How the NIH is developing AI to help with COVID19

Artificial intelligence is a vital component in the fight against COVID-19. Healthcare benefits greatly from machine learning and artificial intelligence techniques that allow for better and faster mapping of the virus as well as for more comprehensive research to administrate the right treatment and create a vaccine.

The National Institutes of Health has launched the Medical Imagining and Data Resource Center (MIDRC) to deliver AI-based solutions for the new type of problems the world is facing in the actual climate. The goal is to combine the power of AI and medical imaging to better understand and retaliate against COVID-19. MIDRC under the supervision of the National Institute of Biomedical Imaging and Bioengineering (NIBIB) is determined to create new AI tools to facilitate:

• early detection of the virus
• monitoring of the treatment
• contact tracing of individuals
• projection of cases and mortality
• development of drugs and vaccines
• reducing the workload of healthcare professionals
• prevention of the disease

Moreover, their goal is to be able to use medical imaging to create personalized treatments for patients with COVID-19.

Artificial intelligence and imaging scans for personalized treatment

The NIH is relying on AI to contribute to the early detection of COVID-19. CT scans confirm the virus leaves “trademark” signs that help medical professionals distinguish it from other respiratory diseases, i.e. small spots and a slightly obscuring haze known by radiologists as “ground glass”. This indicates that the virus has led to fluid accumulation and tissue damage. Moreover, heart scans and ultrasounds also detect abnormalities in many coronavirus patients.

MIDRC aims to develop machine learning algorithms to create a new set of diagnostics according to the severity of the infection. Moreover, AI will be an important component in the process of predicting the response of patients to various treatments. AI innovations need to happen fast and be efficient. The world is counting on artificial intelligence not only to detect the virus and the severity of its impact but also to improve patient outcome.

In order to achieve these goals, MIDRC will work with a large, open-source database that will collect scans of COVID-19-affected chests from tens of thousands of patients. Access to this amount of data will help researchers evaluate the effects COVID-19 has on lung and cardiac tissue and familiarize them with COVID-19 imaging traces.

This important database will be hosted at the University of Chicago and managed by the American College of Radiology, the Radiological Society of North America, and the American Association of Physicists in Medicine.

Research and projects to address the immediate public health needs

Another mission of the NIH is to deliver solutions to the immediate needs the public has in correlation with the pandemic. We are talking here about solutions for communities with poor or no access to medical services and healthcare who are affected by the virus. The solutions rely on artificial intelligence to provide digital health technologies available on smartphones and wearable devices.

These AI tools have the ability to help us use containment efforts, like COVID-19 testing, quarantine, and social distancing exactly where they are needed and allow for the communities less affected by the virus to return to a seemingly normal living with less restrictions. But, more importantly, they would contribute to a lower risk of other local outbreaks.

Artificial intelligence is currently seen as a guiding light in the unknown of COVID-19. Applied to smartphones and wearable devices will help gather huge amounts of data. The data will then be analyzed by cutting-edge AI systems and machine learning methods. The results will be used to reduce the risk of infection and promote a return to normality.

Some of the platforms already in the works are a health measurement platform for the early detection of COVID-19 based on patient-consented data and self-reported data, a platform for monitoring patients with COVID-19 symptoms and patients who have already tested positive, as well as a platform that allows for the identification of COVID-19 and contact tracing based on Wi-Fi technologies.

Currently, the NIH has awarded contracts to seven companies and organizations to create artificial intelligence technology based on big data in order to contribute to the global fight against COVID-19. The estimated value of the projects amounts to $22.8 million.