Role Of A.I (Artificial Intelligence) In Corona Virus Pandemic

Let’s Get started.What is Corona virus?

Corona-viruses(CoV) is infectious disease coming from a large family of viruses that causes illness ranging from common cold to more severe diseases such as mild to moderate respiratory illness. Older people, and those with underlying medical problems like cardiovascular disease, diabetes, chronic respiratory disease, and cancer are more likely to develop serious illness.

Corona-viruses are zoonotic, i.e. it can be transmitted between both animals and human beings. The COVID - 19 is the disease caused by the new coronavirus that emerged in China in December 2019.The COVID-19 virus spreads primarily through droplets of saliva or discharge from the nose when an infected person coughs or sneezes, so it’s important that you also practice respiratory etiquette (for example, by coughing into a flexed elbow). The source of corona virus is believed to be a “wet market” in Wuhan which sold both dead and live animals including fish and birds.

According to the WHO, the most common symptoms of Covid-19 are fever, tiredness and a dry cough. Some patients may also have a runny nose, sore throat, nasal congestion and aches and pains or diarrhoea. Some people report losing their sense of taste and/or smell. About 80% of people who get Covid-19 experience a mild case — about as serious as a regular cold — and recover without needing any special treatment.

India reported the first COVID -19 case on 30th January, when a student arrived in Kerala from Wuhan.

Global Impact Of Corona virus.

The main concern for novel corona virus is public health emergency .Globally killing more than 4000 people and infecting more than 100,000 people . it not end there the impact will surely also hit the Financial Market and the Global Economy too .

Now coming to the point.

Role of A.I (Artificial Intelligence) In Corona Virus Pandemic.

- Tracing the Outbreak( Infection and spread of corona). - Diagnosing Patient and health treatment . - Disinfecting Area - Finding a cure ( vaccination by analysing prior one based on the similarity measure protein structure are made - Through the Trial and Error Researcher are also creating better drug. - Post Treatment also .

Machine Learning: How it can help?

“Machine Learning: A computer is able to learn from experience without being specifically programmed.”

Againgoing with the layman’s terms Machine learning is the subset of Artificial Intelligence provides us statistical tool to explore data . In Machine learning -: - The system is able to make prediction or decision based on past data . - Needs only small amount of data . - Works well with low end computers .

Many sectors are using machine learning; healthcare cannot stand behind! Google has developed an ML algorithm to identify cancerous tumours, Stanford is using it to identify skin cancer.

Types of Machine Learning:-

1.Supervised Learning(label data /past data) 2.Unsupervised Learning(clustering) 3.Reinforcement/Semi-Supervised Learning( no raw data is given as input instead reinforcement learning algorithm have to figures out the situation on their own.)

Process it’s all depend on the data, the cleaner the data the better your machine learning.

Data Collection - Collecting medical data that the algorithm will learn from the data sources are Health Organisation, Satellite data, News and Media, Commercial Flights.

Data Preparation - Data preparationoccurs when data is collected and translated into usable information and stored in databases. It includes Data Wrangling or Data Munging, Data Cleaning, Data scaling, normalizing and standardizing.

Training - It is the process where the machine learning algorithm actually learns.

Data Evaluation - In the process of evaluation we test the model how well it perform at all the time.

Tuning - The final step if we will fine tune the model for maximizing detection performance.

Problem Statement -Predicting structure of proteins and their interactions with the chemical compound . Goal - Facilitate new antiviral drugs / vaccine or recommend current drugs.

-Forecast infection rates and spread patients prognosis . Goal - Enable hospitals / health officials to better plan and resourcing and response.

-Analysis of medical images like X-Rays or CT Scans . Goal - Enable doctors to predict the presence of anomalies faster .

-Mining social media data to drive insights and virology analytics . Goal - To better understand spread / symptoms and general Public perception . Here we look at usage -

Corona virus (COVID - 19) Chest X-Rays Data

-These are used to train a deep learning model with the help of libraries like TensorFlow and Keras.

-This method of machine learning automatically predicts patient is suffering from COVID -19 or not.

Another one

Computer vision alongside machine learning helping measure body temperature of the people in public and track their movement any abnormalities occur.

Case Study.

So this is the part of data visualization for COVID -19

The accumulated confirmation count in South Korea is increasing exponentially after 22nd of Feb. Till the date 15th of feb 2020 it was negligible. There are many reason for infection but most cases have similar reasons that they have visited to Wuhan. South Korea has raised its coronavirus alert to the “highest level” as confirmed case numbers keep rising. South Korea has seen the largest number of confirmed cases after China. More than 4,800 people have confirmed the infection of coronavirus. As the data set says the western part of the country is more affected. Daegu and Gyeongsangbukdo region of South Korea are highly infected by the coronavirus.


import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt import matplotlib.dates as mdates import as px from datetime import date, timedelta from sklearn.cluster import KMeans from fbprophet import Prophet from fbprophet.plot import plot_plotly, add_changepoints_to_plot import plotly.offline as py from statsmodels.tsa.arima_model import ARIMA from import plot_acf, plot_pacf import statsmodels.api as sm from keras.models import Sequential from keras.layers import LSTM,Dense from keras.layers import Dropout from sklearn.preprocessing import MinMaxScaler from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator

Symptoms of Coronavirus

symptoms={'symptom':['Fever', 'Dry cough', 'Fatigue', 'Sputum production', 'Shortness of breath', 'Muscle pain', 'Sore throat', 'Headache', 'Chills', 'Nausea or vomiting', 'Nasal congestion', 'Diarrhoea', 'Haemoptysis', 'Conjunctival congestion'],'percentage':[87.9,67.7,38.1,33.4,18.6,14.8,13.9,13.6,11.4,5.0,4.8,3.7,0.9,0.8]} symptoms=pd.DataFrame(data=symptoms,index=range(14)) symptoms

Just a sample of code.


There are many potentially impactful applications of machine learning to fighting the Covid-19, however, most are still in their early stages. Moreover, a lack of data sharing continues to inhibit overall progress in a variety of medical research problems. However, I believe that utilizing things like meta-learning, domain adaptation, and reinforcement learning, while loosening restrictions to healthcare data, can allow ML to play an important role in containing/responding to both Coronavirus and future pandemics.

In conclusion, with machine learning I — who is no expert in infectious diseases — was able to gain a better understanding of the virus, and even a reasonable forecasting method, using pure ML methods.

In the meantime, stay safe everyone!

Stay safe and healthy!


What I have presented here are the insights of Role of A.I (Artificial Intelligence) In Corona Virus Pandemic. I hope you learned something today.

Always remember that solid business questions, clean and well-distributed data always beat fancy models.

Feel free to leave a message if you have any feedback, and share with anyone that might find this useful.

86 views0 comments
Powered by ProofFactor - Social Proof Notifications