Serious infectious diseases have become more frequent in the last decade. Even before the COVID-19 epidemic, infectious diseases such as tuberculosis, malaria, and influenza killed more than 17 million people a year. COVID-19 claims at least six million people (up to an estimated 18 million) and is expected to cost USD 12.5 trillion globally by 2024.
Covid-19 could have become a local epidemic rather than an epidemic if it had been detected and dealt with as early as possible.
Using Artificial intelligence (AI) can quickly identify serious epidemics in their early days to mine large open-source data. AI can scan global news reports and social media for signs of a new disease or an unknown disease in the community.
The system was developed in 2016 by a team of medical researchers and epidemiologists from the University of New South Wales. EPIWATCH utilizes machine learning and natural language processing – the ability of a computer program to understand the human language spoken and written – early warning signs to cause an epidemic.
It then uses the datasets it has created to map out upcoming epidemics and provides risk-analysis tools to help health officials respond effectively.
The Canadian system, called Blue Dot, has similar capabilities but is largely to be paid to private customers. We have a large amount of open-source data that can provide early warning of an epidemic, but this data must be filtered to eliminate irrelevant information and improve the accuracy of forecasts.
AI-powered data filtering can detect signs of a serious outbreak much earlier than traditional public health monitoring, relying on reporting by doctors, hospitals or laboratories.
The signal for the West African Ebola epidemic in 2014 would have been taken using Twitter data three months before the WHO declared the epidemic, although smartphone use in West Africa is lower than the global average. We can automatically generate red flags using outbreak mapping and statistical methods. While the field is rapidly evolving and more systems are coming online, public health has been slow to adopt digital technologies.
However, with the Center for Forecasting and Outbreak Analytics in the United States, the announcement of an epidemic radar in the United Kingdom, and the establishment of the WHO hub, the focus has shifted to post-epidemic COVID-19 epidemic warning systems. For epidemics and epidemiological intelligence, part World Health Organization (WHO) and co-funded by the German government, all in 2021.
Some publicly available web-based applications collect open source information based on events and happenings. HealthMap collects data on all health conditions, contagious and non-contagious, and received a warning for “mystery hemorrhagic fever” nine days before the WHO declared the 2014 Ebola epidemic.
The Global Public Health Intelligence Network, developed by Canadian Public Health and the WHO, provides intelligence gathered from open-source data. If the network had not been defended in 2019, it could have taken out COVID-19 before it became a global epidemic.
ProMED-Mail, a central site developed by a non-profit organization International Society for Infectious DiseasesReceives warnings from health professionals about unusual, serious epidemics and diseases.
The site was the first to report Middle Eastern Respiratory Syndrome Coronavirus and Ebola in West Africa. ProMED-Mail has also collaborated with three international health organizations to create a closed global community of examined public health experts, EpiCore, which collects information on epidemics.
Systems that do not rely on expert input and moderation can also be valuable. From 2008 to 2015, Google ran Flu Trends as an influenza-prediction tool.
Metabiotia, a biotech company, owns an epidemic tracker that provides an outbreak map. In 2017, WHO launched a system called Epidemic Intelligence from Open Sources, which receives feeds from open source and other systems such as ProMED-Mail.
This US Department of Defense Launched global biosurveillance portal in 2015. A portal is an internal tool that collects a range of data but is not publicly available. In other approaches, citizens report directly to public health officials using a digital platform.
To prevent an epidemic, time is of the essence. Even a few days of warning can make a significant difference in the long-term outcome. The epidemic is characterized by exponential growth: today 20 cases may be 80 cases in three days, which may be 320 cases in six days.
This rapid growth means that health systems work one day and only break down after days or weeks. When large numbers of people are away from work, complex infrastructure is disrupted and the supply chain fails.
Governments plan epidemics and severe epidemics because of their immediate social and economic implications. Even a relatively small SARS outbreak in 2003 cost the global economy 54 54 billion. There is also a risk of unnatural epidemics due to bioterrorism. The value of an effective early-detection system for serious infectious diseases cannot be overstated. (360 data)
