scholarly journals Fast and Accurate Influenza Forecasting in the United States with Inferno

2021 ◽  
Author(s):  
Dave Osthus
Keyword(s):  
Situational Awareness ◽  
Model Development ◽  
Predictive Performance ◽  
The United States ◽  
Primary Objective ◽  
Forecasting Model ◽  
Accurate Information ◽  
Disease Forecasting ◽  
Minimal Impact ◽  
Forecasting Models

AbstractInfectious disease forecasting is an emerging field and has the potential to improve public health through anticipatory resource allocation, situational awareness, and mitigation planning. By way of exploring and operationalizing disease forecasting, the U.S. Centers for Disease Control and Prevention (CDC) has hosted FluSight since the 2013/14 flu season, an annual flu forecasting challenge. Since FluSight’s onset, forecasters have developed and improved forecasting models in an effort to provide more timely, reliable, and accurate information about the likely progression of the outbreak. While improving the predictive performance of these forecasting models is often the primary objective, it is also important for a forecasting model to run quickly, facilitating further model development, improvement, and scalability. In this vein I introduce Inferno, a fast and accurate flu forecasting model inspired by Dante, the top performing model in the 2018/19 FluSight challenge. When compared to all models that participated in FluSight 2018/19, Inferno would have placed 2nd in both the national and state challenges, behind only Dante. Inferno, however, runs in minutes and is trivially parallelizable, while Dante takes hours to run, representing a significant operational improvement with minimal impact to performance. A future consideration for forecasting competitions like FluSight will be how to encourage improvements to secondarily important properties of forecasting models, such as runtime, generalizability, and interpretability.

scholarly journals Searching for the GOAT of tennis win prediction

2016 ◽  
Vol 12 (3) ◽  
Author(s):  
Stephanie Ann Kovalchik
Keyword(s):  
Paired Comparison ◽  
Model Development ◽  
Predictive Performance ◽  
Comparative Performance ◽  
Forecasting Models ◽  
Data Regression ◽  
Model Predictions ◽  
Professional Tennis ◽  
Performance Benchmark ◽  
Player Ranking

AbstractSports forecasting models – beyond their interest to bettors – are important resources for sports analysts and coaches. Like the best athletes, the best forecasting models should be rigorously tested and judged by how well their performance holds up against top competitors. Although a number of models have been proposed for predicting match outcomes in professional tennis, their comparative performance is largely unknown. The present paper tests the predictive performance of 11 published forecasting models for predicting the outcomes of 2395 singles matches during the 2014 season of the Association of Tennis Professionals Tour. The evaluated models fall into three categories: regression-based, point-based, and paired comparison models. Bookmaker predictions were used as a performance benchmark. Using only 1 year of prior performance data, regression models based on player ranking and an Elo approach developed by FiveThirtyEight were the most accurate approaches. The FiveThirtyEight model predictions had an accuracy of 75% for matches of the most highly-ranked players, which was competitive with the bookmakers. The inclusion of career-to-date improved the FiveThirtyEight model predictions for lower-ranked players (from 59% to 64%) but did not change the performance for higher-ranked players. All models were 10–20 percentage points less accurate at predicting match outcomes among lower-ranked players than matches with the top players in the sport. The gap in performance according to player ranking and the simplicity of the information used in Elo ratings highlight directions for further model development that could improve the practical utility and generalizability of forecasting in tennis.

scholarly journals Using Syndromic Surveillance Data to Monitor Endocarditis and Sepsis among Drug Users

2017 ◽  
Vol 9 (1) ◽  
Author(s):  
Lana Deyneka ◽  
Anne Hakenewerth ◽  
Zachary Faigen ◽  
Amy Ising ◽  
Clifton Barnett
Keyword(s):  
Drug Use ◽  
Syndromic Surveillance ◽  
Drug Users ◽  
Situational Awareness ◽  
Temporal Trends ◽  
The United States ◽  
Case Definition ◽  
Accurate Information ◽  
Discharge Data ◽  
Syndromic Surveillance System

ObjectiveTo describe how the state syndromic surveillance system(NC DETECT) was used to initiate near real time surveillance forendocarditis, sepsis and skin infection among drug users.IntroductionRecreational drug use is a major problem in the United States andaround the world. Specifically, drug abuse results in heavy use ofemergency department (ED) services, and is a high financial burdento society and to the hospitals due to chronic ill health and multipleinjection drug use complications. Intravenous drug users are at highrisk of developing sepsis and endocarditis due to the use of a dirty orinfected needle that is either shared with someone else or re-used. Itcan also occur when a drug user repeatedly injects into an inflamedand infected site or due to the poor overall health of an injection druguser. The average cost of hospitalization for aortic valve replacementin USA is about $165,000, and in order for the valve replacement tobe successful, patients must abstain from using drugs.MethodsWe examined temporal trends of drug-related visits to hospitalEDs, as well as drug-related related ED admissions complicated withendocarditis, bacteremia and sepsis.ResultsThe trends in Endocarditis/Sepsis and drug-related relatedadmissions appear to echo overdose related ED admissions increase.Patients ED return visits and hospitalizations for the same problem arealso growing compare to the previous years. We will discuss the NCDETECT case definition used to monitor drug overdose/dependenceand infection, case definition transition from ICD-9 to ICD-10 codes,and will share surveillance analysis results.ConclusionsNC DETECT’s system flexibility has been important in rapidlyestablishing surveillance of infections among drug users. Near realtime analysis on hospital, county and state levels can be performedusing NC DETECT system reports to provide state officials, hospitalsand LHDs with situational awareness. Limitations: Syndromicsurveillance ED data contains less accurate information about thediagnosis codes, procedures, length of stay, and severity comparingto the hospital discharge data.

scholarly journals Multiscale influenza forecasting

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Dave Osthus ◽  
Kelly R. Moran
Keyword(s):  
Temporal Variability ◽  
Health Utility ◽  
The United States ◽  
Forecasting Model ◽  
Spatial And Temporal Variability ◽  
Disease Forecasting ◽  
Seasonal Forecasts ◽  
Short Term ◽  
Coherent Forecasts ◽  
State Regional

AbstractInfluenza forecasting in the United States (US) is complex and challenging due to spatial and temporal variability, nested geographic scales of interest, and heterogeneous surveillance participation. Here we present Dante, a multiscale influenza forecasting model that learns rather than prescribes spatial, temporal, and surveillance data structure and generates coherent forecasts across state, regional, and national scales. We retrospectively compare Dante’s short-term and seasonal forecasts for previous flu seasons to the Dynamic Bayesian Model (DBM), a leading competitor. Dante outperformed DBM for nearly all spatial units, flu seasons, geographic scales, and forecasting targets. Dante’s sharper and more accurate forecasts also suggest greater public health utility. Dante placed 1st in the Centers for Disease Control and Prevention’s prospective 2018/19 FluSight challenge in both the national and regional competition and the state competition. The methodology underpinning Dante can be used in other seasonal disease forecasting contexts having nested geographic scales of interest.

Community Outreach Partnership Center (COPC)

2003 ◽  
Vol 1 (2) ◽  
pp. 44-51
Author(s):  
Kristine Brown ◽  
James Sturges
Keyword(s):  
Health Promotion ◽  
Los Angeles ◽  
Mexican Immigrants ◽  
Community Outreach ◽  
Well Being ◽  
Integrated Services ◽  
The United States ◽  
Primary Objective ◽  
Health Promotion Program ◽  
Federal Grant

With the continued influx of Mexican immigrants to the United States, especially to Southern California, health concerns and needs have increased among this population over the last several years. California State Polytechnic University, Pomona (Cal Poly Pomona) obtained a federal grant that provided resources to establish the Community Outreach Partnership Center (COPC). COPC consists of comprehensive efforts to improve the overall well-being of the Angela Chanslor area within the City of Pomona in East Los Angeles. Focus areas of the project include 1) Education and Integrated Services, 2) Community Planning and Capacity Building for Neighborhood Revitalization and Safety, and 3) Job Development and Training. The focus of this paper is health promotion activities within Education and Integrated Services. The primary objective of this portion of the program was to provide residents with physical examinations and health screenings, health education, and medical and social service referrals. Topics discussed are the target community, general overview of COPC, Family Services Information and Referral Program (i.e. health promotion program within Education and Integrated Services), program impact and results, and suggestions for continued implementation and future efforts. / Con la influencia continua de inmigrantes Mexicanos a los Estados Unidos, especialmente al sur de California, ciertas necesidades con respecto a la salud han incrementado en esta poblacion en los ultimos anos. California State Polytechnic University, Pomona (Cal Poly Pomona). Obtuvo ayuda Federal para establecer El Community Outreach Partnership Center (COPC). El centro COPC consiste de esfuerzos conprensivos para mejorar el bienestar del area Angela Chanslor que esta ubicado en la Ciudad de Pomona en la parte Este de Los Angeles. Las partes enfocadas del proyecto incluyen, 1) Educacion y servicios Integrados, 2) Plan para la Comunidad y un Edificio de Capacitacion para la comunidad que dara revitalizacion y seguridad, 3) Y habrira trabajos y entrenamientos. El enfoque de este proyecto es de actividades en Promocion de Salud aliadas con educacion y Servicios Integrados. El objetivo principal de esta porcion del programa era de proveer a los residentes con examinaciones fisicas, educacion para la salud, y eran referidas a servicios medicos y sociales. Los topicos que son tratados son: La comunidad que sera ayudada, El enfoque general de COPC, informacion del programa para referir a servicios familiares, el impacto del programa y resultados, y sugerencias para implementar futuros esfuerzos.

Forecasting Interconnections in International Housing Markets: Evidence from the Dynamic Model Averaging Approach

2020 ◽  
Vol 42 (1) ◽  
pp. 37-103
Author(s):  
Hardik A. Marfatia
Keyword(s):  
Dynamic Model ◽  
Model Averaging ◽  
Housing Markets ◽  
The United States ◽  
Forecasting Model ◽  
Change Over Time ◽  
The United Kingdom ◽  
Novel Approach ◽  
Dynamic Model Averaging ◽  
Over Time

In this paper, I undertake a novel approach to uncover the forecasting interconnections in the international housing markets. Using a dynamic model averaging framework that allows both the coefficients and the entire forecasting model to dynamically change over time, I uncover the intertwined forecasting relationships in 23 leading international housing markets. The evidence suggests significant forecasting interconnections in these markets. However, no country holds a constant forecasting advantage, including the United States and the United Kingdom, although the U.S. housing market's predictive power has increased over time. Evidence also suggests that allowing the forecasting model to change is more important than allowing the coefficients to change over time.

scholarly journals A Neutrosophic Forecasting Model for Time Series Based on First-Order State and Information Entropy of High-Order Fluctuation

Entropy ◽  
2019 ◽  
Vol 21 (5) ◽  
pp. 455 ◽  
Author(s):  
Hongjun Guan ◽  
Zongli Dai ◽  
Shuang Guan ◽  
Aiwu Zhao
Keyword(s):  
Time Series ◽  
Information Entropy ◽  
Stock Exchange ◽  
Time Series Forecasting ◽  
High Order ◽  
Stock Index ◽  
Neutrosophic Set ◽  
Forecasting Model ◽  
Forecasting Models ◽  
Proposed Model

In time series forecasting, information presentation directly affects prediction efficiency. Most existing time series forecasting models follow logical rules according to the relationships between neighboring states, without considering the inconsistency of fluctuations for a related period. In this paper, we propose a new perspective to study the problem of prediction, in which inconsistency is quantified and regarded as a key characteristic of prediction rules. First, a time series is converted to a fluctuation time series by comparing each of the current data with corresponding previous data. Then, the upward trend of each of fluctuation data is mapped to the truth-membership of a neutrosophic set, while a falsity-membership is used for the downward trend. Information entropy of high-order fluctuation time series is introduced to describe the inconsistency of historical fluctuations and is mapped to the indeterminacy-membership of the neutrosophic set. Finally, an existing similarity measurement method for the neutrosophic set is introduced to find similar states during the forecasting stage. Then, a weighted arithmetic averaging (WAA) aggregation operator is introduced to obtain the forecasting result according to the corresponding similarity. Compared to existing forecasting models, the neutrosophic forecasting model based on information entropy (NFM-IE) can represent both fluctuation trend and fluctuation consistency information. In order to test its performance, we used the proposed model to forecast some realistic time series, such as the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX), the Shanghai Stock Exchange Composite Index (SHSECI), and the Hang Seng Index (HSI). The experimental results show that the proposed model can stably predict for different datasets. Simultaneously, comparing the prediction error to other approaches proves that the model has outstanding prediction accuracy and universality.

Acoustic Modeling of Meteorological Effects on Roadway Noise

2021 ◽  
pp. 036119812199458
Author(s):  
Roger L. Wayson ◽  
Kenneth Kaliski
Keyword(s):  
Road Traffic ◽  
Traffic Noise ◽  
Model Development ◽  
The United States ◽  
Noise Model ◽  
Road Traffic Noise ◽  
Atmospheric Conditions ◽  
Noise Propagation ◽  
Transportation Research ◽  
Meteorological Effects

Modeling road traffic noise levels without including the effects of meteorology may lead to substantial errors. In the United States, the required model is the Traffic Noise Model which does not include meteorology effects caused by refraction. In response, the Transportation Research Board sponsored NCHRP 25-52, Meteorological Effects on Roadway Noise, to collect highway noise data under different meteorological conditions, document the meteorological effects on roadway noise propagation under different atmospheric conditions, develop best practices, and provide guidance on how to: (a) quantify meteorological effects on roadway noise propagation; and (b) explain those effects to the public. The completed project at 16 barrier and no-barrier measurement positions adjacent to Interstate 17 (I-17) in Phoenix, Arizona provided the database which has enabled substantial developments in modeling. This report provides more recent information on the model development that can be directly applied by the noise analyst to include meteorological effects from simple look-up tables to more precise use of statistical equations.

scholarly journals Multicenter point prevalence evaluation of the utilization and safety of drug therapies for COVID-19 at the onset of the pandemic timeline in the United States

2021 ◽  
Author(s):  
Nathaniel J Rhodes ◽  
Atheer Dairem ◽  
William J Moore ◽  
Anooj Shah ◽  
Michael J Postelnick ◽  
...  
Keyword(s):  
Clinical Trials ◽  
Drug Therapy ◽  
Supportive Care ◽  
The United States ◽  
Primary Objective ◽  
Point Prevalence ◽  
Medical Centers ◽  
Academic Medical ◽  
History Of ◽  
Secondary Objective

Abstract Disclaimer In an effort to expedite the publication of articles related to the COVID-19 pandemic, AJHP is posting these manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time. Purpose There are currently no FDA-approved medications for the treatment of coronavirus disease 2019 (COVID-19). At the onset of the pandemic, off-label medication use was supported by limited or no clinical data. We sought to characterize experimental COVID-19 therapies and identify safety signals during this period. Methods We conducted a non-interventional, multicenter, point prevalence study of patients hospitalized with suspected/confirmed COVID-19. Clinical and treatment characteristics within a 24-hour window were evaluated in a random sample of up to 30 patients per site. The primary objective was to describe COVID-19–targeted therapies. The secondary objective was to describe adverse drug reactions (ADRs). Results A total of 352 patients treated for COVID-19 at 15 US hospitals From April 18 to May 8, 2020, were included in the study. Most patients were treated at academic medical centers (53.4%) or community hospitals (42.6%). Sixty-seven patients (19%) were receiving drug therapy in addition to supportive care. Drug therapies used included hydroxychloroquine (69%), remdesivir (10%), and interleukin-6 antagonists (9%). Five patients (7.5%) were receiving combination therapy. The rate of use of COVID-19–directed drug therapy was higher in patients with vs patients without a history of asthma (14.9% vs 7%, P = 0.037) and in patients enrolled in clinical trials (26.9% vs 3.2%, P < 0.001). Among those receiving drug therapy, 8 patients (12%) experienced an ADR, and ADRs were recognized at a higher rate in patients enrolled in clinical trials (62.5% vs 22%; odds ratio, 5.9; P = 0.028). Conclusion While we observed high rates of supportive care for patients with COVID-19, we also found that ADRs were common among patients receiving drug therapy, including those enrolled in clinical trials. Comprehensive systems are needed to identify and mitigate ADRs associated with experimental COVID-19 treatments.

scholarly journals Application of big data in healthcare: examination of the military experience

2021 ◽  
Author(s):  
David Berry
Keyword(s):  
Big Data ◽  
Vietnam War ◽  
Business Models ◽  
Model Development ◽  
The United States ◽  
Practical Implementation ◽  
Systems Research ◽  
System Versus ◽  
Military Systems ◽  
The Military

AbstractHealthcare is fully embracing the promise of Big Data for improving performance and efficiency. Such a paradigm shift, however, brings many unforeseen impacts both positive and negative. Healthcare has largely looked at business models for inspiration to guide model development and practical implementation of Big Data. Business models, however, are limited in their application to healthcare as the two represent a complicated system versus a complex system respectively. Healthcare must, therefore, look toward other examples of complex systems to better gauge the potential impacts of Big Data. Military systems have many similarities with healthcare with a wealth of systems research, as well as practical field experience, from which healthcare can draw. The experience of the United States Military with Big Data during the Vietnam War is a case study with striking parallels to issues described in modern healthcare literature. Core principles can be extracted from this analysis that will need to be considered as healthcare seeks to integrate Big Data into its active operations.

scholarly journals Predictive performance of international COVID-19 mortality forecasting models

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Joseph Friedman ◽  
Patrick Liu ◽  
Christopher E. Troeger ◽  
Austin Carter ◽  
Robert C. Reiner ◽  
...  
Keyword(s):  
Predictive Performance ◽  
Absolute Error ◽  
Decision Makers ◽  
Government Interventions ◽  
World Region ◽  
Mortality Forecasting ◽  
Forecasting Models ◽  
Pandemic Response ◽  
Alternative Scenarios ◽  
Absolute Percent Error

AbstractForecasts and alternative scenarios of COVID-19 mortality have been critical inputs for pandemic response efforts, and decision-makers need information about predictive performance. We screen n = 386 public COVID-19 forecasting models, identifying n = 7 that are global in scope and provide public, date-versioned forecasts. We examine their predictive performance for mortality by weeks of extrapolation, world region, and estimation month. We additionally assess prediction of the timing of peak daily mortality. Globally, models released in October show a median absolute percent error (MAPE) of 7 to 13% at six weeks, reflecting surprisingly good performance despite the complexities of modelling human behavioural responses and government interventions. Median absolute error for peak timing increased from 8 days at one week of forecasting to 29 days at eight weeks and is similar for first and subsequent peaks. The framework and public codebase (https://github.com/pyliu47/covidcompare) can be used to compare predictions and evaluate predictive performance going forward.

Sign in / Sign up

Export Citation Format

Share Document