AUG 08, 2023
How NLP helps evaluate COVID19 complications?
SEP 03, 2021
The COVID-19 pandemic has resulted in a significant loss of human life around the world, and it poses an unprecedented threat to public health, food systems, and the workplace.
The pandemic has wreaked havoc on the economy and society, putting tens of millions of people at risk of descending into extreme poverty. Food security, public health, and employment and labour issues, particularly worker health and safety, all intersect during the COVID-19 crisis.
In this situation of world wide crisis, a new machine learning–based Natural Language Processing (NLP) algorithm is getting popularly used for evaluating COVID-19 complications.
Natural language processing (NLP) is a subject of computer science—specifically, a branch of artificial intelligence (AI)—concerning the ability of computers to understand text and spoken words in the same manner that humans can.
Computational linguistics—rule-based human language modeling—is combined with statistical, machine learning, and deep learning models in NLP. These technologies help computers process human language in the form of text or speech data and ‘understand’ its full meaning.
A machine learning–based NLP system was recently built with the use of big data that can track imaging findings of respiratory disease reported on chest CT imaging reports with a good association to the evolution of the COVID-19 pandemic.
NLP is also being used by organisations to gain access to the landscape of scientific papers related to the coronavirus outbreak. NLP is used by researchers working on COVID-19 therapies to keep track of new articles, notably in the area of medication or vaccination safety.
Publishers have stepped forward to provide free access to key material, such as the Allen Institute for AI’s CORD-19 Dataset, Elsevier’s Coronavirus Dataset, and the Copyright Clearance Center’s COVID-19 collection. These incredible tools can be used to learn about treatment efficacy and safety profiles, co-morbidity profiles, the natural history of a virus or disease, and who in the population is most at risk for serious disease.
The author is Tanisha Gupta.