As per the World Economic Forum, the UN’s trade and development agency says the slowdown in the global economy caused by the corona virus outbreak is likely to cost at least $1 trillion (~INR 75 lakh crore). This impact cues the use of econometric Machine Learning models providing empirical analysis to economic relationships and allowing data-driven decisions. From Economics to ‘Fighting the current pandemic’, Machine learning (ML) is an important tool.
For the later, ML is helping in identifying, diagnosing & predicting who most is at risk, specifically, of developing a severe case based on important risk factors. It assists in assessing treatment outcomes by figuring out how to attack the virus, developing drugs faster by building knowledge graphs and predicting interactions between drugs and viral proteins (drug-target-interactions DTI). It also maps where the disease came from and predicts the spread of the disease using social networks and thereby predicts next pandemic.
When it comes to using ML to help diagnose COVID-19, a very useful application is using ML-powered chatbots to screen patients based on self-reported symptoms. Like many countries, India has developed “self-triage” system, where patients complete a questionnaire about their symptoms and medical history before being advised whether to stay home, call a doctor, or visit a hospital.
A person who is starting to develop symptoms might live in a remote place with no nearby hospitals capable of performing the test. But this same person might still be able to access social networks and immediately leave hints about his health and the spread of the disease – hints that only a machine learning model can learn to process at scale.
By interpreting the content of public interactions on social media, a ML model assesses the likelihood of COVID-19 contamination. The model might not be able to classify people on an individual level, but it can use all of this data to estimate the spread of the pandemic in real time and to forecast the spread in the upcoming weeks.
Natural Language Processing (NLP) on symptoms followed by Machine Language clustering helps in segmenting the data into ‘Healthcare Service-Priority’ / ‘Test-Priority’ / ‘Self-Quarantined’ Categories.
Is this a permanent solution?
No way. The above approach is only for a populous country like INDIA and others to stop COVID-19 spread with limited Healthcare infrastructure. This helps in the containment of the virus.
The permanent solution is Vaccines, which may require months and even years to be ready. A vaccine for COVID-19 may also be found using ML/AI techniques on a combination of existing virus vaccines.
If we take this opportunity to collect data, pool our knowledge, and combine our skills, we can save many lives – both now and in the future.