Public Health - Santé Publique

During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making.

 

We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables.

 

Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745–0.830) when predicting deterioration within 96 hours.

 

The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time.

 

 

In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

 

read the open article at https://www.nature.com/articles/s41746-021-00453-0

 

Lire l'article complet sur : www.nature.com

Via nrip

We discuss the concept of a participatory digital contact notification approach to assist tracing of contacts who are exposed to confirmed cases of coronavirus disease (COVID-19);

 

The core functionality of our concept is to provide a usable, labor-saving tool for contact tracing by confirmed cases themselves

 

the approach is simple and affordable for countries with limited access to health care resources and advanced technology.

 

The proposed tool serves as a supplemental contract tracing approach to counteract the shortage of health care staff while providing privacy protection for both cases and contacts.

• This tool can be deployed on the internet or as a plugin for a smartphone app.


• Confirmed cases with COVID-19 can use this tool to provide contact information (either email addresses or mobile phone numbers) of close contacts.


• The system will then automatically send a message to the contacts informing them of their contact status, what this status means, the actions that should follow (eg, self-quarantine, respiratory hygiene/cough etiquette), and advice for receiving early care if they develop symptoms.


• The name of the sender of the notification message by email or mobile phone can be anonymous or not.


• The message received by the contact contains no disease information but contains a security code for the contact to log on the platform to retrieve the information.

 

Conclusion

The successful application of this tool relies heavily on public social responsibility and credibility, and it remains to be seen if the public would adopt such a tool and what mechanisms are required to prevent misuse.

 

This is a simple tool that does not require complicated computer techniques despite strict user privacy protection design with respect to countries and regions. Additionally, this tool can help avoid coercive surveillance, facilitate the allocation of health resources, and prioritize clinical service for patients with COVID-19. Information obtained from the platform can also increase our understanding of the epidemiology of COVID-19.

 

read this concept paper at https://mhealth.jmir.org/2020/6/e20369

 

 

Lire l'article complet sur : mhealth.jmir.org

Via nrip

The COVID-19 pandemic is the greatest public health crisis of the last 100 years. Countries have responded with various levels of lockdown to save lives and stop health systems from being overwhelmed. At the same time, lockdowns entail large socioeconomic costs.

 

One exit strategy under consideration is a mobile phone app that traces the close contacts of those infected with COVID-19.

 

Recent research has demonstrated the theoretical effectiveness of this solution in different disease settings. However, concerns have been raised about such apps because of the potential privacy implications. This could limit the acceptability of app-based contact tracing in the general population. As the effectiveness of this approach increases strongly with app uptake, it is crucial to understand public support for this intervention.

 

Objective: The objective of this study is to investigate the user

acceptability of a contact-tracing app in five countries hit by the pandemic.

Methods: We conducted a largescale, multicountry study (N=5995) to measure public support for the digital contact tracing of COVID-19 infections.

 

We ran anonymous online surveys in France, Germany, Italy, the United Kingdom, and the United States and measured intentions to use a contact-tracing app across different installation regimes (voluntary installation vs automatic installation by mobile phone providers) and studied how these intentions vary across individuals and countries.

Results: We found strong support for the app under both regimes, in all countries, across all subgroups of the population, and irrespective of regional-level COVID-19 mortality rates.

We investigated the main factors that may hinder or facilitate uptake and found that concerns about cybersecurity and privacy, together with a lack of trust in the government, are the main barriers to adoption.

Conclusions:

 

Epidemiological evidence shows that app-based contact tracing can suppress the spread of COVID-19 if a high enough proportion of the population uses the app and that it can still reduce the number of infections if uptake is moderate. Our findings show that the willingness to install the app is very high. The available evidence suggests that app-based contact tracing may be a viable approach to control the diffusion of COVID-19.

 

read the study at https://mhealth.jmir.org/2020/8/e19857

 

Lire l'article complet sur : mhealth.jmir.org

Via nrip

“ATMAN AI”, an Artificial Intelligence algorithm that can detect the presence of COVID-19 disease in Chest X Rays, has been developed to combat COVID fatalities involving lung. ATMAN AI is used for chest X-ray screening as a triaging tool in Covid-19 diagnosis, a method for rapid identification and assessment of lung involvement. This is a joint effort of the DRDO Centre for Artificial Intelligence and Robotics (CAIR), 5C Network & HCG Academics. This will be utilized by online diagnostic startup 5C Network with support of HCG Academics across India.

 

Triaging COVID suspect patients using X Ray is fast, cost effective and efficient. It can be a very useful tool especially in smaller towns in India owing to lack of easy access to CT scans there.

 

This will also reduce the existing burden on radiologists and make CT machines which are being used for COVID be used for other diseases and illness owing to overload for CT scans.

 

The novel feature namely “Believable AI” along with existing ResNet models have improved the accuracy of the software and being a machine learning tool, the accuracy will improve continually.

 

Chest X-Rays of RT-PCR positive hospitalized patients in various stages of disease involvement were retrospectively analysed using Deep Learning & Convolutional Neural Network models by an indigenously developed deep learning application by CAIR-DRDO for COVID -19 screening using digital chest X-Rays. The algorithm showed an accuracy of 96.73%.

 

 read more at http://indiaai.gov.in/news/drdo-cair-5g-network-and-hcg-academics-develop-atman-ai

 

 

Lire l'article complet sur : indiaai.gov.in

Via nrip