scholarly journals DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic

2020 ◽  
Author(s):  
Mahdi Rezaei ◽  
Mohsen Azarmi
Keyword(s):  
Risk Assessment ◽  
High Risk ◽  
World Health Organisation ◽  
Infection Risk ◽  
Superior Performance ◽  
World Health ◽  
Mapping Technique ◽  
People Detection ◽  
Social Distancing ◽  
Risk Zones

Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a Deep Neural Network-based Model for automated people detection, tracking, and inter-people distances estimation in the crowd, using common CCTV security cameras. The proposed DNN model along with an inverse perspective mapping technique leads to a very accurate people detection and social distancing monitoring in challenging conditions, including people occlusion, partial visibility, and lighting variations. We also provide an online infection risk assessment scheme by statistical analysis of the Spatio-temporal data from the moving trajectories and the rate of social distancing violations. We identify high-risk zones with the highest possibility of virus spread and infection. This may help authorities to redesign the layout of a public place or to take precaution actions to mitigate high-risk zones. The efficiency of the proposed methodology is evaluated on the Oxford Town Centre dataset, with superior performance in terms of accuracy and speed compared to three state-of-the-art methods.

scholarly journals DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic

2020 ◽  
Author(s):  
Mahdi Rezaei ◽  
Mohsen Azarmi
Keyword(s):  
Risk Assessment ◽  
High Risk ◽  
World Health Organisation ◽  
Superior Performance ◽  
World Health ◽  
People Detection ◽  
Social Distancing ◽  
Online Risk ◽  
Risk Zones ◽  
Spatio Temporal

Abstract Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a generic Deep Neural Network-Based model for automated people detection, tracking, and inter-people distances estimation in the crowd, using common CCTV security cameras. The proposed model includes a YOLOv4-based framework and inverse perspective mapping for accurate people detection and social distancing monitoring in challenging conditions, including people occlusion, partial visibility, and lighting variations. We also provide an online risk assessment scheme by statistical analysis of the Spatio-temporal data from the moving trajectories and the rate of social distancing violations. We identify high-risk zones with the highest possibility of virus spread and infection. This may help authorities to redesign the layout of a public place or to take precaution actions to mitigate high-risk zones. The efficiency of the proposed methodology is evaluated on the Oxford Town Centre dataset, with superior performance in terms of accuracy and speed compared to three state-of-the-art methods.

scholarly journals DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic

2020 ◽  
Author(s):  
Mahdi Rezaei ◽  
Mohsen Azarmi
Keyword(s):  
Risk Assessment ◽  
High Risk ◽  
World Health Organisation ◽  
Superior Performance ◽  
World Health ◽  
People Detection ◽  
Social Distancing ◽  
Online Risk ◽  
Risk Zones ◽  
Spatio Temporal

Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a generic Deep Neural Network-Based model for automated people detection, tracking, and inter-people distances estimation in the crowd, using common CCTV security cameras. The proposed model includes a YOLOv4-based framework and inverse perspective mapping for accurate people detection and social distancing monitoring in challenging conditions, including people occlusion, partial visibility, and lighting variations. We also provide an online risk assessment scheme by statistical analysis of the Spatio-temporal data from the moving trajectories and the rate of social distancing violations. We identify high-risk zones with the highest possibility of virus spread and infections. This may help authorities to redesign the layout of a public place or to take precaution actions to mitigate high-risk zones. The efficiency of the proposed methodology is evaluated on the Oxford Town Centre dataset, with superior performance in terms of accuracy and speed compared to three state-of-the-art methods.

scholarly journals DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic

2020 ◽  
Vol 10 (21) ◽  
pp. 7514
Author(s):  
Mahdi Rezaei ◽  
Mohsen Azarmi
Keyword(s):  
Risk Assessment ◽  
High Risk ◽  
Human Action ◽  
Infection Risk ◽  
Human Detection ◽  
Superior Performance ◽  
World Health ◽  
People Detection ◽  
Social Distancing ◽  
Risk Zones

Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-m physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a hybrid Computer Vision and YOLOv4-based Deep Neural Network (DNN) model for automated people detection in the crowd in indoor and outdoor environments using common CCTV security cameras. The proposed DNN model in combination with an adapted inverse perspective mapping (IPM) technique and SORT tracking algorithm leads to a robust people detection and social distancing monitoring. The model has been trained against two most comprehensive datasets by the time of the research—the Microsoft Common Objects in Context (MS COCO) and Google Open Image datasets. The system has been evaluated against the Oxford Town Centre dataset (including 150,000 instances of people detection) with superior performance compared to three state-of-the-art methods. The evaluation has been conducted in challenging conditions, including occlusion, partial visibility, and under lighting variations with the mean average precision of 99.8% and the real-time speed of 24.1 fps. We also provide an online infection risk assessment scheme by statistical analysis of the spatio-temporal data from people’s moving trajectories and the rate of social distancing violations. We identify high-risk zones with the highest possibility of virus spread and infection. This may help authorities to redesign the layout of a public place or to take precaution actions to mitigate high-risk zones. The developed model is a generic and accurate people detection and tracking solution that can be applied in many other fields such as autonomous vehicles, human action recognition, anomaly detection, sports, crowd analysis, or any other research areas where the human detection is in the centre of attention.

scholarly journals Live wildlife trade in markets - a scoping review to inform risk assessment of emerging infectious diseases

2021 ◽  
Author(s):  
Victoria J Brookes ◽  
Okta Wismandanu ◽  
Etih Sudarnika ◽  
Justin A Roby ◽  
Lynne Hayes ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Infectious Diseases ◽  
Scoping Review ◽  
Epistemic Uncertainty ◽  
Mammalian Species ◽  
Emerging Infectious Diseases ◽  
World Health Organisation ◽  
World Health ◽  
Wildlife Trade ◽  
The Impact

Wet markets are important for food security in many regions worldwide but have come under scrutiny due to their potential role in the emergence of infectious diseases. The sale of live wildlife has been highlighted as a particular risk, and the World Health Organisation has called for the banning of live, wild-caught mammalian species in markets unless risk assessment and effective regulations are in place. Following PRISMA guidelines, we conducted a global scoping review of peer-reviewed information about the sale of live, terrestrial wildlife in markets that are likely to sell fresh food, and collated data about the characteristics of such markets, activities involving live wildlife, the species sold, their purpose, and animal, human, and environmental health risks that were identified. Of the 59 peer-reviewed records within scope, only 25% (n = 14) focussed on disease risks; the rest focused on the impact of wildlife sale on conservation. Although there were some global patterns (for example, the types of markets and purpose of sale of wildlife), there was wide diversity and huge epistemic uncertainty in all aspects associated with live, terrestrial wildlife sale in markets such that the feasibility of accurate assessment of the risk of emerging infectious disease associated with live wildlife trade in markets is limited. Given the value of both wet markets and wildlife trade and the need to support food affordability and accessibility, conservation, public health, and the social and economic aspects of livelihoods of often vulnerable people, there are major information gaps that need to be addressed to develop evidence-based policy in this environment. This review identifies these gaps and provides a foundation from which information for risk assessments can be collected.

Single-center prognostic validation of the risk assessment of the 2015 ESC/ERS guidelines in patients with pulmonary arterial hypertension in Japan

2020 ◽  
Vol 98 (9) ◽  
pp. 653-658 ◽  
Author(s):  
Ryo Imai ◽  
Shiro Adachi ◽  
Masahiro Yoshida ◽  
Shigetake Shimokata ◽  
Yoshihisa Nakano ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Pulmonary Arterial Hypertension ◽  
High Risk ◽  
Arterial Hypertension ◽  
Risk Group ◽  
Low Risk ◽  
World Health ◽  
Right Atrial ◽  
Walking Distance ◽  
Pulmonary Arterial

The 2015 European Society of Cardiology/European Respiratory Society guidelines for the diagnosis and treatment of pulmonary hypertension include a multidimensional risk assessment for patients with pulmonary arterial hypertension (PAH). However, prognostic validations of this risk assessment are limited, especially outside Europe. Here, we validated the risk assessment strategy in PAH patients in our institution in Japan. Eighty consecutive PAH patients who underwent right heart catheterization between November 2006 and December 2018 were analyzed. Patients were classified as low, intermediate, or high risk by using a simplified version of the risk assessment that included seven variables: World Health Organization functional class, 6-min walking distance, peak oxygen consumption, brain natriuretic peptide, right atrial pressure, mixed venous oxygen saturation, and cardiac index. The high-risk group showed significantly higher mortality than the low- or intermediate-risk group at baseline (P < 0.001 for both comparisons), and the mortalities in the intermediate- and low-risk groups were both low (P = 0.989). At follow-up, patients who improved to or maintained a low-risk status showed better survival than those who did not (P = 0.041). Our data suggest that this risk assessment can predict higher mortality risk and long-term survival in PAH patients in Japan.

Prediction of fatal and non-fatal cardiovascular events in young and middle-aged healthy workers: The IberScore model

2019 ◽  
pp. 204748731989488 ◽  
Author(s):  
Carlos Fernández-Labandera ◽  
Eva Calvo-Bonacho ◽  
Pedro Valdivielso ◽  
Luis Quevedo-Aguado ◽  
Paloma Martínez-Munoz ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Cardiovascular Risk ◽  
High Risk ◽  
Cardiovascular Events ◽  
Clinical Utility ◽  
Superior Performance ◽  
Valuable Insight ◽  
New Model ◽  
Temporal Validation

Aims Our primary objective was to improve risk assessment for fatal and non-fatal cardiovascular events in a working population, mostly young and healthy. Methods We conducted a prospective cohort study to derive a survival model to predict fatal and non-fatal 10-year cardiovascular risk. We recruited 992,523 workers, free of diagnosed cardiovascular disease at entry, over six years, from 2004–2009. We divided the sample into two independent cohorts: a derivation one (626,515 workers; from 2004–2006) and a temporal validation one (366,008 workers; over 2007–2009). Then, we followed both cohorts over 10 years and registered all fatal and non-fatal cardiovascular events. We built a new risk calculator using an estimation of cardiovascular biological age as a predictor and named it IberScore. There were remarkable differences between this new model and Systematic Coronary Risk Evaluation (SCORE) (in both the specification and the equation). Results Over the 10-year follow-up, we found 3762 first cardiovascular events (6‰) in the derivation cohort. Most of them (80.3%) were non-fatal ischaemic events. If we had been able to use our model at the beginning of the study, we had classified in the ‘high-risk’ or ‘very high-risk’ groups 82% of those who suffered a cardiovascular event during the follow-up. All the post-estimation tests showed superior performance (true positive rate: 81.8% vs 11.8%), higher discrimination power and better clinical utility (standardised net benefit: 58% vs 13%) for IberScore when compared to SCORE. Conclusion Risk assessment of fatal and non-fatal cardiovascular events in young and healthy workers was improved when compared to the previously used model (SCORE). The latter was not reliable to predict cardiovascular risk in our sample. The new model showed superior clinical utility and provided four useful measures for risk assessment. We gained valuable insight into cardiovascular ageing and its predictors.

scholarly journals Early Computational Detection of Potential High Risk SARS-CoV-2 Variants

2021 ◽  
Author(s):  
Karim Beguir ◽  
Marcin J Skwark ◽  
Yunguan Fu ◽  
Thomas Pierrot ◽  
Santiago Nicolas Lopez Carranza ◽  
...  
Keyword(s):  
High Risk ◽  
Immune Evasion ◽  
Immune Escape ◽  
Warning System ◽  
World Health Organisation ◽  
Language Models ◽  
Spike Protein ◽  
World Health ◽  
Increased Risk

The ongoing COVID-19 pandemic is leading to the discovery of hundreds of novel SARS-CoV-2 variants on a daily basis. While most variants do not impact the course of the pandemic, some variants pose significantly increased risk when the acquired mutations allow better evasion of antibody neutralisation in previously infected or vaccinated subjects, or increased transmissibility. Early detection of such high risk variants (HRVs) is paramount for the proper management of the pandemic. However, experimental assays to determine immune evasion and transmissibility characteristics of new variants are resource-intensive and time-consuming, potentially leading to delayed appropriate responses by decision makers. Here we present a novel in silico approach combining Spike protein structure modelling and large protein transformer language models on Spike protein sequences, to accurately rank SARS-CoV-2 variants for immune escape and fitness potential. We validate our immune escape and fitness metrics with in vitro pVNT and binding assays. These metrics can be combined into an automated Early Warning System (EWS) capable of evaluating new variants in minutes and risk monitoring variant lineages in near real-time. The EWS flagged 12 out of 13 variants, designated by the World Health Organisation (WHO, Alpha-Omicron) as potentially dangerous, on average two months ahead of them being designated as such, demonstrating its ability to help increase preparedness against future variants. Omicron was flagged by the EWS on the day its sequence was made available, with immune evasion and binding metrics subsequently confirmed through our in vitro experiments.

scholarly journals Risk assessment in medically treated chronic thromboembolic pulmonary hypertension patients

2018 ◽  
Vol 52 (5) ◽  
pp. 1800248 ◽  
Author(s):  
Marion Delcroix ◽  
Gerd Staehler ◽  
Henning Gall ◽  
Ekkehard Grünig ◽  
Matthias Held ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Pulmonary Hypertension ◽  
High Risk ◽  
Chronic Thromboembolic Pulmonary Hypertension ◽  
Low Risk ◽  
World Health ◽  
Right Atrial ◽  
European Respiratory Society ◽  
Thromboembolic Pulmonary Hypertension

Abbreviated versions of the risk stratification strategy of the European Society of Cardiology (ESC)/European Respiratory Society (ERS) pulmonary hypertension guidelines have been recently validated in patients with pulmonary arterial hypertension. We aimed to investigate their prognostic value in medically treated chronic thromboembolic pulmonary hypertension (CTEPH) patients from the COMPERA registry, which collects six variables of interest (World Health Organization Functional Class, 6-min walk distance, brain natriuretic peptide, right atrial pressure, cardiac index and mixed venous oxygen saturation).We included patients with at least one follow-up visit, no pulmonary endarterectomy and at least three of the six variables available, and classified the patients into low-, intermediate- and high-risk groups. As a secondary analysis, the number of noninvasive low-risk criteria was counted. The association between risk assessment and survival was evaluated.Data from inclusion and follow-up (median 7 months) visits were available for 561 and 231 patients, respectively. Baseline 1- and 5-year survival estimates were significantly different (p<0.0001) in the baseline low-risk (98.6% and 88.3%, respectively), intermediate-risk (94.9% and 61.8%, respectively) and high-risk (75.5% and 32.9%, respectively) cohorts. Follow-up data were even more discriminative, with 100%, 92% and 69% 1-year survival, respectively. The number of low-risk noninvasive criteria was also associated with survival.These analyses suggest that the ESC/ERS risk assessment may be applicable in patients with medically treated CTEPH.

scholarly journals Disconnecting for the good: A network-oriented model for social contagion of opinions and social network interventions to increase adherence to social distancing

2020 ◽  
Author(s):  
Eric Araújo ◽  
Mariza Ferro ◽  
Gabrieli Silva
Keyword(s):  
Social Network ◽  
World Health Organisation ◽  
Social Contagion ◽  
Positive Opinion ◽  
World Health ◽  
Current Time ◽  
Social Distancing ◽  
Health Authorities ◽  
Best Response ◽  
The World

The pandemic of the new COVID-19 has raised many questions to a very connected society as to how to best respond to such a challenge at this current time. The best response so far is to call people for following the instructions from the World Health Organisation (WHO) as a way of reducing the spread of the virus and thus relieving the health system, striving to avoid a collapse. This work studies the spread of positive opinion on adhering to social distancing based on network topology and metrics using a network-oriented model for social contagion. It is shown that interventions based on social network measurements can be used to boost the spread of positive opinion about adhering to these measures. It is also shown that our model accounts for the relevance the health authorities have on encouraging people to partake in social distancing voluntarily.

Sign in / Sign up

Export Citation Format

Share Document