How successful is the CatBoost classifier in diagnosing different dental anomalies in patients via sella turcica and vertebral morphologic alteration?
Algorithms
Machine learning
Orthodontics
Tooth abnormalities
Tooth, impacted
Journal
BMC medical informatics and decision making
ISSN: 1472-6947
Titre abrégé: BMC Med Inform Decis Mak
Pays: England
ID NLM: 101088682
Informations de publication
Date de publication:
29 Aug 2024
29 Aug 2024
Historique:
received:
31
05
2024
accepted:
21
08
2024
medline:
31
8
2024
pubmed:
31
8
2024
entrez:
29
8
2024
Statut:
epublish
Résumé
To investigate how successfully the classification of patients with and without dental anomalies was achieved through four experiments involving different dental anomalies. Lateral cephalometric radiographs (LCRs) from 526 individuals aged between 14 and 22 years were included. Four experiments involving different dental anomalies were created. Experiment 1 included the total dental anomaly group and control group (CG). Experiment 2 only had dental agenesis and a CG. Experiment 3 consisted of only palatally impacted canines and the CG. Experiment 4 comprised patients with various dental defects (transposition, hypodontia, agenesis-palatally affected canine, peg-shaped laterally, hyperdontia) and the CG. Twelve sella measurements and assessments of the ponticulus posticus and posterior arch deficiency were given as input. The target was to distinguish between anomalies and controls. The CatBoost algorithm was applied to classify patients with and without dental anomalies. In order from lowest to highest, the predictive accuracies of the experiments were as follows: experiment 4 < experiment 2 < experiment 3 < experiment 1. The sella area (SA) (mm2) was the most important variable in experiment 1. The most significant variable in prediction model of experiment 2 was sella height posterior (SHP) (mm). Sella area (SA) (mm2) was again the most relevant variable in experiment 3. The most important variable in experiment 4 was sella height median (SHM) (mm). Every prediction model from the four experiments prioritized different variables. These findings may suggest that related research should focus on specific traits from a diagnostic perspective.
Sections du résumé
BACKGROUND
BACKGROUND
To investigate how successfully the classification of patients with and without dental anomalies was achieved through four experiments involving different dental anomalies.
METHODS
METHODS
Lateral cephalometric radiographs (LCRs) from 526 individuals aged between 14 and 22 years were included. Four experiments involving different dental anomalies were created. Experiment 1 included the total dental anomaly group and control group (CG). Experiment 2 only had dental agenesis and a CG. Experiment 3 consisted of only palatally impacted canines and the CG. Experiment 4 comprised patients with various dental defects (transposition, hypodontia, agenesis-palatally affected canine, peg-shaped laterally, hyperdontia) and the CG. Twelve sella measurements and assessments of the ponticulus posticus and posterior arch deficiency were given as input. The target was to distinguish between anomalies and controls. The CatBoost algorithm was applied to classify patients with and without dental anomalies.
RESULTS
RESULTS
In order from lowest to highest, the predictive accuracies of the experiments were as follows: experiment 4 < experiment 2 < experiment 3 < experiment 1. The sella area (SA) (mm2) was the most important variable in experiment 1. The most significant variable in prediction model of experiment 2 was sella height posterior (SHP) (mm). Sella area (SA) (mm2) was again the most relevant variable in experiment 3. The most important variable in experiment 4 was sella height median (SHM) (mm).
CONCLUSIONS
CONCLUSIONS
Every prediction model from the four experiments prioritized different variables. These findings may suggest that related research should focus on specific traits from a diagnostic perspective.
Identifiants
pubmed: 39210331
doi: 10.1186/s12911-024-02643-8
pii: 10.1186/s12911-024-02643-8
pmc: PMC11360316
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
237Informations de copyright
© 2024. The Author(s).
Références
Dentomaxillofac Radiol. 2010 Jul;39(5):277-83
pubmed: 20587651
Eur J Orthod. 1983 Feb;5(1):1-46
pubmed: 6572593
J Korean Neurosurg Soc. 2015 Dec;58(6):528-33
pubmed: 26819687
J Chiropr Med. 2016 Jun;15(2):155-63
pubmed: 27330520
J Orthod Sci. 2022 Jan 28;11:2
pubmed: 35282293
Folia Morphol (Warsz). 2018;77(3):543-550
pubmed: 29500897
Cleft Palate Craniofac J. 2001 Sep;38(5):498-503
pubmed: 11522172
Clin Cosmet Investig Dent. 2018 Aug 20;10:179-187
pubmed: 30154673
Cleft Palate Craniofac J. 2021 Nov;58(11):1382-1388
pubmed: 33375837
Big Data. 2017 Jun;5(2):73-84
pubmed: 28632443
Eur J Orthod. 2010 Apr;32(2):148-53
pubmed: 19752019
Am J Orthod Dentofacial Orthop. 2014 Oct;146(4):437-41
pubmed: 25263146
Angle Orthod. 2009 Jul;79(4):727-32
pubmed: 19537879
Open Dent J. 2018 Jul 31;12:510-519
pubmed: 30197690
Odontology. 2020 Oct;108(4):730-737
pubmed: 32232696
Surg Radiol Anat. 2021 Jan;43(1):117-125
pubmed: 32914225
Eur J Orthod. 2006 Dec;28(6):580-5
pubmed: 16954179
Am J Orthod Dentofacial Orthop. 2021 May;159(5):627-634
pubmed: 33931222
Eur J Orthod. 2007 Oct;29(5):457-63
pubmed: 17693429
BMC Oral Health. 2018 Mar 16;18(1):45
pubmed: 29548316
Methods Protoc. 2022 Nov 21;5(6):
pubmed: 36412813
J Clin Pediatr Dent. 2023 Sep;47(5):124-132
pubmed: 37732445
Eur J Orthod. 2015 Feb;37(1):28-36
pubmed: 23159420
Eur J Orthod. 2011 Aug;33(4):461-5
pubmed: 21212168
Pol J Radiol. 2018 Apr 03;83:e120-e126
pubmed: 30038688
Int J Paediatr Dent. 2017 Nov;27(6):568-573
pubmed: 28387468
J Stomatol Oral Maxillofac Surg. 2018 Dec;119(6):482-485
pubmed: 29792938
J Big Data. 2020;7(1):94
pubmed: 33169094
Cleft Palate Craniofac J. 2015 Sep;52(5):597-604
pubmed: 26317632
Am J Orthod Dentofacial Orthop. 2017 Mar;151(3):513-520
pubmed: 28257736
Biometrics. 1977 Mar;33(1):159-74
pubmed: 843571
Artif Intell Med. 2001 Aug;23(1):89-109
pubmed: 11470218
Int J Dent. 2022 Sep 6;2022:3389741
pubmed: 36110970
Niger J Clin Pract. 2017 Jan;20(1):106-110
pubmed: 27958256
Eur J Orthod. 2004 Dec;26(6):597-604
pubmed: 15650069
Int J Environ Res Public Health. 2021 Apr 22;18(9):
pubmed: 33922272