Prediction models for early diagnosis of actinomycotic osteomyelitis of the jaw using machine learning techniques: a preliminary study.
Actinomycosis
Machine learning
Osteomyelitis
Journal
BMC oral health
ISSN: 1472-6831
Titre abrégé: BMC Oral Health
Pays: England
ID NLM: 101088684
Informations de publication
Date de publication:
06 05 2022
06 05 2022
Historique:
received:
28
10
2021
accepted:
25
04
2022
entrez:
6
5
2022
pubmed:
7
5
2022
medline:
11
5
2022
Statut:
epublish
Résumé
This study aimed to develop and validate five machine learning models designed to predict actinomycotic osteomyelitis of the jaw. Furthermore, this study determined the relative importance of the predictive variables for actinomycotic osteomyelitis of the jaw, which are crucial for clinical decision-making. A total of 222 patients with osteomyelitis of the jaw were analyzed, and Actinomyces were identified in 70 cases (31.5%). Logistic regression, random forest, support vector machine, artificial neural network, and extreme gradient boosting machine learning methods were used to train the models. The models were subsequently validated using testing datasets. These models were compared with each other and also with single predictors, such as age, using area under the receiver operating characteristic (ROC) curve (AUC). The AUC of the machine learning models ranged from 0.81 to 0.88. The performance of the machine learning models, such as random forest, support vector machine and extreme gradient boosting was significantly superior to that of single predictors. Presumed causes, antiresorptive agents, age, malignancy, hypertension, and rheumatoid arthritis were the six features that were identified as relevant predictors. This prediction model would improve the overall patient care by enhancing prognosis counseling and informing treatment decisions for high-risk groups of actinomycotic osteomyelitis of the jaw.
Sections du résumé
BACKGROUND
This study aimed to develop and validate five machine learning models designed to predict actinomycotic osteomyelitis of the jaw. Furthermore, this study determined the relative importance of the predictive variables for actinomycotic osteomyelitis of the jaw, which are crucial for clinical decision-making.
METHODS
A total of 222 patients with osteomyelitis of the jaw were analyzed, and Actinomyces were identified in 70 cases (31.5%). Logistic regression, random forest, support vector machine, artificial neural network, and extreme gradient boosting machine learning methods were used to train the models. The models were subsequently validated using testing datasets. These models were compared with each other and also with single predictors, such as age, using area under the receiver operating characteristic (ROC) curve (AUC).
RESULTS
The AUC of the machine learning models ranged from 0.81 to 0.88. The performance of the machine learning models, such as random forest, support vector machine and extreme gradient boosting was significantly superior to that of single predictors. Presumed causes, antiresorptive agents, age, malignancy, hypertension, and rheumatoid arthritis were the six features that were identified as relevant predictors.
CONCLUSIONS
This prediction model would improve the overall patient care by enhancing prognosis counseling and informing treatment decisions for high-risk groups of actinomycotic osteomyelitis of the jaw.
Identifiants
pubmed: 35524204
doi: 10.1186/s12903-022-02201-6
pii: 10.1186/s12903-022-02201-6
pmc: PMC9074201
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
164Informations de copyright
© 2022. The Author(s).
Références
Oral Surg Oral Med Oral Pathol. 1978 Jul;46(1):101-6
pubmed: 277867
Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 1998 May;85(5):496-508
pubmed: 9619663
Case Rep Dent. 2015;2015:689240
pubmed: 26451261
Infect Drug Resist. 2014 Jul 05;7:183-97
pubmed: 25045274
Dent Traumatol. 2013 Jun;29(3):185-96
pubmed: 23294978
Eur J Clin Microbiol Infect Dis. 2014 Nov;33(11):1873-80
pubmed: 24880820
Clin Oral Investig. 2021 May;25(5):2801-2809
pubmed: 33006027
J Dent Sci. 2017 Sep;12(3):301-307
pubmed: 30895066
J Med Internet Res. 2019 Apr 05;21(4):e12286
pubmed: 30950797
EJIFCC. 2009 Jan 20;19(4):203-11
pubmed: 27683318
J Oral Maxillofac Surg. 2018 Oct;76(10):2122-2130
pubmed: 29782813
Implant Dent. 2011 Oct;20(5):331-6
pubmed: 21881516
Nat Mach Intell. 2019 May;1(5):206-215
pubmed: 35603010
Protein Cell. 2018 May;9(5):488-500
pubmed: 29736705
J Oral Maxillofac Pathol. 2019 Jan-Apr;23(1):122-128
pubmed: 31110428
Sci Rep. 2016 Aug 17;6:31604
pubmed: 27530150
Stroke Vasc Neurol. 2017 Jun 21;2(4):230-243
pubmed: 29507784
Nat Biomed Eng. 2018 Oct;2(10):719-731
pubmed: 31015651
Adv Dent Res. 2018 Feb;29(1):71-77
pubmed: 29355422
Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 1997 Jun;83(6):652-6
pubmed: 9195617
J Oral Maxillofac Surg. 2009 Jul;67(7):1363-72
pubmed: 19531404
J Endod. 2002 Aug;28(8):613-8
pubmed: 12184427
Clin Infect Dis. 2009 Dec 1;49(11):1729-32
pubmed: 19886792
Nat Med. 2019 Jan;25(1):44-56
pubmed: 30617339
J Med Syst. 2018 Sep 29;42(11):214
pubmed: 30269237
Nat Med. 2019 Jan;25(1):24-29
pubmed: 30617335