changes to health status and need to be evaluated together or used to calculate specific signal parameters. In addition, the environment surrounding the individual needs to be considered when interpreting the data. To address these issues, PNNL has developed an application that collects, analyzes, and integrates wearable sensor data with geographic landscape and weather information to provide a real-time early alert and situational awareness tool for monitoring the health of groups and individuals.Methods: The prototype application described here was a product of PNNL’s BSVE Application Development Competition. The final product that will be deployed in the BSVE is currently under development by PNNL and will vary slightly in the exact design and architecture described.Data. Wearable sensor data was collected from the Rim2Rim (R2R) Watch Study of individuals hiking the Grand Canyon in Arizona [1]. Weather information was obtained from nearby weather stations and mapping features were derived from Google Maps.Calculations. A physiological Strain Index (PSI) was calculated using core temperature estimates derived through a Kalman Filter approach and heart rate [2,3].Application. The prototype backend application development was based in Python with a MongoDB. The front-end development was built using a scalable architecture and modular approach with components in React and D3.Results: A prototype application was developed this past summer through the PNNL BSVE App Competition (Fig 1). The application was aimed at visualizing wearable sensor data from the Grand Canyon R2R hike dataset. Simulated real-time analysis was used to calculate health status of individuals hiking based on measured physiological parameters and to alert to individuals with signs of physiologic health stress. Visualization tools were incorporated to enable sensor data for individuals and the group to be viewed simultaneously along with pertinent weather, geographic, and elevation data.Many features described in the prototype application will be incorporated into the final BSVE application. The key changes will be 1) the ability to select given time periods for viewing historical data as well as the real-time data collection, 2) environmental data and map view will come from BSVE internal data sources, and 3) the alerts will provide more information and have their own page for reviewing.Conclusions: The Wearable Sensor Application developed by PNNL for integration into the BSVE provides an early warning system for individual and group health using physiologic and environmental parameters. The application highlights health status from wearable sensors and relevant environmental parameters while monitoring a calculated physiological strain index. With this tool, an analyst can easily monitor the health of individuals and groups with the aid of real-time alerting tool for early detection of abnormal health parameters.

Early Warning↗

NBIC Biofeeds: Deploying a New, Digital Tool for Open Source Biosurveillance across Federal Agencies

The National Biosurveillance Integration Center (NBIC) is deploying a scalable, flexible open source data collection, analysis, and dissemination tool to support biosurveillance operations by the U.S. Department of Homeland Security (DHS) and its federal interagency partners.IntroductionNBIC integrates, analyzes, and distributes key information about health and disease events to help ensure the nation’s responses are well-informed, save lives, and minimize economic impact. To meet its mission objectives, NBIC utilizes a variety of data sets, including open source information, to provide comprehensive coverage of biological events occurring across the globe. NBIC Biofeeds is a digital tool designed to improve the efficiency of analyzing large volumes of open source reporting and increase the number of relevant insights gleaned from this dataset. Moreover, the tool provides a mechanism to disseminate tailored, electronic message notifications in near-real time so that NBIC can share specific information of interest to its interagency partners in a timely manner. NBIC intends to implement operational use of the capability in FY 2018. The core components of the system are data collection, curation, and dissemination of information deemed important by NBIC subject matter experts. NBIC Biofeeds has captured information from more than 70,000 unique sources published from around the globe and presents, on average, 9,000 new biosurveillance-relevant articles to users each day. NBIC leverages a variety of data feeds, including third party aggregators like Google and subscription-based feeds such as HealthMap, as well as Really Simple Syndication (RSS) feeds and web-scraping of highly relevant sources. The NBIC biosurveillance taxonomy imbedded in the tool consists of more than 600 metadata targets that cover key information for understanding the significance of an active biological event, including etiologic agents, impact to humans and animals (e.g., infection severity, healthcare workers involved, type of host), social disruption, infrastructure strain, countermeasures engaged, and ‘red flag’ characteristics (e.g., pathogen appearance in a new geographic area, unusual clinical signs). This taxonomy serves as a foundation for data curation and can be tailored by NBIC partners to more directly meet their own mission objectives. At this time, metadata is predominately captured by NBIC analysts, who manually tag information, which triggers the population of three automatically-disseminated products from the tool: 1) the NBIC Daily Biosurveillance Review, 2) immediate and daily summary email notifications, and 3) custom-designed RSS feeds. These products are meant for individual recipients in the federal interagency and for consumption by other biosurveillance information technology systems, such as the Department of Defense, Defense Threat Reduction Agency (DTRA) Biosurveillance Ecosystem (BSVE). NBIC is working in partnership with DTRA to integrate NBIC Biofeeds as an application directly into the BSVE and further develop the BSVE as an all-in-one platform for biosurveillance data analytics. To improve the efficiency and effectiveness of gaining insights using NBIC Biofeeds, developers of the tool at the Pacific Northwest National Laboratory (PNNL) are researching and testing a variety of advanced analytics techniques focused on: 1) article relevancy ratings to improve the review of queried data, 2) significance ratings to elucidate the perceived severity of an event based on reported characteristics, 3) full-text article retrieval and storage for improved machine-tagging, and 4) anomaly detection for emerging threats. Testing and implementation of new analytic capabilities in NBIC Biofeeds is planned for this fiscal year. NBIC Biofeeds was developed to serve as a sophisticated and powerful open source biosurveillance technology of value to the federal government by providing information to stakeholders conducting open source biosurveillance as well as those consuming biosurveillance information. In FY 2018, NBIC Biofeeds will begin operational use by NBIC and an initial set of users in various federal agencies. User accounts for testing purposes will be available to other federal partners, and a broad scope of federal stakeholders can receive products directly from NBIC Biofeeds based on their interests. NBIC Biofeeds is expected to enable more rapid recognition and enhanced analysis of emerging biological events by NBIC analysts. NBIC anticipates other federal agencies with biosurveillance missions will find this technology of value and intends to offer use of the platform to those federal partners that can benefit from access to the tool and information generated from NBIC Biofeeds.

NBIC↗

Text-based Analytics for Biosurveillance

The ability to prevent, mitigate, or control a biological threat depends on how quickly the threat is identified and characterized. Ensuring the timely delivery of data and analytics is an essential aspect of providing adequate situational awareness in the face of a disease outbreak. This chapter outlines an analytic pipeline for supporting an advanced early warning system that can integrate multiple data sources and provide situational awareness of potential and occurring disease situations. The pipeline, includes real-time automated data analysis founded on natural language processing (NLP), semantic concept matching, and machine learning techniques, to enrich content with metadata related to biosurveillance. Online news articles are presented as an example use case for the pipeline, but the processes can be generalized to any textual data. In this chapter, the mechanics of a streaming pipeline are briefly discussed as well as the major steps required to provide targeted situational awareness. The text-based analytic pipeline includes various processing steps as well as identifying article relevance to biosurveillance (e.g., relevance algorithm) and article feature extraction (who, what, where, why, how, and when). The ability to prevent, mitigate, or control a biological threat depends on how quickly the threat is identified and characterized. Ensuring the timely delivery of data and analytics is an essential aspect of providing adequate situational awareness in the face of a disease outbreak. This chapter outlines an analytic pipeline for supporting an advanced early warning system that can integrate multiple data sources and provide situational awareness of potential and occurring disease situations. The pipeline, includes real-time automated data analysis founded on natural language processing (NLP), semantic concept matching, and machine learning techniques, to enrich content with metadata related to biosurveillance. Online news articles are presented as an example use case for the pipeline, but the processes can be generalized to any textual data. In this chapter, the mechanics of a streaming pipeline are briefly discussed as well as the major steps required to provide targeted situational awareness. The text-based analytic pipeline includes various processing steps as well as identifying article relevance to biosurveillance (e.g., relevance algorithm) and article feature extraction (who, what, where, why, how, and when).

Biomedical NLP↗

Multiple Document Representations from News Alerts for Automated Bio-surveillance Event Detection

Due to globalization, geographic boundaries no longer serve as effective shields for the spread of infectious diseases. In order to aid bio-surveillance analysts in disease tracking, recent research has been devoted to developing information retrieval and analysis methods utilizing the vast corpora of publicly available documents on the internet. In this work, we present methods for the automated retrieval and classification of documents related to active public health events. We demonstrate classification performance on an auto-generated corpus, using recurrent neural network, TFIDF, and Naive Bayes log count ratio document representations. By jointly modeling the title and description of a document, we achieve 97% recall and 93.3% accuracy with our best performing bio-surveillance event classification model; logistic regression on the combined output from a pair of bidirectional recurrent neural networks.

language analysis, Biosurveillance, document class↗

Uncovering the relationships between military community health and affects expressed in social media

Military populations present a small, unique community whose mental and physical health impacts the security of the nation. Recent literature has explored social media's ability to enhance disease surveillance and characterize distinct communities with encouraging results. We present a novel analysis of the relationships between influenza-like illnesses (ILI) clinical data and affects (i.e., emotions and sentiments) extracted from social media around military facilities. Our analyses examine (1) differences in affects expressed by military and control populations, (2) affect changes over time by users, (3) differences in affects expressed during high and low ILI seasons, and (4) correlations and cross-correlations between ILI clinical visits and affects from an unprecedented scale –171M geo-tagged tweets across 31 global geolocations. Key findings include: Military and control populations dier in the way they express affects in social media over space and time. Control populations express more positive and less negative sentiments and less sadness, fear, disgust, and anger emotions than military. However, affects expressed in social media by both populations within the same area correlate similarly with ILI visits to military health facilities. We have identified potential responsible co-factors leading to location variability, e.g., region or state locale, military service type and/or the ratio of military to civilian populations. For most locations, ILI proportions positively correlate with sadness and neutral sentiment, which are the affects most often expressed during high ILI season. The ILI proportions negatively correlate with fear, disgust, surprise, and positive sentiment. These results are similar to the low ILI season where anger, surprise, and positive sentiment are highest. Finally, cross-correlation analysis shows that most affects lead ILI clinical visits, i.e. are predictive of ILI data, with affect-ILI leading intervals dependent on geo-location and affect type. Altogether, information gained in this study exemplifies a usage of social media data to understand the correlation between psychological behavior and health in the military population and the potential for use of social media affects for prediction of ILI cases.

60 APPLIED LIFE SCIENCES↗