scholarly journals Forecasting the Transmission Trends of Respiratory Infectious Diseases with an Exposure-Risk-Based Model at the Microscopic Level

2021 ◽  
Author(s):  
Ziwei Cui ◽  
Ming Cai ◽  
Yao Xiao ◽  
Zheng Zhu ◽  
Mofeng Yang
Keyword(s):  
Infectious Diseases ◽  
Risk Estimation ◽  
Absolute Error ◽  
The United States ◽  
Microscopic Level ◽  
Percentage Error ◽  
Human Society ◽  
Exposure Risk ◽  
Microscopic Models ◽  
Respiratory Infectious Diseases

Respiratory infectious diseases (e.g., COVID- 19) have brought huge damages to human society, and the accurate prediction of their transmission trends is essential for both the health system and policymakers. Most related studies concentrate on epidemic trend forecasting at the macroscopic level, which ignores the microscopic social interactions among individuals. Meanwhile, current microscopic models are still not able to sufficiently decipher the individual-based spreading process and lack valid quantitative tests. To tackle these problems, we propose an exposure-risk-based model at the microscopic level, including 4 modules: individual movement, virion-laden droplet movement, individual exposure risk estimation, and prediction of new cases. First, the front two modules reproduce the movements of individuals and the droplets of infectors’ expiratory activities. Then, the outputs are fed to the third module for estimating the personal exposure risk. Accordingly, the number of new cases is predicted in the final module. Our model outperforms 4 existing macroscopic or microscopic models through the forecast of new cases of COVID-19 in the United States. Specifically, mean absolute error, root mean square error and mean absolute percentage error by our model are 2454.70, 3170.51, and 3.38% smaller than the minimum results of comparison models, respectively. In sum, the proposed model successfully describes the scenarios from a microscopic perspective and shows great potential for predicting the transmission trends with different scenarios and management policies.

scholarly journals Forecasting the Transmission Trends of Respiratory Infectious Diseases with an Exposure-Risk-Based Model at the Microscopic Level

2021 ◽  
Author(s):  
ziwei Cui ◽  
Ming Cai ◽  
Yao Xiao ◽  
Zheng Zhu ◽  
Mofeng Yang
Keyword(s):  
Infectious Diseases ◽  
Risk Estimation ◽  
Absolute Error ◽  
The United States ◽  
Microscopic Level ◽  
Percentage Error ◽  
Human Society ◽  
Exposure Risk ◽  
Microscopic Models ◽  
Respiratory Infectious Diseases

Respiratory infectious diseases (e.g., COVID- 19) have brought huge damages to human society, and the accurate prediction of their transmission trends is essential for both the health system and policymakers. Most related studies concentrate on epidemic trend forecasting at the macroscopic level, which ignores the microscopic social interactions among individuals. Meanwhile, current microscopic models are still not able to sufficiently decipher the individual-based spreading process and lack valid quantitative tests. To tackle these problems, we propose an exposure-risk-based model at the microscopic level, including 4 modules: individual movement, virion-laden droplet movement, individual exposure risk estimation, and prediction of new cases. First, the front two modules reproduce the movements of individuals and the droplets of infectors’ expiratory activities. Then, the outputs are fed to the third module for estimating the personal exposure risk. Accordingly, the number of new cases is predicted in the final module. Our model outperforms 4 existing macroscopic or microscopic models through the forecast of new cases of COVID-19 in the United States. Specifically, mean absolute error, root mean square error and mean absolute percentage error by our model are 2454.70, 3170.51, and 3.38% smaller than the minimum results of comparison models, respectively. In sum, the proposed model successfully describes the scenarios from a microscopic perspective and shows great potential for predicting the transmission trends with different scenarios and management policies.

scholarly journals Forecasting the Transmission Trends of Respiratory Infectious Diseases with an Exposure-Risk-Based Model at the Microscopic Level

2021 ◽  
Author(s):  
ziwei Cui ◽  
Ming Cai ◽  
Yao Xiao ◽  
Zheng Zhu ◽  
Mofeng Yang
Keyword(s):  
Infectious Diseases ◽  
Risk Estimation ◽  
Absolute Error ◽  
The United States ◽  
Microscopic Level ◽  
Percentage Error ◽  
Human Society ◽  
Exposure Risk ◽  
Microscopic Models ◽  
Respiratory Infectious Diseases

Respiratory infectious diseases (e.g., COVID- 19) have brought huge damages to human society, and the accurate prediction of their transmission trends is essential for both the health system and policymakers. Most related studies concentrate on epidemic trend forecasting at the macroscopic level, which ignores the microscopic social interactions among individuals. Meanwhile, current microscopic models are still not able to sufficiently decipher the individual-based spreading process and lack valid quantitative tests. To tackle these problems, we propose an exposure-risk-based model at the microscopic level, including 4 modules: individual movement, virion-laden droplet movement, individual exposure risk estimation, and prediction of new cases. First, the front two modules reproduce the movements of individuals and the droplets of infectors’ expiratory activities. Then, the outputs are fed to the third module for estimating the personal exposure risk. Accordingly, the number of new cases is predicted in the final module. Our model outperforms 4 existing macroscopic or microscopic models through the forecast of new cases of COVID-19 in the United States. Specifically, mean absolute error, root mean square error and mean absolute percentage error by our model are 2454.70, 3170.51, and 3.38% smaller than the minimum results of comparison models, respectively. In sum, the proposed model successfully describes the scenarios from a microscopic perspective and shows great potential for predicting the transmission trends with different scenarios and management policies.

scholarly journals A Novel Matrix Profile-Guided Attention LSTM Model for Forecasting COVID-19 Cases in USA

2021 ◽  
Vol 9 ◽  
Author(s):  
Qian Liu ◽  
Daryl L. X. Fung ◽  
Leann Lac ◽  
Pingzhao Hu
Keyword(s):  
Health Care ◽  
Hospital Admission ◽  
Short Term Memory ◽  
Absolute Error ◽  
The United States ◽  
Percentage Error ◽  
Group A ◽  
Novel Coronavirus ◽  
Delphi Research ◽  
Death Cases

Background: The outbreak of the novel coronavirus disease 2019 (COVID-19) has been raging around the world for more than 1 year. Analysis of previous COVID-19 data is useful to explore its epidemic patterns. Utilizing data mining and machine learning methods for COVID-19 forecasting might provide a better insight into the trends of COVID-19 cases. This study aims to model the COVID-19 cases and perform forecasting of three important indicators of COVID-19 in the United States of America (USA), which are the adjusted percentage of daily admitted hospitalized COVID-19 cases (hospital admission), the number of daily confirmed COVID-19 cases (confirmed cases), and the number of daily death cases caused by COVID-19 (death cases).Materials and Methods: The actual COVID-19 data from March 1, 2020 to August 5, 2021 were obtained from Carnegie Mellon University Delphi Research Group. A novel forecasting algorithm was proposed to model and predict the three indicators. This algorithm is a hybrid of an unsupervised time series anomaly detection technique called matrix profile and an attention-based long short-term memory (LSTM) model. Several classic statistical models and the baseline recurrent neural network (RNN) models were used as the baseline models. All models were evaluated using a repeated holdout training and test strategy.Results: The proposed matrix profile-assisted attention-based LSTM model performed the best among all the compared models, which has the root mean square error (RMSE) = 1.23, 31612.81, 467.17, mean absolute error (MAE) = 0.95, 26259.55, 364.02, and mean absolute percentage error (MAPE) = 0.25, 1.06, 0.55, for hospital admission, confirmed cases, and death cases, respectively.Conclusion: The proposed model is more powerful in forecasting COVID-19 cases. It can potentially aid policymakers in making prevention plans and guide health care managers to allocate health care resources reasonably.

scholarly journals Forecasting COVID 19 Confirmed Cases Using Machine Learning: the Case of America

2020 ◽  
Author(s):  
Mario Jojoa ◽  
Begoña Garcia-Zapirain
Keyword(s):  
United States ◽  
Machine Learning ◽  
Open Data ◽  
Absolute Error ◽  
The United States ◽  
Percentage Error ◽  
Support Vector ◽  
Learning Tools ◽  
The European Union ◽  
Testing Stage

This paper presents a Multilayer Perceptron and Support Vector Machine algorithms approach to predict the number of COVID19 infections in different countries of America. It intends to serve as a tool for decision-making and tackling the pandemic that the world is currently facing. The models were trained and tested using open data from the European Union repository where a time series of confirmed contagious cases was modeled until May 25, 2020. The hyperparameters as number of neurons per layer were set up using a tabu list algorithm. The countries selected to carry out the study were Brazil, Chile, Colombia, Mexico, Peru and the United States. The metrics used are Pearson's correlation coefficient (CP), Mean Absolute Error (MAE), and Mean Percentage Error (MPE). For the testing stage we obtained the following results: Brazil, CP=0.65, MAE=2508 and MPE=17%; Chile, CP=0.64, MAE=504, MPE=16%; Colombia, CP=0.83, MAE=76, MPE=9%; Mexico, CP=0.77, MAE=231, MPE=9%; Peru, CP=0.76, MAE=686, MPE=18% and the United States of America, CP=0.93, MAE=799, MPE=4%. This resulted in powerful machine learning tools although it is necessary to use specific algorithms depending on the data and the stage of the country’s pandemic.

scholarly journals Verification of Healthcare Personnel Immunity as a Strategy for Measles Preparedness

2020 ◽  
Vol 41 (S1) ◽  
pp. s431-s432
Author(s):  
Rachael Snyders ◽  
Hilary Babcock ◽  
Christopher Blank
Keyword(s):  
Infectious Diseases ◽  
Multidisciplinary Team ◽  
The United States ◽  
Transmission Risk ◽  
Healthcare Personnel ◽  
Serological Tests ◽  
Preparedness Plan ◽  
Vaccine Preventable Diseases ◽  
Measles Outbreaks ◽  
Centralized Database

Background: Immunization resistance is fueling a resurgence of vaccine-preventable diseases in the United States, where several large measles outbreaks and 1,282 measles cases were reported in 2019. Concern about these measles outbreaks prompted a large healthcare organization to develop a preparedness plan to limit healthcare-associated transmission. Verification of employee rubeola immunity and immunization when necessary was prioritized because of transmission risk to nonimmune employees and role of the healthcare personnel in responding to measles cases. Methods: The organization employs ∼31,000 people in diverse settings. A multidisciplinary team was formed by infection prevention, infectious diseases, occupational health, and nursing departments to develop the preparedness plan. Immunity was monitored using a centralized database. Employees without evidence of immunity were asked to provide proof of vaccination, defined by the CDC as 2 appropriately timed doses of rubeola-containing vaccine, or laboratory confirmation of immunity. Employees were given 30 days to provide documentation or to obtain a titer at the organization’s expense. Staff with negative titers were given 2 weeks to coordinate with the occupational heath department for vaccination. Requests for medical or religious accommodations were evaluated by occupational heath staff, the occupational heath medical director, and the human resources department. All employees were included, though patient-interfacing employees in departments considered higher risk were prioritized. These areas were the emergency, dermatology, infectious diseases, labor and delivery, obstetrics, and pediatrics departments. Results: At the onset of the initiative in June 2019, 4,009 employees lacked evidence of immunity. As of November 2019, evidence of immunity had been obtained for 3,709 employees (92.5%): serological evidence of immunity was obtained for 2,856 (71.2%), vaccine was administered to 584 (14.6%), and evidence of previous vaccination was provided by 269 (6.7%). Evidence of immunity has not been documented for 300 (7.5%). The organization administered 3,626 serological tests and provided 997 vaccines, costing ∼$132,000. Disposition by serological testing is summarized in Table 1. Conclusions: A measles preparedness strategy should include proactive assessment of employees’ immune status. It is possible to expediently assess a large number of employees using a multidisciplinary team with access to a centralized database. Consideration may be given to prioritization of high-risk departments and patient-interfacing roles to manage workload.Funding: NoneDisclosures: None

scholarly journals Learning to Detain Asylum Seekers and the Growth of Mass Immigration Detention in the United States

2021 ◽  
pp. 1-29
Author(s):  
Smita Ghosh ◽  
Mary Hoopes
Keyword(s):  
United States ◽  
Infectious Diseases ◽  
Cognitive Dissonance ◽  
Media Coverage ◽  
Asylum Seekers ◽  
Ad Hoc ◽  
The United States ◽  
Critical Component ◽  
Immigration Detention ◽  
Important Shift

Drawing upon an analysis of congressional records and media coverage from 1981 to 1996, this article examines the growth of mass immigration detention. It traces an important shift during this period: while detention began as an ad hoc executive initiative that was received with skepticism by the legislature, Congress was ultimately responsible for entrenching the system over objections from the agency. As we reveal, a critical component of this evolution was a transformation in Congress’s perception of asylum seekers. While lawmakers initially decried their detention, they later branded them as dangerous. Lawmakers began describing asylum seekers as criminals or agents of infectious diseases in order to justify their detention, which then cleared the way for the mass detention of arriving migrants more broadly. Our analysis suggests that they may have emphasized the dangerousness of asylum seekers to resolve the dissonance between their theoretical commitments to asylum and their hesitance to welcome newcomers. In addition to this distinctive form of cognitive dissonance, we discuss a number of other implications of our research, including the ways in which the new penology framework figured into the changing discourse about detaining asylum seekers.

scholarly journals Survey of Saliva Components and Virus Sensors for Prevention of COVID-19 and Infectious Diseases

Biosensors ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 14
Author(s):  
Priya Dave ◽  
Roberto Rojas-Cessa ◽  
Ziqian Dong ◽  
Vatcharapan Umpaichitra
Keyword(s):  
Infectious Diseases ◽  
Dental Health ◽  
The United States ◽  
Human Saliva ◽  
Field Application ◽  
Future Research ◽  
Prevention Measures ◽  
Control And Prevention ◽  
Close Distance

The United States Centers for Disease Control and Prevention considers saliva contact the lead transmission mean of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which causes the coronavirus disease 2019 (COVID-19). Saliva droplets or aerosols expelled by sneezing, coughing, breathing, and talking may carry this virus. People in close distance may be exposed directly to these droplets or indirectly when touching the droplets that fall on surrounding surfaces and ending up contracting COVID-19 after touching the mucosa tissue of their faces. It is of great interest to quickly and effectively detect the presence of SARS-CoV-2 in an environment, but the existing methods only work in laboratory settings, to the best of our knowledge. However, it may be possible to detect the presence of saliva in the environment and proceed with prevention measures. However, detecting saliva itself has not been documented in the literature. On the other hand, many sensors that detect different organic components in saliva to monitor a person’s health and diagnose different diseases, ranging from diabetes to dental health, have been proposed and they may be used to detect the presence of saliva. This paper surveys sensors that detect organic and inorganic components of human saliva. Humidity sensors are also considered in the detection of saliva because a large portion of saliva is water. Moreover, sensors that detect infectious viruses are also included as they may also be embedded into saliva sensors for a confirmation of the presence of the virus. A classification of sensors by their working principles and the substances they detect is presented, including the sensors’ specifications, sample size, and sensitivity. Indications of which sensors are portable and suitable for field application are presented. This paper also discusses future research and challenges that must be resolved to realize practical saliva sensors. Such sensors may help minimize the spread of not only COVID-19 but also other infectious diseases.

Sign in / Sign up

Export Citation Format

Share Document