AI solves future pandemics

Artificial intelligence (AI) has been applied widely in our daily lives in a variety of ways with numerous success stories. AI has also contributed to dealing with the coronavirus disease (COVID-19) pandemic, which has been happening around the globe. This paper presents a survey of AI methods being used in various applications in the fight against the COVID-19 outbreak and outlines the crucial role of AI research in this unprecedented battle. We touch on areas where AI plays as an essential component, from medical image processing, data analytics, text mining and natural language processing, the Internet of Things, to computational biology and medicine. A summary of COVID-19 related data sources that are available for research purposes is also presented. Research directions on exploring the potential of AI and enhancing its capability and power in the pandemic battle are thoroughly discussed. We identify 13 groups of problems related to the COVID-19 pandemic and highlight promising AI methods and tools that can be used to address these problems. It is envisaged that this study will provide AI researchers and the wider community with an overview of the current status of AI applications, and motivate researchers to harness AI’s potential in the fight against COVID-19. Technology. To combat the pandemic, the power of AI can be fully exploited to support this effort. AI can be utilized for the preparedness and response activities against the unprecedented national and global crisis. For example, AI can be applied to create more effective robots and autonomous machines for disinfection, working in hospitals, delivering food (and medicine) to patients. AI-based NLP tools can be used to create systems that help understand the public responses to intervention strategies, e.g., lockdown and physical distancing, to detect issues by measuring mental health and social anxiety, and to aid governments in making better public policy. NLP technologies can be employed to develop chatbot systems able to remotely communicate and provide consultations to people and patients about the coronavirus. AI can also be used to eradicate fake news on social media platforms to ensure clear, responsible, and reliable information about the pandemic. The COVID-19 pandemic has considerably impacted the lives of people around the globe, and the number of deaths related to the disease keeps increasing worldwide. While AI technologies have penetrated into our daily lives with many successes, they have also contributed to helping humans in the fight against COVID19. This paper has presented a survey of AI applications so far appearing in the literature that are relevant to the COVID-19 crisis responses and control strategies. These applications range from medical diagnosis based on chest radiology images, virus transmission modelling and forecasting based on number of cases time series and IoT data, text mining and NLP to capture the public awareness of virus prevention measures, to biological data analysis for drug discovery. Although various studies have been published, we observe that there are still limited AI applications and the contributions of AI in this battle remain relatively limited. This is partly due to the scarce availability of data about COVID-19 while AI methods normally require large amounts of data for computational models to effectively learn and acquire knowledge. However, we expect that the number of AI studies related to COVID-19 will increase significantly in the months to come as more COVID-19 data, such as medical images and biological sequences, become available. It is promising to observe an increasing number of AI applications being used against the COVID19 pandemic. However, AI methods are not silver bullets. Some limitations and challenges include the lack of (or poor quality of) training and validation data, explainability, and the resulting trust deficit. Significant efforts are needed for an AI system to be effective and useful. These may include appropriate data processing pipelines, model selection, efficient algorithm development, remodelling and retraining, continuous performance monitoring and validation to facilitate continuous deployment and so on. There are AI ethics principles and guidelines that each phase of the AI system life-cycle, i.e., design, development, implementation and ongoing maintenance, may need to adhere to, especially when most AI applications against COVID-19 involve (or affect) human beings. The more AI applications that are proposed, the more these applications need to ensure fairness, safety, explainability, accountability, privacy protection, data security, and also ensure alignment with human values in order to have positive impacts on societal and environmental well-being.