COVID19 Predictive Model for Decision Making
Developed By IIT Kharagpur
A system that helps in predicting the spread of COVID-19 has been developed by the Indian Institute of Technology (IIT), Kharagpur, in a recent study. The researchers say that this prediction system could significantly help decision-making in the economy, academics, industry, and health-care.
This study was led by Professor from the Department of Computer Science and Engineering at IIT Kharagpur, Abhijit Das, and he said, “Without accessing sensitive information pertaining to medical records or contact-tracing data for a large fraction of the population, the prediction system uses only the daily infection counts available in the public domain. The prediction can be used well for future planning as the curves show surprisingly good fitting with the past data.”
Based on a logistic model, the available daily counts of infection cases can be fitted in this system. The data used for the predictions pertain particularly to the eight most affected states Maharashtra, Tami Nadu, Delhi, Madhya Pradesh, West Bengal, Rajasthan, Uttar Pradesh, and Gujarat, and to the entire country.
IIT Kharagpur Director, Prof. Virendra Kumar Tewari said, “People have been living in uncertainty and for them to understand and plan their wayforward, a study like this based on a clear statistical model will be helpful. Policy matters related to the Institute and the campus under the current circumstances and academic semester planning can be done with the help of the model.”
However, with time, the predictions for the future could change rapidly. For this, there are many potential factors like the evolution of the coronavirus, change in diagnostic facilities, large-scale migration of laborers, different mobility patterns of Indian people in different phases of lockdown, and so on. These factors are well beyond the control of any currently known prediction model or the logistic model.
The trend clearly reveals that the disease is going to stay in the country for many more months, although the implementation fails to generate stable and reliable predictions at the moment.
Prof. Das remarked, “India is yet to achieve a steady pattern in the spread of the disease, according to our study. Before the end of September 2020, it is unlikely to get rid of COVID-19. The reality has to be accepted and to address all the issues associated with the outbreak of the pandemic, appropriate plans must be chalked out.”
COVID19 Predictive Model for Decision making