Next Article in Journal
Comparison of Innovative and Traditional Cardiometabolic Indices in Estimating Atherosclerotic Cardiovascular Disease Risk in Adults
Next Article in Special Issue
A Laboratory-Based Surveillance Study of Invasive Neisseria meningitidis, Streptococcus pneumoniae, and Haemophilus influenzae Diseases in a Serbian Pediatric Population—Implications for Vaccination
Previous Article in Journal
Proteomic Expression Profile in Human Temporomandibular Joint Dysfunction
 
 
Article

Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study

1
National Meningitis Reference Laboratory, Department of Public Health Policy, School of Public Health, University of West Attica, 122 43 Athens, Greece
2
Department of Mathematical Sciences and Informatics, and Health Research Institute (IdISBa), University of the Balearic Islands (UIB), 07122 Palma, Balearic Islands, Spain
3
ADEMA University School, University of the Balearic Islands (UIB), 07122 Palma, Balearic Islands, Spain
4
Department of Intensive Care Medicine, University Medical Center Hamburg-Eppendorf, 20251 Hamburg, Germany
*
Author to whom correspondence should be addressed.
Current address: University Research Institute of Maternal and Child Health and Precision Medicine, 115 27 Athens, Greece.
Academic Editors: Edward R.B. Moore, Raul Colodner and Ahmet F. Coskun
Diagnostics 2021, 11(4), 602; https://doi.org/10.3390/diagnostics11040602
Received: 1 February 2021 / Revised: 23 March 2021 / Accepted: 26 March 2021 / Published: 28 March 2021
(This article belongs to the Special Issue Diagnosis and Management of Meningococcal Disease)
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. View Full-Text
Keywords: meningitis; bacterial infection; viral infection; neutrophil-to-lymphocyte ratio; artificial intelligence; machine learning meningitis; bacterial infection; viral infection; neutrophil-to-lymphocyte ratio; artificial intelligence; machine learning
Show Figures

Figure 1

MDPI and ACS Style

Mentis, A.-F.A.; Garcia, I.; Jiménez, J.; Paparoupa, M.; Xirogianni, A.; Papandreou, A.; Tzanakaki, G. Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study. Diagnostics 2021, 11, 602. https://doi.org/10.3390/diagnostics11040602

AMA Style

Mentis A-FA, Garcia I, Jiménez J, Paparoupa M, Xirogianni A, Papandreou A, Tzanakaki G. Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study. Diagnostics. 2021; 11(4):602. https://doi.org/10.3390/diagnostics11040602

Chicago/Turabian Style

Mentis, Alexios-Fotios A., Irene Garcia, Juan Jiménez, Maria Paparoupa, Athanasia Xirogianni, Anastasia Papandreou, and Georgina Tzanakaki. 2021. "Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study" Diagnostics 11, no. 4: 602. https://doi.org/10.3390/diagnostics11040602

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop