Machine learning approach to identify adverse events in scientific biomedical literature
Abstract Monitoring the occurrence of adverse events in the scientific literature is a mandatory process in drug marketing surveillance. This is a very time‐consuming and complex task to fulfill the compliance and, most importantly, to ensure patient safety. Therefore, a machine learning (ML) algori...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2022-06-01
|
Series: | Clinical and Translational Science |
Online Access: | https://doi.org/10.1111/cts.13268 |
_version_ | 1811243172868653056 |
---|---|
author | Sonja Wewering Claudia Pietsch Marc Sumner Kornél Markó Anna‐Theresa Lülf‐Averhoff David Baehrens |
author_facet | Sonja Wewering Claudia Pietsch Marc Sumner Kornél Markó Anna‐Theresa Lülf‐Averhoff David Baehrens |
author_sort | Sonja Wewering |
collection | DOAJ |
description | Abstract Monitoring the occurrence of adverse events in the scientific literature is a mandatory process in drug marketing surveillance. This is a very time‐consuming and complex task to fulfill the compliance and, most importantly, to ensure patient safety. Therefore, a machine learning (ML) algorithm has been trained to support this manual intellectual review process, by automatically providing a classification of the literature articles into two types. An algorithm has been designed to automatically classify “relevant articles” which are reporting any kind of drug safety relevant information, and those which are not reporting an adverse drug reaction as “not relevant.” The review process is consisted of many rules and aspects which needed to be taken into consideration. Therefore, for the training of the algorithm, thousands of documents from previous screenings have been used. After several iterations of adjustments and fine tuning, the ML approach is definitively a great achievement in pre‐sorting the articles into “relevant” and “non‐relevant” and supporting the intellectual review process. |
first_indexed | 2024-04-12T14:02:44Z |
format | Article |
id | doaj.art-1c4e4322c0714966a2f34f52d7a764b8 |
institution | Directory Open Access Journal |
issn | 1752-8054 1752-8062 |
language | English |
last_indexed | 2024-04-12T14:02:44Z |
publishDate | 2022-06-01 |
publisher | Wiley |
record_format | Article |
series | Clinical and Translational Science |
spelling | doaj.art-1c4e4322c0714966a2f34f52d7a764b82022-12-22T03:30:09ZengWileyClinical and Translational Science1752-80541752-80622022-06-011561500150610.1111/cts.13268Machine learning approach to identify adverse events in scientific biomedical literatureSonja Wewering0Claudia Pietsch1Marc Sumner2Kornél Markó3Anna‐Theresa Lülf‐Averhoff4David Baehrens5Scientific & Competitive Intelligence, Bayer AG Wuppertal GermanyScientific & Competitive Intelligence, Bayer AG Wuppertal GermanyAverbis GmbH Freiburg GermanyAverbis GmbH Freiburg GermanyScientific & Competitive Intelligence, Bayer AG Wuppertal GermanyAverbis GmbH Freiburg GermanyAbstract Monitoring the occurrence of adverse events in the scientific literature is a mandatory process in drug marketing surveillance. This is a very time‐consuming and complex task to fulfill the compliance and, most importantly, to ensure patient safety. Therefore, a machine learning (ML) algorithm has been trained to support this manual intellectual review process, by automatically providing a classification of the literature articles into two types. An algorithm has been designed to automatically classify “relevant articles” which are reporting any kind of drug safety relevant information, and those which are not reporting an adverse drug reaction as “not relevant.” The review process is consisted of many rules and aspects which needed to be taken into consideration. Therefore, for the training of the algorithm, thousands of documents from previous screenings have been used. After several iterations of adjustments and fine tuning, the ML approach is definitively a great achievement in pre‐sorting the articles into “relevant” and “non‐relevant” and supporting the intellectual review process.https://doi.org/10.1111/cts.13268 |
spellingShingle | Sonja Wewering Claudia Pietsch Marc Sumner Kornél Markó Anna‐Theresa Lülf‐Averhoff David Baehrens Machine learning approach to identify adverse events in scientific biomedical literature Clinical and Translational Science |
title | Machine learning approach to identify adverse events in scientific biomedical literature |
title_full | Machine learning approach to identify adverse events in scientific biomedical literature |
title_fullStr | Machine learning approach to identify adverse events in scientific biomedical literature |
title_full_unstemmed | Machine learning approach to identify adverse events in scientific biomedical literature |
title_short | Machine learning approach to identify adverse events in scientific biomedical literature |
title_sort | machine learning approach to identify adverse events in scientific biomedical literature |
url | https://doi.org/10.1111/cts.13268 |
work_keys_str_mv | AT sonjawewering machinelearningapproachtoidentifyadverseeventsinscientificbiomedicalliterature AT claudiapietsch machinelearningapproachtoidentifyadverseeventsinscientificbiomedicalliterature AT marcsumner machinelearningapproachtoidentifyadverseeventsinscientificbiomedicalliterature AT kornelmarko machinelearningapproachtoidentifyadverseeventsinscientificbiomedicalliterature AT annatheresalulfaverhoff machinelearningapproachtoidentifyadverseeventsinscientificbiomedicalliterature AT davidbaehrens machinelearningapproachtoidentifyadverseeventsinscientificbiomedicalliterature |