A novel machine learning-based web application for field identification of infectious and inflammatory disorders of the central nervous system in cattle.
bovine neurology
central nervous system infections
clinical decision-making process
machine learning
Journal
Journal of veterinary internal medicine
ISSN: 1939-1676
Titre abrégé: J Vet Intern Med
Pays: United States
ID NLM: 8708660
Informations de publication
Date de publication:
Mar 2023
Mar 2023
Historique:
received:
16
11
2022
accepted:
03
02
2023
medline:
31
3
2023
pubmed:
11
3
2023
entrez:
10
3
2023
Statut:
ppublish
Résumé
Central nervous system (CNS) infections in cattle are a major cause of economic loss and mortality. Machine learning (ML) techniques are gaining widespread application in solving predictive tasks in both human and veterinary medicine. Our primary aim was to develop and compare ML models that could predict the likelihood of a CNS disorder of infectious or inflammatory origin in neurologically-impaired cattle. Our secondary aim was to create a user-friendly web application based on the ML model for the diagnosis of infection and inflammation of the CNS. Ninety-eight cattle with CNS infection and 86 with CNS disorders of other origin. Retrospective observational study. Six different ML methods (logistic regression [LR]; support vector machine [SVM]; random forest [RF]; multilayer perceptron [MLP]; K-nearest neighbors [KNN]; gradient boosting [GB]) were compared for their ability to predict whether an infectious or inflammatory disease was present based on demographics, neurological examination findings, and cerebrospinal fluid (CSF) analysis. All 6 methods had high prediction accuracy (≥80%). The accuracy of the LR model was significantly higher (0.843 ± 0.005; receiver operating characteristic [ROC] curve Our findings support the use of ML algorithms as promising tools for veterinarians to improve diagnosis. The open-access web application may aid clinicians in achieving correct diagnosis of infectious and inflammatory neurological disorders in livestock, with the added benefit of promoting appropriate use of antimicrobials.
Sections du résumé
BACKGROUND
BACKGROUND
Central nervous system (CNS) infections in cattle are a major cause of economic loss and mortality. Machine learning (ML) techniques are gaining widespread application in solving predictive tasks in both human and veterinary medicine.
OBJECTIVES
OBJECTIVE
Our primary aim was to develop and compare ML models that could predict the likelihood of a CNS disorder of infectious or inflammatory origin in neurologically-impaired cattle. Our secondary aim was to create a user-friendly web application based on the ML model for the diagnosis of infection and inflammation of the CNS.
ANIMALS
METHODS
Ninety-eight cattle with CNS infection and 86 with CNS disorders of other origin.
METHODS
METHODS
Retrospective observational study. Six different ML methods (logistic regression [LR]; support vector machine [SVM]; random forest [RF]; multilayer perceptron [MLP]; K-nearest neighbors [KNN]; gradient boosting [GB]) were compared for their ability to predict whether an infectious or inflammatory disease was present based on demographics, neurological examination findings, and cerebrospinal fluid (CSF) analysis.
RESULTS
RESULTS
All 6 methods had high prediction accuracy (≥80%). The accuracy of the LR model was significantly higher (0.843 ± 0.005; receiver operating characteristic [ROC] curve
CONCLUSION AND CLINICAL IMPORTANCE
CONCLUSIONS
Our findings support the use of ML algorithms as promising tools for veterinarians to improve diagnosis. The open-access web application may aid clinicians in achieving correct diagnosis of infectious and inflammatory neurological disorders in livestock, with the added benefit of promoting appropriate use of antimicrobials.
Identifiants
pubmed: 36896810
doi: 10.1111/jvim.16664
pmc: PMC10061175
doi:
Types de publication
Observational Study, Veterinary
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
766-773Subventions
Organisme : Ministero dell'Istruzione, dell'Università e della Ricerca
Informations de copyright
© 2023 The Authors. Journal of Veterinary Internal Medicine published by Wiley Periodicals LLC on behalf of American College of Veterinary Internal Medicine.
Références
Front Neurol. 2019 Aug 14;10:869
pubmed: 31474928
Vet Clin Pathol. 2009 Mar;38(1):103-12
pubmed: 19228366
Vet Clin North Am Food Anim Pract. 2004 Jul;20(2):243-73, vi
pubmed: 15203225
Vet Clin North Am Food Anim Pract. 2017 Mar;33(1):27-41
pubmed: 27939221
Vet Clin North Am Food Anim Pract. 1987 Mar;3(1):25-44
pubmed: 3552150
Front Vet Sci. 2021 Nov 02;8:721167
pubmed: 34796224
Vet Clin North Am Food Anim Pract. 2017 Mar;33(1):67-99
pubmed: 27956341
Vet Clin North Am Food Anim Pract. 2004 Jul;20(2):413-34, viii
pubmed: 15203233
Vet Clin North Am Food Anim Pract. 2004 Jul;20(2):363-77, vii
pubmed: 15203230
J Vet Diagn Invest. 2019 Jul;31(4):588-593
pubmed: 31179896
J Vet Intern Med. 2015 May-Jun;29(3):967-71
pubmed: 25857732
Vet Clin North Am Food Anim Pract. 2004 Jul;20(2):275-86, vi
pubmed: 15203226
Vet Clin North Am Food Anim Pract. 2004 Jul;20(2):287-302, vi-vii
pubmed: 15203227
J Vet Intern Med. 2023 Mar;37(2):766-773
pubmed: 36896810
Vet Clin North Am Food Anim Pract. 2004 Jul;20(2):231-42, v-vi
pubmed: 15203224
Vet Clin North Am Food Anim Pract. 2004 Jul;20(2):215-30, v
pubmed: 15203223
J Equine Vet Sci. 2020 Jul;90:102973
pubmed: 32534764
Vet Clin North Am Food Anim Pract. 2017 Mar;33(1):9-18
pubmed: 28166937
J Vet Intern Med. 2017 May;31(3):940-945
pubmed: 28382682