Photo Source: Pixinio
The world faces a new deadly disease—a coronavirus named “2019-nCoV”, and machine learning is playing an essential role in helping public health agencies across the globe to battle it. According to the US Centers for Disease Control and Prevention (CDC), the new coronavirus presents as a respiratory illness with symptoms that include fever, cough, and shortness of breath. (cdc.gov/coronavirus) More extreme symptoms include kidney failure, diarrhea, and difficulty breathing.
The coronavirus 2019-nCoV constitutes a member of a large family of viruses, Coronaviridae, that effects a number of mammals and birds, including humans, dogs, cats, bats, and chickens. The name "coronavirus" comes from the fact that the virus, when viewed with an electron microscope, has little projections that look like the tines on a crown. Some types of coronavirus cause mild infections such as the common cold, while others such as SARS, MERS, and 2019-nCov produce intense symptoms and can even result in death. 2019-nCov appears to have emerged from a live animal, or wet, market in Wuhan, China, in late December of last year. It appears, like SARS, that the 2019-nCoV originated in bats and was transmitted to humans from the bats sold at the wet market. China bears the overwhelming burden of the coronavirus outbreak with over 17,000 confirmed cases and 360 deaths so far. (bloombergnews.com)
With no known cure or vaccine available, quarantine remains the primary weapon that doctors and health officials have to stop the spread of the coronavirus. In an unprecedented move, China has almost wholly restricted the travel of over thirty-five million people in and around Wuhan, but because of the far reach of air travel and the long, fourteen day incubation period, the virus has spread to other cities around the world, with new coronavirus cases appearing in many other countries including the United States, Great Britain, Thailand, and the Philippines.
Predicting disease outbreaks and how a disease will spread poses a massive challenge to health authorities. Fortunately, the advent of machine learning and artificial intelligence (AI) provides a new tool that helps make better and earlier predictions for disease breakouts and insights into disease proliferation. Machine learning allows a computer to make sense of billions of data points, more than a person could monitor, and find patterns of activity that suggest a disease has broken out. For example, a company called BlueDot (bluedot.global) has developed an automated system that uses AI to look for patterns of emergent diseases around the clock. BlueDot uses over 100 different kinds of data such as flight records to forecast possible infections moving around the globe, real-time weather data to identify the right conditions for certain disease transmitters, and blogs to identify clues of an outbreak. In fact, a report on Alternative Investments News claims that BlueDot identified the corona virus outbreak in China back in December 2019, weeks before the Chinese government announced it.
In an article in ContagionLive titled, “AI Could Present a New Paradigm in Epidemiology,” the author Jared Kaltwasser details several applications of AI in predicting disease outbreaks. One case involves a Malaysian startup called AIME Healthcare that uses AI to predict dengue fever outbreaks and helps healthcare authorities to deploy their resources best. Another example of the use of AI in combating the coronavirus outbreak came recently from a report in the South China Morning Post that Chinese tech giants such as Alibaba and Baidu pledged money and free access to their computing power, genetic sequencing capabilities, and AI molecular modeling programs to scientists researching how to defeat the coronavirus. (scmp.com) Such computing capabilities can help scientists more quickly find vulnerabilities in the virus for exploitation in vaccine development and possibly even a cure.
The opening weeks of 2020 have witnessed the beginning of a major, global health emergency with the outbreak of the deadly coronavirus 2019-nCoV in Wuhan, China. The virus that originated in bats now infects tens of thousands of people and has spread beyond China’s borders. The large human population and the speed of air travel allow diseases to spread faster than ever in human history. Fortunately, technology such as artificial intelligence stands to help health authorities combat the danger of widespread contagion. AI has shown promise in early detection of disease outbreak even before governments announce the growing epidemic. Moreover, AI can provide insights into where a disease will most likely spread giving health authorities a chance to prepare and contain an emerging disease such as the coronavirus. Additionally, AI provides tools to assist scientists with developing vaccines and even curing emergent new infectious diseases.
Dr. Smith’s career in scientific and information research spans the areas of bioinformatics, artificial intelligence, toxicology, and chemistry. He has published a number of peer-reviewed scientific papers. He has worked over the past seventeen years developing advanced analytics, machine learning, and knowledge management tools to enable research and support high level decision making. Tim completed his Ph.D. in Toxicology at Cornell University and a Bachelor of Science in chemistry from the University of Washington.
You can buy his book on Amazon in paperback here and in kindle format here.