scholarly journals Real-World Implications of a Rapidly Responsive COVID-19 Spread Model with Time-Dependent Parameters via Deep Learning: Model Development and Validation

10.2196/19907 ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. e19907 ◽  
Author(s):  
Se Young Jung ◽  
Hyeontae Jo ◽  
Hwijae Son ◽  
Hyung Ju Hwang
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Influenza Pandemic ◽  
The United States ◽  
Sir Model ◽  
Time Dependent ◽  
Systems Science ◽  
Model Parameters ◽  
Viral Spread ◽  
Spread Model

Background The COVID-19 pandemic has caused major disruptions worldwide since March 2020. The experience of the 1918 influenza pandemic demonstrated that decreases in the infection rates of COVID-19 do not guarantee continuity of the trend. Objective The aim of this study was to develop a precise spread model of COVID-19 with time-dependent parameters via deep learning to respond promptly to the dynamic situation of the outbreak and proactively minimize damage. Methods In this study, we investigated a mathematical model with time-dependent parameters via deep learning based on forward-inverse problems. We used data from the Korea Centers for Disease Control and Prevention (KCDC) and the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University for Korea and the other countries, respectively. Because the data consist of confirmed, recovered, and deceased cases, we selected the susceptible-infected-recovered (SIR) model and found approximated solutions as well as model parameters. Specifically, we applied fully connected neural networks to the solutions and parameters and designed suitable loss functions. Results We developed an entirely new SIR model with time-dependent parameters via deep learning methods. Furthermore, we validated the model with the conventional Runge-Kutta fourth order model to confirm its convergent nature. In addition, we evaluated our model based on the real-world situation reported from the KCDC, the Korean government, and news media. We also crossvalidated our model using data from the CSSE for Italy, Sweden, and the United States. Conclusions The methodology and new model of this study could be employed for short-term prediction of COVID-19, which could help the government prepare for a new outbreak. In addition, from the perspective of measuring medical resources, our model has powerful strength because it assumes all the parameters as time-dependent, which reflects the exact status of viral spread.

scholarly journals Real-World Implications of a Rapidly Responsive COVID-19 Spread Model with Time-Dependent Parameters via Deep Learning: Model Development and Validation (Preprint)

2020 ◽  
Author(s):  
Se Young Jung ◽  
Hyeontae Jo ◽  
Hwijae Son ◽  
Hyung Ju Hwang
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Influenza Pandemic ◽  
The United States ◽  
Sir Model ◽  
Time Dependent ◽  
Systems Science ◽  
Model Parameters ◽  
Viral Spread ◽  
Spread Model

BACKGROUND The COVID-19 pandemic has caused major disruptions worldwide since March 2020. The experience of the 1918 influenza pandemic demonstrated that decreases in the infection rates of COVID-19 do not guarantee continuity of the trend. OBJECTIVE The aim of this study was to develop a precise spread model of COVID-19 with time-dependent parameters via deep learning to respond promptly to the dynamic situation of the outbreak and proactively minimize damage. METHODS In this study, we investigated a mathematical model with time-dependent parameters via deep learning based on forward-inverse problems. We used data from the Korea Centers for Disease Control and Prevention (KCDC) and the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University for Korea and the other countries, respectively. Because the data consist of confirmed, recovered, and deceased cases, we selected the susceptible-infected-recovered (SIR) model and found approximated solutions as well as model parameters. Specifically, we applied fully connected neural networks to the solutions and parameters and designed suitable loss functions. RESULTS We developed an entirely new SIR model with time-dependent parameters via deep learning methods. Furthermore, we validated the model with the conventional Runge-Kutta fourth order model to confirm its convergent nature. In addition, we evaluated our model based on the real-world situation reported from the KCDC, the Korean government, and news media. We also crossvalidated our model using data from the CSSE for Italy, Sweden, and the United States. CONCLUSIONS The methodology and new model of this study could be employed for short-term prediction of COVID-19, which could help the government prepare for a new outbreak. In addition, from the perspective of measuring medical resources, our model has powerful strength because it assumes all the parameters as time-dependent, which reflects the exact status of viral spread.

scholarly journals SIR Model Parameters Estimation with COVID-19 Data

2021 ◽  
pp. 97-117
Author(s):  
Nilson C. Roberty ◽  
Lucas S. F. de Araujo
Keyword(s):  
Removal Rate ◽  
Sir Model ◽  
Parameters Estimation ◽  
Systems Science ◽  
Model Parameters ◽  
Science And Engineering ◽  
University Center ◽  
Johns Hopkins University ◽  
System Solution ◽  
Rate Of Decay

Based on the SIR model that divides the population into susceptible, infected and removed individuals, data about the evolution of the pandemic compiled by the Johns Hopkins University Center for Systems Science and Engineering (JHUCSSE) are integrated into the numerical system solution. The system parameters Rate of Contact β, Basic Reproduction Number R0 and Removal Rate γ, also named Rate of Decay, are determined according to a ridge regression approach and a mobile statistical scheme with different averages. Data is automatically downloaded from https://raw.githubusercontent.com/CSSEGISandData/COVID-19. The main Python libraries used are Numpy, Pandas, Skit-Learn, Requests and Urllib.

scholarly journals A study of disproportionately affected populations by race/ethnicity during the SARS-CoV-2 pandemic using multi-population SEIR modeling and ensemble data assimilation

2021 ◽  
Vol 3 (3) ◽  
pp. 479
Author(s):  
Emmanuel Fleurantin ◽  
Christian Sampson ◽  
Daniel Paul Maes ◽  
Justin Bennett ◽  
Tayler Fernandes-Nunez ◽  
...  
Keyword(s):  
Public Health ◽  
Data Assimilation ◽  
The United States ◽  
Time Dependent ◽  
Reproductive Number ◽  
Model Parameters ◽  
Critical Metrics ◽  
Ensemble Data Assimilation ◽  
Ensemble Data ◽  
Public Health Officials

<p style='text-indent:20px;'>The disparity in the impact of COVID-19 on minority populations in the United States has been well established in the available data on deaths, case counts, and adverse outcomes. However, critical metrics used by public health officials and epidemiologists, such as a time dependent viral reproductive number (<inline-formula><tex-math id="M1">\begin{document}$ R_t $\end{document}</tex-math></inline-formula>), can be hard to calculate from this data especially for individual populations. Furthermore, disparities in the availability of testing, record keeping infrastructure, or government funding in disadvantaged populations can produce incomplete data sets. In this work, we apply ensemble data assimilation techniques which optimally combine model and data to produce a more complete data set providing better estimates of the critical metrics used by public health officials and epidemiologists. We employ a multi-population SEIR (Susceptible, Exposed, Infected and Recovered) model with a time dependent reproductive number and age stratified contact rate matrix for each population. We assimilate the daily death data for populations separated by ethnic/racial groupings using a technique called Ensemble Smoothing with Multiple Data Assimilation (ESMDA) to estimate model parameters and produce an <inline-formula><tex-math id="M10000">\begin{document}$R_t(n)$\end{document}</tex-math></inline-formula> for the <inline-formula><tex-math id="M2000">\begin{document}$n^{th}$\end{document}</tex-math></inline-formula> population. We do this with three distinct approaches, (1) using the same contact matrices and prior <inline-formula><tex-math id="M30000">\begin{document}$R_t(n)$\end{document}</tex-math></inline-formula> for each population, (2) assigning contact matrices with increased contact rates for working age and older adults to populations experiencing disparity and (3) as in (2) but with a time-continuous update to <inline-formula><tex-math id="M4">\begin{document}$R_t(n)$\end{document}</tex-math></inline-formula>. We make a study of 9 U.S. states and the District of Columbia providing a complete time series of the pandemic in each and, in some cases, identifying disparities not otherwise evident in the aggregate statistics.</p>

Epidemic Evolution: Multiple Analytical Solutions for the SIR Model

2020 ◽  
Author(s):  
Ian Lerche
Keyword(s):  
Analytical Solutions ◽  
Influenza Pandemic ◽  
Dynamical Evolution ◽  
Analytic Form ◽  
Sir Model ◽  
Analytic Solutions ◽  
Time Dependent ◽  
Closed Analytic Form

While there are many models of epidemic evolution perhaps the basis for such models finds itself in the lumped behavior expressed through the so-called SIR model (Susceptible, Infectious, Recovered) from which spring many related models. This paper discusses multiple analytic solutions to that equation including those that are available in closed analytic form and those for which at least one final integral has to be done numerically, so-called quasi-analytic solutions. The solutions are intrinsically time-dependent of course. The hope is that such an investigation will lead to a better understanding of when and how models can be of use in studying the dynamical evolution of diseases including, perhaps, the great influenza pandemic of 1918 together with later pandemics and epidemics not excluding the Covid-19 pandemic of the present day.

Weakly Supervised Spatial Deep Learning for Earth Image Segmentation Based on Imperfect Polyline Labels

2022 ◽  
Vol 13 (2) ◽  
pp. 1-20
Author(s):  
Zhe Jiang ◽  
Wenchong He ◽  
Marcus Stephen Kirby ◽  
Arpan Man Sainju ◽  
Shaowen Wang ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Real World ◽  
Large Scale ◽  
Model Parameters ◽  
Vector Representation ◽  
High Quality ◽  
Geometric Properties ◽  
Location Errors ◽  
Weakly Supervised

In recent years, deep learning has achieved tremendous success in image segmentation for computer vision applications. The performance of these models heavily relies on the availability of large-scale high-quality training labels (e.g., PASCAL VOC 2012). Unfortunately, such large-scale high-quality training data are often unavailable in many real-world spatial or spatiotemporal problems in earth science and remote sensing (e.g., mapping the nationwide river streams for water resource management). Although extensive efforts have been made to reduce the reliance on labeled data (e.g., semi-supervised or unsupervised learning, few-shot learning), the complex nature of geographic data such as spatial heterogeneity still requires sufficient training labels when transferring a pre-trained model from one region to another. On the other hand, it is often much easier to collect lower-quality training labels with imperfect alignment with earth imagery pixels (e.g., through interpreting coarse imagery by non-expert volunteers). However, directly training a deep neural network on imperfect labels with geometric annotation errors could significantly impact model performance. Existing research that overcomes imperfect training labels either focuses on errors in label class semantics or characterizes label location errors at the pixel level. These methods do not fully incorporate the geometric properties of label location errors in the vector representation. To fill the gap, this article proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations. Specifically, we model label location errors in the vector representation to partially reserve geometric properties (e.g., spatial contiguity within line segments). Evaluations on real-world datasets in the National Hydrography Dataset (NHD) refinement application illustrate that the proposed framework outperforms baseline methods in classification accuracy.

scholarly journals Parameter Optimization for Real-World ENSO Forecast in an Intermediate Coupled Model

2019 ◽  
Vol 147 (5) ◽  
pp. 1429-1445 ◽  
Author(s):  
Yuchu Zhao ◽  
Zhengyu Liu ◽  
Fei Zheng ◽  
Yishuai Jin
Keyword(s):  
Data Assimilation ◽  
Parameter Optimization ◽  
Real World ◽  
Climate Models ◽  
Coupled Model ◽  
Prediction Skill ◽  
Model Parameters ◽  
Real World Data ◽  
The Real ◽  
Advection Term

Abstract We performed parameter estimation in the Zebiak–Cane model for the real-world scenario using the approach of ensemble Kalman filter (EnKF) data assimilation and the observational data of sea surface temperature and wind stress analyses. With real-world data assimilation in the coupled model, our study shows that model parameters converge toward stable values. Furthermore, the new parameters improve the real-world ENSO prediction skill, with the skill improved most by the parameter of the highest climate sensitivity (gam2), which controls the strength of anomalous upwelling advection term in the SST equation. The improved prediction skill is found to be contributed mainly by the improvement in the model dynamics, and second by the improvement in the initial field. Finally, geographic-dependent parameter optimization further improves the prediction skill across all the regions. Our study suggests that parameter optimization using ensemble data assimilation may provide an effective strategy to improve climate models and their real-world climate predictions in the future.

scholarly journals National Trends in Emergency Department Care Processes for Acute Myocardial Infarction in the United States, 2005 to 2015

2020 ◽  
Vol 9 (20) ◽  
Author(s):  
Akshay Pendyal ◽  
Craig Rothenberg ◽  
Jean E. Scofi ◽  
Harlan M. Krumholz ◽  
Basmah Safdar ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Emergency Department ◽  
Length Of Stay ◽  
Real World ◽  
The United States ◽  
Emergency Department Care ◽  
Care Processes ◽  
Ed Visits

Background Despite investments to improve quality of emergency care for patients with acute myocardial infarction (AMI), few studies have described national, real‐world trends in AMI care in the emergency department (ED). We aimed to describe trends in the epidemiology and quality of AMI care in US EDs over a recent 11‐year period, from 2005 to 2015. Methods and Results We conducted an observational study of ED visits for AMI using the National Hospital Ambulatory Medical Care Survey, a nationally representative probability sample of US EDs. AMI visits were classified as ST‐segment–elevation myocardial infarction (STEMI) and non‐STEMI. Outcomes included annual incidence of AMI, median ED length of stay, ED disposition type, and ED administration of evidence‐based medications. Annual ED visits for AMI decreased from 1 493 145 in 2005 to 581 924 in 2015. Estimated yearly incidence of ED visits for STEMI decreased from 1 402 768 to 315 813. The proportion of STEMI sent for immediate, same‐hospital catheterization increased from 12% to 37%. Among patients with STEMI sent directly for catheterization, median ED length of stay decreased from 62 to 37 minutes. ED administration of antithrombotic and nonaspirin antiplatelet agents rose for STEMI (23%–31% and 10%–27%, respectively). Conclusions National, real‐world trends in the epidemiology of AMI in the ED parallel those of clinical registries, with decreases in AMI incidence and STEMI proportion. ED care processes for STEMI mirror evolving guidelines that favor high‐intensity antiplatelet therapy, early invasive strategies, and regionalization of care.

scholarly journals Time fused coefficient SIR model with application to COVID-19 epidemic in the United States

2021 ◽  
pp. 1-15
Author(s):  
Hou-Cheng Yang ◽  
Yishu Xue ◽  
Yuqing Pan ◽  
Qingyang Liu ◽  
Guanyu Hu
Keyword(s):  
United States ◽  
The United States ◽  
Sir Model

scholarly journals Fractional SIR-Model for Estimating Transmission Dynamics of COVID-19 in India

J ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 86-100
Author(s):  
Nita H. Shah ◽  
Ankush H. Suthar ◽  
Ekta N. Jayswal ◽  
Ankit Sikarwar
Keyword(s):  
Basic Reproduction Number ◽  
Reproduction Number ◽  
Transmission Rate ◽  
Sir Model ◽  
Time Dependent ◽  
Contact Rate ◽  
Distribution Maps ◽  
Fundamental Parameters ◽  
Different Order ◽  
The Basic Reproduction Number

In this article, a time-dependent susceptible-infected-recovered (SIR) model is constructed to investigate the transmission rate of COVID-19 in various regions of India. The model included the fundamental parameters on which the transmission rate of the infection is dependent, like the population density, contact rate, recovery rate, and intensity of the infection in the respective region. Looking at the great diversity in different geographic locations in India, we determined to calculate the basic reproduction number for all Indian districts based on the COVID-19 data till 7 July 2020. By preparing district-wise spatial distribution maps with the help of ArcGIS 10.2, the model was employed to show the effect of complete lockdown on the transmission rate of the COVID-19 infection in Indian districts. Moreover, with the model's transformation to the fractional ordered dynamical system, we found that the nature of the proposed SIR model is different for the different order of the systems. The sensitivity analysis of the basic reproduction number is done graphically which forecasts the change in the transmission rate of COVID-19 infection with change in different parameters. In the numerical simulation section, oscillations and variations in the model compartments are shown for two different situations, with and without lockdown.

Sign in / Sign up

Export Citation Format

Share Document