Prediction of Epidemic Disease Dynamics using Machine Learning

Prediction of Epidemic Disease Dynamics using Machine Learning

What is AI? Why is everyone talking about it? Why is everyone trying to incorporate it in their respective areas or are interested in learning about AI? What’s this fuss all about? The above are a few questions that crop up in people’s mind who hear the hype surrounding about AI. The classic textbook definition of AI – “a system’s ability to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation”, as given by Kaplan and Haenlein succinctly sums up what AI is, but does moderate justification to its prowess. AI has evolved in ways that far exceed its original conception. Artificial Intelligence (AI) is poised to disrupt our world. With incredible advances made in data collection, processing and computation power, intelligent systems can now be deployed to take over a variety of tasks, enable connectivity and enhance productivity. As AI’s capabilities have dramatically expanded, so have its utility in a growing number of fields.

Looking back into the history, who would have imagined the all-pervasive influence of AI in our everyday lives. From Apple to Alexa, self-driving cars to Sophia Robot, AlphaGo to IBM Watson and many more such innovations are taking place every now and then. Currently, AI is one of the most trending careers on the planet. And in the future, we don’t see any prospect of it slowing down. AI presents opportunities to complement and supplement human intelligence and enrich the way people live and work.

From my personal perspective – I have been working on AI for the past one year, I could say that it has tremendous growth potential and it could be deployed successfully to solve variety of problems plaguing India. With many stakeholders in sectors like Healthcare, logistics, Finance, blockchain, etc., India is one of the bright spots for deployment of AI, and hence, harness its potential.

Let me share my experience of working on AI – I’m one of the Intel Ambassadors for AI. As part of the Intel® AI Developer Program, get access to newly optimized frameworks and technologies, hands-on training, and technical resources for graduate and PhD students from top universities worldwide to further innovation in AI.

Last year, I won the Intel Python Hack Fury Hackathon. (Team name: abhijit210_2c41) The model, or POC, that I presented was “Prediction of Epidemic Disease Dynamics using Machine Learning”. I am the sole developer, leader and designer of the project. My team included my friend Shubham who provided valuable insights regarding pertinent to biological aspects involved in the epidemic spread. The prize money we won was worth Rs 2 lakhs. The broad objective behind the project was – Given an area where an epidemic outbreak has occurred, our ML model should be able to identify next outbreak prone areas and identify features which contribute significantly in the spread of the outbreak. There were over 4000+ teams taking part from all over India to solve real-world problems through AI, ML, DL & their prototypes – that are built with Intel’s latest technologies & showcase how they saw efficiency and performance improvement on AWS Cloud using Intel Distribution of Python and Intel Architectures for Machine Learning & Deep Learning. Kicked off in June 2018 and the first of its kind in India, the online Python Hack fury (Hackathon) was organized by Intel, IISER Pune and Amazon Web services with an aim to motivate and harness talent in the applicability of Python Programming to solve real-world problems in the areas of Science and Technology. Grand finale of the Hackathon was held on 7th September, 2018 at IISER Pune. Of the 4043 registered teams, eight teams made it to the final round after gruelling evaluations. The finale witnessed the finalists presenting their work using Python tools to the jury and audience in the areas of Health, Agriculture, Quantum predictions, Inventory management, Finance etc. using Artificial Intelligence, Machine Learning, and Deep Learning frameworks.

Abhijit Gupta at Intel Python Hackfury

Reliable predictions of infectious disease dynamics can be valuable to public health organizations that plan interventions to decrease or prevent disease transmission. With the big data growth in healthcare and biomedical sector, accurate analysis of such data could help in early disease detection and better patient care. With the availability of huge computational power at hand, it is now very much viable to exploit the ‘big data’ for predicting and managing an epidemic outbreak. Our idea is to analyse and determine the spread of epidemic diseases in villages and sub-urban areas, where healthcare might not be readily available. We want to build a machine learning model that could predict the epidemic disease dynamics and tell us where the next outbreak of epidemic would most likely be. Our approach takes into consideration the geography, climate and population distribution of an affected area, as these are relevant features and subtly contribute to epidemic disease dynamics. Our model would be beneficial for the healthcare authorities by assisting them to take the appropriate action in terms of assuring that enough resources are available to suffice the need and, if possible, curbing the occurrence of such epidemic disease. We achieved a prediction accuracy of 95% for detecting the spread of epidemic – Zika virus and were able to identify key factors responsible for its spread.

Abhijit Gupta

Abhijit Gupta is a PhD student at IISER Pune in the field of Machine Learning. He is the Intel Student Ambassador and the winner of Intel Python HackFury.

2
0
Share

We love hearing from you! You can also reply anonymously skipping the details!

%d bloggers like this: