AI might be effective weapon against COVID-19
The novel coronavirus is one of the most infectious diseases to have reached our green planet in the last decades, if not the most lethal one. This has spread to more than 90 countries in just over three months since the virus was first identified in mainland China, infected more than 185,000 people and claimed more than 3,500 lives.
As governments and health organizations struggle to control coronavirus spread, they need all the support they can get from artificial intelligence, including. While current AI technologies are far from replicating human intelligence, they prove to be very helpful in monitoring outbreaks, diagnosing patients, disinfecting areas and speeding up process of finding a cure for COVID-19.
Data science and machine learning might be two of the most effective weapons we have in the fight against the coronavirus outbreak.
Blue Dot utilizes natural language processing and machine learning algorithms to peruse hundreds of sources of knowledge for early signs of contagious epidemics. The AI investigates comments from government agencies, commercial flights, animal welfare reports, climate data from satellites, and news reports. With so much data being generated on coronavirus every day, the AI algorithms can help home in on the bits that can provide pertinent information on the spread of the virus. It can also find important correlations between data points, such as the movement patterns of the people who are living in the areas most affected by the virus.
The organization also hires hundreds of specialists working in a range of fields including geographic information systems, spatial modeling, data analysis, computer sciences, as well as pediatric infectious disease, travel and tropical medicine, and public health specialists. The experts are analyzing the details flagged by the AI and sending out reports on their results.
Combined with human expert assistance, Blue Dot’s AI can not only predict the emergence of an outbreak but also predict how it will spread. In the case of COVID-19, the AI successfully identified the towns to which the virus would be spread after it surfaced in Wuhan. Training by machine learning algorithms studying travel patterns were able to predict where the people who had contracted coronavirus were likely to travel.
Using computer vision to detect coronavirus infection
At border crossings and airports, you also saw the COVID-19 screenings. Health officers are using thermometer weapons and visually monitoring passengers for symptoms of fever, coughing and trouble breathing.
Today, on a broad scale, computer vision algorithms will do the same. An AI program developed by the Chinese tech giant Baidu uses computer vision-equipped cameras and infrared sensors to predict the temperatures of people in public areas. The device is capable of screening up to 200 people every minute and measuring their temperature within 0.5 degrees C. The AI flags someone with a temperature greater than 37.3 degrees. The system is now in operation at Qinghe Railway Station in Beijing.
Another Chinese tech giant, Alibaba has developed an AI device capable of detecting coronavirus in chest CT scans. The AI has a 96 per cent accuracy, Wuhan Universityaccording to the researchers who created the program. The AI has been trained on data from 5,000 cases of coronavirus and can conduct the test in 20 seconds, as opposed to the 15 minutes of testing taken by a human expert. It can say the difference between coronavirus and common viral pneumonia, too. The algorithm will provide a boost to the medical centers already under tremendous pressure to test patients for COVID-19 infection. The program is currently being implemented at 100 Chinese hospitals.
A separate AI produced by researchers from Wuhan University's Renmin Hospital, Wuhan EndoAngel Medical Technology Firm, and the China University of Geosciences allegedly shows 95 percent accuracy on COVID-19 detection in chest CT scans. The program is a deep learning algorithm trained on 45,000 CT scans that are anonymized. The efficiency of the AI is comparable to that of expert radiologists according to a preprint paper published on medRxiv.
Robots at the frontlines of the fight against COVID-19
One of the key methods of avoiding the spread of the novel coronavirus is to decrease communication between infected patients and individuals who have not contracted. To this end, many businesses and organizations have engaged in attempts to automate some of the procedures that historically allowed patients to communicate with health professionals and medical personnel.
Chinese companies use drones and robotics to distribute contactless, and spray disinfectants in public areas to reduce the possibility of cross-infection. Many robots screen people for fever and other signs of COVID-19, and include free hand sanitizer foam and gel. Inside hospitals, robots are delivering food and medicine to patients and disinfecting their rooms to obviate the need for the presence of nurses. Other robots are busy cooking rice without human supervision, reducing the number of staff required to run the facility.
AI is driving drug discovery
The war on the novel coronavirus doesn't end until we create a vaccine that can immunize everybody against the virus. But creating new medicines and drugs is a very lengthy and expensive operation. It can cost over $1 billion, and take up to 12 years. That's the kind of timeline we don't have as the virus keeps spreading at an alarming pace.
Understanding protein structures can provide important clues to the coronavirus vaccine formula. DeepMind is one of several organizations who are engaged in the race to unlock the coronavirus vaccine. It has leveraged the result of decades of machine learning progress as well as research on protein folding.