Cargando…

An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool

Background: Critically ill neonates are at greater risk for adverse drug reactions (ADRs). The differentiation of ADRs from reactions associated with organ dysfunction/immaturity or genetic variability is difficult. Methods: In this prospective cohort study, each ADR was assessed using newborn-speci...

Descripción completa

Detalles Bibliográficos
Autores principales: Yalçın, Nadir, Kaşıkcı, Merve, Çelik, Hasan Tolga, Allegaert, Karel, Demirkan, Kutay, Yiğit, Şule, Yurdakök, Murat
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9777414/
https://www.ncbi.nlm.nih.gov/pubmed/36553270
http://dx.doi.org/10.3390/children9121826
_version_ 1784856097769652224
author Yalçın, Nadir
Kaşıkcı, Merve
Çelik, Hasan Tolga
Allegaert, Karel
Demirkan, Kutay
Yiğit, Şule
Yurdakök, Murat
author_facet Yalçın, Nadir
Kaşıkcı, Merve
Çelik, Hasan Tolga
Allegaert, Karel
Demirkan, Kutay
Yiğit, Şule
Yurdakök, Murat
author_sort Yalçın, Nadir
collection PubMed
description Background: Critically ill neonates are at greater risk for adverse drug reactions (ADRs). The differentiation of ADRs from reactions associated with organ dysfunction/immaturity or genetic variability is difficult. Methods: In this prospective cohort study, each ADR was assessed using newborn-specific severity and probability scales by the clinical pharmacist. Subsequently, a machine learning-based risk score was designed to predict ADR presence in neonates. Results: In 98/412 (23.8%) of (56.3%; male) neonates included, 187 ADRs (0.42 ADR/patient) were determined related to 49 different drugs (37.12%). Drugs identified as high risk were enoxaparin, dexmedetomidine, vinblastine, dornase alfa, etoposide/carboplatin and prednisolone. The independent variables included in the risk score to predict ADR presence, according to the random forest importance criterion, were: systemic hormones (2 points), cardiovascular drugs (3 points), diseases of the circulatory system (1 point), nervous system drugs (1 point), and parenteral nutrition treatment (1 point), (cut-off value: 3 points). This risk score correctly classified 91.1% of the observations in the test set (c-index: 0.914). Conclusions: Using the high-performing risk score specific to neonates, it is expected that high-risk neonatal ADRs can be determined and prevented before they occur. Moreover, the awareness of clinicians of these drugs can be improved with this web-tool, and mitigation strategies (change of drug, dose, treatment duration, etc.) can be considered, based on a benefit-harm relationship for suspected drugs with a newborn-centered approach.
format Online
Article
Text
id pubmed-9777414
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97774142022-12-23 An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool Yalçın, Nadir Kaşıkcı, Merve Çelik, Hasan Tolga Allegaert, Karel Demirkan, Kutay Yiğit, Şule Yurdakök, Murat Children (Basel) Article Background: Critically ill neonates are at greater risk for adverse drug reactions (ADRs). The differentiation of ADRs from reactions associated with organ dysfunction/immaturity or genetic variability is difficult. Methods: In this prospective cohort study, each ADR was assessed using newborn-specific severity and probability scales by the clinical pharmacist. Subsequently, a machine learning-based risk score was designed to predict ADR presence in neonates. Results: In 98/412 (23.8%) of (56.3%; male) neonates included, 187 ADRs (0.42 ADR/patient) were determined related to 49 different drugs (37.12%). Drugs identified as high risk were enoxaparin, dexmedetomidine, vinblastine, dornase alfa, etoposide/carboplatin and prednisolone. The independent variables included in the risk score to predict ADR presence, according to the random forest importance criterion, were: systemic hormones (2 points), cardiovascular drugs (3 points), diseases of the circulatory system (1 point), nervous system drugs (1 point), and parenteral nutrition treatment (1 point), (cut-off value: 3 points). This risk score correctly classified 91.1% of the observations in the test set (c-index: 0.914). Conclusions: Using the high-performing risk score specific to neonates, it is expected that high-risk neonatal ADRs can be determined and prevented before they occur. Moreover, the awareness of clinicians of these drugs can be improved with this web-tool, and mitigation strategies (change of drug, dose, treatment duration, etc.) can be considered, based on a benefit-harm relationship for suspected drugs with a newborn-centered approach. MDPI 2022-11-26 /pmc/articles/PMC9777414/ /pubmed/36553270 http://dx.doi.org/10.3390/children9121826 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yalçın, Nadir
Kaşıkcı, Merve
Çelik, Hasan Tolga
Allegaert, Karel
Demirkan, Kutay
Yiğit, Şule
Yurdakök, Murat
An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool
title An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool
title_full An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool
title_fullStr An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool
title_full_unstemmed An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool
title_short An Artificial Intelligence Approach to Support Detection of Neonatal Adverse Drug Reactions Based on Severity and Probability Scores: A New Risk Score as Web-Tool
title_sort artificial intelligence approach to support detection of neonatal adverse drug reactions based on severity and probability scores: a new risk score as web-tool
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9777414/
https://www.ncbi.nlm.nih.gov/pubmed/36553270
http://dx.doi.org/10.3390/children9121826
work_keys_str_mv AT yalcınnadir anartificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT kasıkcımerve anartificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT celikhasantolga anartificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT allegaertkarel anartificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT demirkankutay anartificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT yigitsule anartificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT yurdakokmurat anartificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT yalcınnadir artificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT kasıkcımerve artificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT celikhasantolga artificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT allegaertkarel artificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT demirkankutay artificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT yigitsule artificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool
AT yurdakokmurat artificialintelligenceapproachtosupportdetectionofneonataladversedrugreactionsbasedonseverityandprobabilityscoresanewriskscoreaswebtool