Emerging infectious diseases pose a growing threat to human populations. Accurate disease forecasting models markedly improve epidemic prevention and control capabilities. The better we can track the disease or virus, the better we can fight it.
Existing frameworks for epidemic preparedness focus on disease surveillance using either expert knowledge or statistical modeling of disease activity and thresholds to identify times and areas of risk. Traditional epidemiology tracks where and when people contact a disease to identify the source of the outbreak and which populations are most at risk. Today is the era of Artificial Intelligence. AI systems model how diseases spread in populations, which makes it possible to predict where outbreaks will occur and forecast how far and fast diseases will spread. It can sift through enormous amounts of data that would either be too much for humans. It quickly identifies possible correlations and causations that are accurate; as long as the data it is being fed is reliable.

Artificial intelligence firms like Blue Dot have been in the news in recent weeks for warning about the new mysterious pneumonia strain in the city of Wuhan, ahead of the official alerts from the Centers for Disease Control and Prevention (CDCP) and the World Health Organisation (WHO). The initial prediction by Blue Dot correctly pinpointed a handful of cities in the virus’s path. Blue Dot’s AI algorithm can process more data and can sift through 100,000 articles and online posts daily in 65 languages, reports from plant and animal disease tracking networks and airline ticketing data. The result is an algorithm that’s better at simulating disease spread than algorithms that rely on public health data only.
Besides predicting the course of an epidemic, many hope that in future AI will help identify people who have been infected. Machine-learning models for examining medical images can catch early signs of disease that human doctors miss, from eye disease to heart conditions to cancer. But these models typically require a lot of data to learn from. A handful of research has suggested that machine learning can diagnose Covid-19 from CT scans of lung tissue if trained to spot tell-tale signs of the disease in the images.
It’s also believed that AI systems will help develop treatments for the disease by using generative design algorithms, which produce a vast number of potential results and then sift through them to highlight those that are worth looking at more closely. This technique can be used to quickly search through millions of biological or molecular structures.
AIs could also be used to predict the evolution of the coronavirus too. This will allow virologists to be a few steps ahead of the viruses and create vaccines in case any of these doomsday mutations occur. AI never gets tired, and it doesn’t need to take time off. It has become a regular facet of our everyday lives, helping us get through each day in an easier, faster and smarter way.

Dr Immad A Shah is working as a Lecturer at the Division of Agricultural Statistics, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir. Dr Showkat Maqbool is working as an Associate Professor at the Division of Agricultural Statistics, Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir.

Dr Immad A Shah & Dr Showkat Maqbool