Cargando…

Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study

Differential diagnosis between bacterial and viral meningitis is crucial. In our study, to differentiate bacterial vs. viral meningitis, three machine learning (ML) algorithms (multiple logistic regression (MLR), random forest (RF), and naïve-Bayes (NB)) were applied for the two age groups (0–14 and...

Descripción completa

Detalles Bibliográficos
Autores principales: Mentis, Alexios-Fotios A., Garcia, Irene, Jiménez, Juan, Paparoupa, Maria, Xirogianni, Athanasia, Papandreou, Anastasia, Tzanakaki, Georgina
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8065596/
https://www.ncbi.nlm.nih.gov/pubmed/33800653
http://dx.doi.org/10.3390/diagnostics11040602
_version_ 1783682378462396416
author Mentis, Alexios-Fotios A.
Garcia, Irene
Jiménez, Juan
Paparoupa, Maria
Xirogianni, Athanasia
Papandreou, Anastasia
Tzanakaki, Georgina
author_facet Mentis, Alexios-Fotios A.
Garcia, Irene
Jiménez, Juan
Paparoupa, Maria
Xirogianni, Athanasia
Papandreou, Anastasia
Tzanakaki, Georgina
author_sort Mentis, Alexios-Fotios A.
collection PubMed
description Differential diagnosis between bacterial and viral meningitis is crucial. In our study, to differentiate bacterial vs. viral meningitis, three machine learning (ML) algorithms (multiple logistic regression (MLR), random forest (RF), and naïve-Bayes (NB)) were applied for the two age groups (0–14 and >14 years) of patients with meningitis by both conventional (culture) and molecular (PCR) methods. Cerebrospinal fluid (CSF) neutrophils, CSF lymphocytes, neutrophil-to-lymphocyte ratio (NLR), blood albumin, blood C-reactive protein (CRP), glucose, blood soluble urokinase-type plasminogen activator receptor (suPAR), and CSF lymphocytes-to-blood CRP ratio (LCR) were used as predictors for the ML algorithms. The performance of the ML algorithms was evaluated through a cross-validation procedure, and optimal predictions of the type of meningitis were above 95% for viral and 78% for bacterial meningitis. Overall, MLR and RF yielded the best performance when using CSF neutrophils, CSF lymphocytes, NLR, albumin, glucose, gender, and CRP. Also, our results reconfirm the high diagnostic accuracy of NLR in the differential diagnosis between bacterial and viral meningitis.
format Online
Article
Text
id pubmed-8065596
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-80655962021-04-25 Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study Mentis, Alexios-Fotios A. Garcia, Irene Jiménez, Juan Paparoupa, Maria Xirogianni, Athanasia Papandreou, Anastasia Tzanakaki, Georgina Diagnostics (Basel) Article Differential diagnosis between bacterial and viral meningitis is crucial. In our study, to differentiate bacterial vs. viral meningitis, three machine learning (ML) algorithms (multiple logistic regression (MLR), random forest (RF), and naïve-Bayes (NB)) were applied for the two age groups (0–14 and >14 years) of patients with meningitis by both conventional (culture) and molecular (PCR) methods. Cerebrospinal fluid (CSF) neutrophils, CSF lymphocytes, neutrophil-to-lymphocyte ratio (NLR), blood albumin, blood C-reactive protein (CRP), glucose, blood soluble urokinase-type plasminogen activator receptor (suPAR), and CSF lymphocytes-to-blood CRP ratio (LCR) were used as predictors for the ML algorithms. The performance of the ML algorithms was evaluated through a cross-validation procedure, and optimal predictions of the type of meningitis were above 95% for viral and 78% for bacterial meningitis. Overall, MLR and RF yielded the best performance when using CSF neutrophils, CSF lymphocytes, NLR, albumin, glucose, gender, and CRP. Also, our results reconfirm the high diagnostic accuracy of NLR in the differential diagnosis between bacterial and viral meningitis. MDPI 2021-03-28 /pmc/articles/PMC8065596/ /pubmed/33800653 http://dx.doi.org/10.3390/diagnostics11040602 Text en © 2021 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 (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ).
spellingShingle Article
Mentis, Alexios-Fotios A.
Garcia, Irene
Jiménez, Juan
Paparoupa, Maria
Xirogianni, Athanasia
Papandreou, Anastasia
Tzanakaki, Georgina
Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study
title Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study
title_full Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study
title_fullStr Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study
title_full_unstemmed Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study
title_short Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study
title_sort artificial intelligence in differential diagnostics of meningitis: a nationwide study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8065596/
https://www.ncbi.nlm.nih.gov/pubmed/33800653
http://dx.doi.org/10.3390/diagnostics11040602
work_keys_str_mv AT mentisalexiosfotiosa artificialintelligenceindifferentialdiagnosticsofmeningitisanationwidestudy
AT garciairene artificialintelligenceindifferentialdiagnosticsofmeningitisanationwidestudy
AT jimenezjuan artificialintelligenceindifferentialdiagnosticsofmeningitisanationwidestudy
AT paparoupamaria artificialintelligenceindifferentialdiagnosticsofmeningitisanationwidestudy
AT xirogianniathanasia artificialintelligenceindifferentialdiagnosticsofmeningitisanationwidestudy
AT papandreouanastasia artificialintelligenceindifferentialdiagnosticsofmeningitisanationwidestudy
AT tzanakakigeorgina artificialintelligenceindifferentialdiagnosticsofmeningitisanationwidestudy