Fascinating AI/ML fight against COVID-19 – Baijayanta Roy – Elemental

  • Lauren
  • April 21, 2020
  • Comments Off on Fascinating AI/ML fight against COVID-19 – Baijayanta Roy – Elemental

How Artificial Intelligence & Machine Learning helping fight against Corona VirusEver since corona has hit the earth with its deadly menace, the use of AI and Machine learning helped countries to identify & contain the spread of the virus, distribute limited resources, assist in deciding the next course of action.AI technologies, in areas including natural language processing, speech recognition, computer vision, data analytics, machine learning, and deep learning, are now being deployed as powerful weapons against COVID-19. This article is a collection of stories narrating how successful application of technology, particularly Artificial Intelligence, Machine Learning and Data Science taking the battle head-on against deadly coronavirus to save our habitat.Image Courtesy: PixabayAfter severe acute respiratory syndrome broke out in late 2002, scientists had to wait months before they knew what the viral genome looked like. For COVID-19, Chinese scientists sequenced the genome using AI, published it, and shared it with researchers around the world in early January, weeks after the first cases appeared in Wuhan.This coronavirus, like Sars and Mers, is a single-strand RNA virus, which means it is susceptible to mutation and harder to test for. However, Alibaba’s research institute Damo Academy was able to crack this nut by developing an AI algorithm that helps get the job done in 30 minutes.DeepMind, the AI arm of Google’s parent company Alphabet, is using data on genomes to predict organisms’ protein structure, potentially shedding light on which drugs could work against COVID-19. DeepMind has released a deep-learning library called AlphaFold, which uses neural networks to predict how the proteins that make up an organism curve or crinkle, based on their genome. DeepMind hasn’t tested out AlphaFold’s predictions outside of a computer, but it’s putting the results out there in case researchers can use them to develop treatments for COVID-19.Image Courtesy: PixabayThe corona outbreak itself is a great example where researchers applied AI to study flight traveler data to predict where the novel coronavirus could pop up next. A National Geographic report demonstrates how monitoring the internet or social media can help detect the early stages of a potential outbreak.Taiwan, even though having proximity to China, used technology and a robust pandemic plan created after the 2003 SARS outbreak to minimize the COVID-19 impact on its land. Part of their strategy integrated the national health insurance database with data from its immigration and customs database. By centralizing the data in this way, when faced with coronavirus, they were able to get real-time alerts regarding who might be infected based on symptoms and travel history. In addition to this, they had QR code scanning and online reporting of travel and health symptoms that helped them classify travelers’ infection risks and a toll-free hotline for citizens to report suspicious symptoms. Officials took immediate action from the minute WHO broadcast information about pneumonia of unknown causes in China on 31 December 2019. This was the first reported case of coronavirus, and Taiwan’s quick response and use of technology are the likely reasons they have a lower rate of infection than others despite their proximity to China.Image CourtesyThermal cameras have been used for some time now for detecting people with fever. The drawback to the technology is the need for a human operator. Now, however, cameras possessing AI-based multisensory technology have been deployed in airports, hospitals, nursing homes, etc. The technology automatically detects individuals with fever and tracks their movements, recognize their faces, and even can detect whether the person is wearing a face mask.In South Korea, Seoul-based molecular biotech company Seegene used AI to speed up the development of testing kits, enabling it to submit its solution to the Korea Centers for Disease Control and Prevention (KCDC) three weeks after scientists began working on it. The company’s founder and chief executive, Chun Jong-Yoon, told that had AI not been used, the process would have taken two to three months. Similarly, in Singapore, local Medtech firm Mixes, for example, has been mass-producing diagnostic test kits that were developed in a matter of just three weeks by the Agency for Science, Technology, and Research (A*Star) and Tan Tock Seng Hospital (TTSH).Besides lab tests, CAT scans of lungs are also an effective way to detect signs of coronavirus infection. During an epidemic, radiologists might be overwhelmed by the thousands of scans they have to inspect every day. Singapore-based AI start-up 6Estates, for example, has come up with an AI-powered assistive CT-scan diagnosis platform. Similarly, in China, Damo Academy trained an AI system using data from thousands of confirmed cases. The resulting diagnosis system was able to detect coronavirus cases with an accuracy of up to 96 percent. Infravision, a Beijing start-up, created a similar system that learned from thousands of cases, including early cases from Tongji Hospital in Wuhan, the center of the epidemic. UC San Diego Health developed and applied an artificial intelligence algorithm to more than 2,000 lung X-ray images, helping radiologists more quickly identify signs of early pneumonia in COVID-19 patients. China’s Zhongnan Hospital, for example, already uses AI to interpret CT scans and identify COVID-19 symptoms when human radiologists are unavailable.Mayo Clinic teamed up with the state’s health department to create an artificial intelligence-powered tool that can identify zones of greater COVID-19 transmission in southern Minnesota.Israeli start-up harnessing artificial intelligence, Diagnostics.ai is currently providing laboratories in the US and UK with its advanced diagnostic tool, which employs artificial intelligence for faster and more accurate test results. Diagnostics.ai’s technology streamlines the process of detecting, diagnosing, and tracking infectious diseases by automating the DNA analysis step.One Israeli start-up Vocalis Health, which collects voice samples of coronavirus patients and healthy individuals, so that it’s AI technology can help triage, screen, and monitor patients remotely. Through vocal biomarkers, Vocalis can correlate the voice with the symptoms of COVID-19 and alert patients and healthcare systems by a simple smartphone message. Vocalis Health, an Israeli start-up company, is working with hospitals and academic institutions to sample voices of confirmed Coronavirus patients through a mobile application; the algorithm would be used for remote diagnosis and monitoringhttps://coronavirus.jhu.edu/map.htmlIn this age of information-hungry generation, visual display and reporting is an extremely challenging task to collect, clean data from 180+ countries, and present that in a meaningful way. Johns Hopkins has done a phenomenal job of providing almost real-time updates.Another tool that has been helpful for private citizens, government policy-makers and healthcare professionals to see the progression of contagion and to inform models of how invasive this virus will be are dashboards from entities such as the World Health Organization that provide real-time stats. Few prominent dashboards for COVIT-19 :These dashboards pull in data from around the world to show confirmed cases and deaths from coronavirus and locations. These analytics takes all available data, including the number of confirmed cases, deaths, tracing contacts of infected people, population densities, maps, traveler flow, and more, and then processes it through machine learning to create models of the disease. These models represent the best predictions regarding peak infection rates and outcomes.Image Courtesy: PixabayGovernments and health specialists across the world are collectively striving to find solutions to the COVID-19 pandemic. One technology trend that is gaining mass adoption at an incredibly fast pace is contact tracing systems.Reference: BBCThe Chinese government rolled out a “Close Contact Detector” App that alerted users if they were in contact with someone who had the virus. Similar App was used by many countries like (Singapore: TraceTogether, India: Aarogya Setu). As countries search for ways to exit lockdown and avoid or manage a second wave of COVID-19 cases, many have turned to the promise held by contact-tracing apps. In a rare display of collaboration, Apple and Google recently joined forces to help the technology work effectively. Though there is a privacy concern, this tracing technology, together with AI-driven prediction from data collected from these Apps (proximity, duration of contact, etc.), would give a hope to exit policy from lockdown.AI has helped on the front line, too. Chatbots reduce the pressure on hospital and government personnel by automatically answering queries from members of the public, and even advising individuals about whether they need to undergo screening in hospital or stay at home for a 14-day quarantine.In the fight against the coronavirus, social distancing has proven to be a very effective measure to slow down the spread of the disease. To ensure social distancing protocol in the workplace, government and organizations using AI-enabled social distancing detection tool that can detect if people are keeping a safe distance from each other by analyzing real-time video streams from the camera (Refer to the above demo video of one such Computer Vision tool from Landing AI ).Many countries have used security cameras to discover people who weren’t compliant with quarantine orders. If a person was supposed to be in quarantine, but cameras tracked them outside their homes, authorities would be notified. Mobile phone and drone data were also used to track movements. In the United States, the government is in conversation with tech giants such as Facebook, Google, and others to determine what’s possible — and ethical — in terms of using location data from Americans’ smartphones to track movements and understand patterns.Image Courtesy: PixabayAlthough the race to find a vaccine is well underway, doctors are currently pinning their hopes on drugs already being used to treat other diseases that they are repurposing for coronavirus patients.An Israeli company with an AI solution for COVID-19 is CLEW Medical. Its AI-powered, machine-learning models enable an intensive care unit (ICU) workers to manage disease severity and workload proactively. The company has developed a ‘predictive analytics engine’ that detects respiratory deterioration in real-time and delivers preemptive warnings throughout the patient’s ICU stay. The CLEW Medical solution is already implemented in coronavirus units in Israeli hospitals and is currently being tested by several hospitals in many countries, including the US.ReferencePrivate sector companies, such as UK-based BenevolentAI, are also using AI to crunch vast amounts of public data to find existing drugs that could be used to treat coronavirus patients before a vaccine becomes available.And in the US, San Francisco-based start-ups, including Vir Biotechnology and Atomwise are harnessing algorithms to find a molecule that could serve as the basis of treatment before the end of the year. The aim is to design ‘broad-spectrum’ antiviral drugs that are futureproofed to protect against a future coronavirus outbreak.Scientists from South Korea and the US using deep learning to investigate the potential for commercially available antiviral drugs have suggested atazanavir, used to treat Aids, could be a good candidate.Scientists at the University of Oxford have been working on a vaccine, which they plan to test on the first UK volunteers. US and China have approved early-stage human tests for experimental vaccines to combat the new coronavirus. As per a report, there are now 70 vaccines in development. In all these fast track vaccine development, AI and ML play a major role in simulation and making the right decision.Image Courtesy: PixabayThis is an extraordinary time, and we have seen traditional rival companies coming together to fight against COVID-19.A consortium of tech leaders — including Seattle’s Allen Institute for Artificial Intelligence, Microsoft, and Facebook CEO Mark Zuckerberg’s charity unveiled an AI-enabled database that’s meant to give researchers quicker, surer access to resources relating to coronavirus and how to stop it.In the US, The White House Office of Science and Technology Policy called for the creation of what became known as the COVID-19 Open Research Dataset (CORD-19). The dataset is a machine-readable coronavirus literature collection, comprising over 44,000 scholarly articles for use by the global research community.In a similar effort to harness tech companies’ expertise, it is understood executives from Amazon, Google, Microsoft, Apple, and Facebook met UK officials at Downing Street on 11 March to discuss their role in the coronavirus crisis, including in modeling and tracking data using AI techniques.Google-owned machine-learning community Kaggle is setting several COVID-19-related challenges to its members, including forecasting the number of cases and fatalities by the city as a way of identifying exactly why some places are hit worse than others.Image Courtesy: PixabayRecently, we’ve all seen poignant images of healthcare professionals across the globe working tirelessly to treat COVID-19 patients, often putting their own lives at risk. AI could play a crucial role in lightening their load while ensuring that the quality of care does not suffer. For instance, the Tampa General Hospital in Florida is using AI to detect fever in visitors with a simple facial scan. AI is also helping doctors at the Sheba Medical Center.Johannes Eichstaedt, assistant professor in Stanford University’s department of psychology, has been examining Twitter posts to estimate how COVID-19, and the changes that it’s brought to the way we live our lives, is affecting our mental health.This is only the tip of the iceberg. It’s even likely that AI will play a significant role in ending the COVID-19 pandemic. AI & ML is vital in the fight against coronavirus and future pandemics.In addition to being able to support modeling efforts and predicting the flow of a pandemic, Artificial Intelligence, machine learning, and other technology can quickly and effectively analyze data to help humans on the frontlines figure out the best preparation and response to future pandemics.I look forward to your comment. Do share if you come across any new AI/ML development in this fight against COVID-19. Thanks for reading. You can connect me @LinkedIn.Reference:https://www.scmp.com/tech/big-tech/article/3048317/alibaba-and-baidu-offer-ai-gene-sequencing-tools-help-fight-chinahttps://www.martechadvisor.com/news/cloud-integration/alibaba-cloud-leverages-ai-to-tackle-covid19/https://deepmind.com/research/open-source/computational-predictions-of-protein-structures-associated-with-COVID-19https://economictimes.indiatimes.com/magazines/panache/the-world-wasnt-prepared-for-covid-19-in-future-ai-will-curb-the-next-pandemic/articleshow/74776209.cms?from=mdrhttps://www.businessinsider.sg/coronavirus-taiwan-case-study-rapid-response-containment-2020-3?r=US&IR=Thttps://www.prnewswire.com/news-releases/platinum-cctv-releases-new-thermal-body-temperature-camera-that-identifies-individual-body-temperatures-in-addition-to-providing-visual-security–an-innovative-tool-to-rapidly-pre-screen-individuals-for-fevers-when-entering-a-fa-301029866.htmlhttps://www.forbes.com/sites/forbesasia/2020/04/05/how-one-firms-covid-19-tests-help-control-the-virus-in-south-korea/#5fab82625bffhttps://www.businesstimes.com.sg/sme/local-sme-to-mass-produce-sars-cov-2-diagnostic-test-kitshttps://www.wired.com/story/chinese-hospitals-deploy-ai-help-diagnose-covid-19/https://www.sgsme.sg/news/covid-19-putting-singapore-global-deeptech-radarhttps://www.beckershospitalreview.com/artificial-intelligence/mayo-clinic-uses-ai-to-map-covid-19-hot-zones.htmlhttps://www.forbes.com/sites/startupnationcentral/2020/04/13/israeli-startups-artificial-intelligence-covid19-coronavirus/#52af57b04567https://www.straitstimes.com/asia/east-asia/coronavirus-china-introduces-close-contact-detection-apphttps://www.globalgovernmentforum.com/governments-turn-to-ai-in-fight-against-coronavirus/https://www.telegraph.co.uk/news/2020/04/17/human-trials-coronavirus-vaccine-set-begin-uk-next-week/https://finance.yahoo.com/news/ai2-microsoft-team-other-tech-191521313.htmlhttps://www.bbc.com/news/technology-51851292https://news.stanford.edu/2020/04/14/covid-19-research-roundup/
Source: https://medium.com/@baijayanta.roy/fascinating-ai-ml-fight-against-covid-19-67d91afcbfee