VESIT studies how tuberculosis spreads using Azure and AI

Source: Microsoft. Dr Giri.

A professor and her students are using artificial intelligence (AI) to predict how airborne diseases can propagate based on climate conditions, air quality, and population density.

“If we can employ AI algorithms to predict the spread of disease and understand how environmental changes, including climatic conditions and external factors like pollution impact the ecology and epidemiology of disease, we can initiate precision public health at a granular level,” explains Dr Nupur Giri, Professor, and Head of Department of Computer Engineering at Vivekanand Education Society’s Institute of Technology (VESIT), Mumbai, India.

In 2018, the team began with looking for correlations to predict how tuberculosis (TB) would spread. The disease affected an estimated 2.74 million people in India in 2017. India is one of the countries with the most multi-drug resistant TB (MDR-TB) patients in the world.

To study the impact of environmental conditions, such as climatic factors and pollution on the epidemiology of TB, the team collated data from 725 districts over a 17-year timeframe from various sources: climate datasets from Skymet Weather, pollution and air quality datasets from the Open Government Data Platform India, the tuberculosis dataset from the Central Tuberculosis Division of India and population data from the national census.

The team spent a few months on standardising and normalising the data to allow apples-to-apples comparisons across datasets. Dr Giri subsequently won a Microsoft AI for Earth grant, which allowed the team to use Microsoft’s Azure platform and associated tools.

“The data science virtual machine was a huge benefit, as it comes preloaded with all the tools required, and data crunching became easier. The Machine Learning Studio allowed us to minimise the time required to develop algorithms and write codes, as it has a drag-and-drop authoring environment,” she said.

“The initial results are good, but we are currently testing multiple machine learning and neural network models to improve the accuracy of their prediction for every district in India.”

The team plans to provide a data visualisation dashboard of the results to help those working on eradicating TB make more informed decisions. Predicting the hotspots for TB is just the beginning. The team is hopeful that once it’s cracked the model, it will be able to extend it to other diseases as well.