Comprehensive identification of Long Covid articles with human-in-the-loop machine learning

09/16/2022
by   Robert Leaman, et al.
11

A significant percentage of COVID-19 survivors experience ongoing multisystemic symptoms that often affect daily living, a condition known as Long Covid or post-acute-sequelae of SARS-CoV-2 infection. However, identifying Long Covid articles is challenging since articles refer to the condition using a variety of less common terms or refrain from naming it at all. We developed an iterative human-in-the-loop machine learning framework designed to effectively leverage the data available and make the most efficient use of human labels. Specifically, our approach combines data programming with active learning into a robust ensemble model. Evaluating our model on a holdout set demonstrates over three times the sensitivity of other methods. We apply our model to PubMed to create the Long Covid collection, and demonstrate that (1) most Long Covid articles do not refer to Long Covid by any name (2) when the condition is named, the name used most frequently in the biomedical literature is Long Covid, and (3) Long Covid is associated with disorders in a wide variety of body systems. The Long Covid collection is updated weekly and is searchable online at the LitCovid portal: https://www.ncbi.nlm.nih.gov/research/coronavirus/docsum?filters=e_condition.LongCovid

READ FULL TEXT

page 2

page 6

page 7

research
09/27/2022

LitCovid in 2022: an information resource for the COVID-19 literature

LitCovid (https://www.ncbi.nlm.nih.gov/research/coronavirus/), first lau...
research
10/27/2020

A Comprehensive Dictionary and Term Variation Analysis for COVID-19 and SARS-CoV-2

The number of unique terms in the scientific literature used to refer to...
research
12/16/2022

Using machine learning algorithms to determine the post-COVID state of a person by his rhythmogram

In this study we applyed machine-learning algorithms to determine the po...
research
04/24/2020

Target specific mining of COVID-19 scholarly articles using one-class approach

In recent years, several research articles have been published in the fi...
research
01/05/2021

COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data

Here we proposed an approach to analyze text classification methods base...
research
10/12/2020

SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search

With worldwide concerns surrounding the Severe Acute Respiratory Syndrom...
research
09/04/2020

Evaluating the effect of city lock-down on controlling COVID-19 propagation through deep learning and network science models

The special epistemic characteristics of the COVID-19, such as the long ...

Please sign up or login with your details

Forgot password? Click here to reset