key: cord-0778953-pxbkfdy0 authors: Dananjayan, Sathian; Raj, Gerard Marshall title: Artificial Intelligence during a pandemic: The COVID‐19 example date: 2020-05-20 journal: Int J Health Plann Manage DOI: 10.1002/hpm.2987 sha: ec63ed4269b715892bb7802a4d4d2a28569c236b doc_id: 778953 cord_uid: pxbkfdy0 nan outcomes. 1 But how effective are the AI algorithms during a disease outbreak or for that matter a pandemic? After 2000, the pandemics are testing the AI's ability to handle extreme events. The two major factors affecting AI algorithms include the availability of historical and real-time data and high computational power. The different roles played by AI during pandemics are early warning and alerts, prediction and detection of outbreak of diseases, real-time disease monitoring worldwide, analysis and visualisation of spreading trends, prediction of infection rate and infection trend, rapid decision-making to identify the effective treatments, study and analysis of the pathogens, and drug discovery. All these are executed at a greater speed with AI. WHO and CDC (United States) are receiving data of several diseases and situations occurring across the world. With modern computer architecture and internet, all these data can be accessed in real-time by different institutes to develop an autonomous or collaborative AI model to handle various tasks. In addition to the official data, AI can gather information from news outlets, forums, healthcare reports, travel data, social media posts, and others in multiple languages across the world by using natural language processing (NLP) techniques and flag their priority. Several terabytes of data which includes patients' case history, geographical events, and social media posts about a new pneumonia are processed at a rapid rate with high-performance computing to predict the possible outbreak of a pandemic. [1] [2] [3] Most importantly unsupervised ML can identify its own pattern from the noise (historical and real-time data) rather than the training it on a preselected dataset, thus giving a wider possibility and new behaviour. An AI model trained to predict a particular disease can be retrained on the new data of a new or different disease. Some noticeable examples of AI that are used to battle the COVID-19 pandemic and others are as follows: • AI can be used as an early outbreak warning system, BlueDot, an AI-driven algorithm not only successfully detected the outbreak of Zika virus in Florida 4 but also spotted COVID-19, 9 days before the WHO released its statement alerting people to the emergence of a novel coronavirus. 5 • Researchers from the Huazhong University of Science and Technology (HUST) and Tongji Hospital in Wuhan, Hubei have developed an AI diagnostic tool (XGBoost machine learning-based prognostic model) that can quickly analyse blood samples to predict survival rates of COVID-19 infected patients and it turns out to be 90% accurate. 6 • In Wuhan, China, an AI diagnostic tool is used to distinguish COVID-19 from other types of pneumonia within seconds by analysing patients' chest CT scan images. The authors claimed that their new model holds great potential to relieve the pressure off frontline radiologists, improve early diagnosis, isolation and treatment, and thus contribute to the control of the epidemic. 7 • COVID-Net, a deep learning model is designed to detect the COVID-19 positive cases from chest X-rays and accelerate treatment for those who need it the most. 8 • Google's DeepMind is helping scientist to study various features of the SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) and has predicted the protein structure of the virus. 9 • Several AI-based computer vision camera systems are deployed in China and across the world to scan crowds for COVID-19 symptoms and monitor people during lockdown. 10 • FluSense, a contactless syndromic surveillance platform, is used to forecast seasonal flu and other viral respiratory outbreaks, such as the COVID-19 pandemic or SARS. 11 • Interestingly, AI-powered autonomous service robots and humanoid robots "Cloud Ginger (aka XR-1)" are used in hospitals at Wuhan, China. The first is used to assist the healthcare workers to deliver the foods and medicines to the patients and the latter is used to entertain the patients during quarantine. 12 There are also few AI models that are a hit and miss due to lack of historical training data. Though AI has not completely evolved to overcome a pandemic, but the role of AI is noticeably high during COVID-19 when compared to that of previous pandemics and is rightly used as a tool complementing the human intelligence. Artificial intelligence in healthcare: past, present and future Artificial intelligence in medicine How artificial intelligence will change medicine Anticipating the international spread of Zika virus from Brazil An AI Epidemiologist Sent the First Warnings of the Coronavirus | WIRED Prediction of criticality in patients with severe COVID-19 infection using three clinical features: a machine learning-based prognostic model with clinical data in Wuhan. medRxiv preprint Deep learning-based model for detecting 2019 novel coronavirus pneumonia on highresolution computed tomography: a prospective study. medRxiv preprint COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest radiography images Computational predictions of protein structures associated with COVID-19. DeepMind website Coronavirus: China's investment in AI is paying off in a big way FluSense: a contactless syndromic surveillance platform for influenza-like illness in hospital waiting areas What America can learn from China's use of robots and telemedicine to combat the coronavirus