Browse
Submit Data
Databases
API
Help

Dataset Information

29 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine learning to predict distal caries in mandibular second molars associated with impacted third molars.

ABSTRACT: Impacted mandibular third molars (M3M) are associated with the occurrence of distal caries on the adjacent mandibular second molars (DCM2M). In this study, we aimed to develop and validate five machine learning (ML) models designed to predict the occurrence of DCM2Ms due to the proximity with M3Ms and determine the relative importance of predictive variables for DCM2Ms that are important for clinical decision making. A total of 2642 mandibular second molars adjacent to M3Ms were analyzed and DCM2Ms were identified in 322 cases (12.2%). The models were trained using logistic regression, random forest, support vector machine, artificial neural network, and extreme gradient boosting ML methods and were subsequently validated using testing datasets. The performance of the ML models was significantly superior to that of single predictors. The area under the receiver operating characteristic curve of the machine learning models ranged from 0.88 to 0.89. Six features (sex, age, contact point at the cementoenamel junction, angulation of M3Ms, Winter's classification, and Pell and Gregory classification) were identified as relevant predictors. These prediction models could be used to detect patients at a high risk of developing DCM2M and ultimately contribute to caries prevention and treatment decision-making for impacted M3Ms.

SUBMITTER: Hur SH

PROVIDER: S-EPMC8322059 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Outcomes of Coronectomy and Total Odontectomy of Impacted Mandibular Third Molars.

Project description:ObjectiveThe aim of this research was to evaluate the surgical complications and neurosensory deficits after coronectomy and the complete removal of mandibular third molars.MethodsThe study sample included patients requiring surgical removal of mandibular third molars. A coronectomy was conducted on 220 teeth showing signs of close proximity to the inferior alveolar canal. A complete extraction was performed on 218 teeth with no risk signs. The patients were evaluated at 1 week and 1, 3, 6, 12, and 24 months after surgery for pain, swelling, neurologic deficit, dry socket, postoperative bleeding, infection, root migration, and eruption.ResultsNo significant difference was noted in pain and swelling; however, bleeding and dry socket were significantly higher in the odontectomy group (P = .017). The inferior alveolar nerve deficit was higher in the odontectomy group (3.7%) than the coronectomy group (0.5%) (P = .017). The percentage and distance of root migration of coronectomised teeth at 3, 6, and 12 months were 60% (2.37 ± 0.96 mm), 66% (3.35 ± 0.86 mm), and 74% (3.85 ± 0.93 mm), respectively.ConclusionsCoronectomy is a safe procedure and should be performed when the roots are closely associated with the mandibular canal. Although root migration is common, the likelihood of root exposure is low and roots rarely need removal.

| S-EPMC10988245 | biostudies-literature

Automated detection of third molars and mandibular nerve by deep learning.

Project description:The approximity of the inferior alveolar nerve (IAN) to the roots of lower third molars (M3) is a risk factor for the occurrence of nerve damage and subsequent sensory disturbances of the lower lip and chin following the removal of third molars. To assess this risk, the identification of M3 and IAN on dental panoramic radiographs (OPG) is mandatory. In this study, we developed and validated an automated approach, based on deep-learning, to detect and segment the M3 and IAN on OPGs. As a reference, M3s and IAN were segmented manually on 81 OPGs. A deep-learning approach based on U-net was applied on the reference data to train the convolutional neural network (CNN) in the detection and segmentation of the M3 and IAN. Subsequently, the trained U-net was applied onto the original OPGs to detect and segment both structures. Dice-coefficients were calculated to quantify the degree of similarity between the manually and automatically segmented M3s and IAN. The mean dice-coefficients for M3s and IAN were 0.947 ± 0.033 and 0.847 ± 0.099, respectively. Deep-learning is an encouraging approach to segment anatomical structures and later on in clinical decision making, though further enhancement of the algorithm is advised to improve the accuracy.

| S-EPMC6588560 | biostudies-literature

Role of αENaC in root resorption of adjacent teeth due to entirely impacted mandibular third molars.

Project description:BackgroundEntirely impacted mandibular third molar (EIM3M) concerns the pathological external root resorption (ERR) of the adjacent mandibular second molar (M2M) and formation of granulation tissue between two molars. The study aimed to clarify the effect of αENaC, a mechano-sensitive molecule, to explore the mechanical mechanism in this scenario.MethodsThe force EIM3M exerted on M2M was proved by finite element analysis. αENaC expressions were tested by real-time polymerase chain reaction (PCR), immunoblotting and immunofluorescence. Inflammatory and epithelial-mesenchymal transition (EMT)-related molecules expressions were also detected by real-time PCR. The correlation was analyzed by Spearman's correlation analysis, and receiver-operator characteristic (ROC) curve was further exhibited.ResultsThe force was concentrated in the ERR area. αENaC was upregulated, positively correlated with ERR degree and localized to the fibroblasts in ERR granulation tissues. Moreover, αENaC was respectively and positively associated with elevated TNF-α and N-cadherin in ERR granulation tissues. More importantly, ROC analysis verified αENaC as a novel indication of the incidence of this disease.ConclusionsOur finding revealed the force from EIM3M causing ERR of M2M, and elucidated the expression and localization of αENaC and its positive correlation with inflammation, EMT and disease severity, suggesting a novel indication in this disease.

| S-EPMC10956368 | biostudies-literature

Evaluation of multi-task learning in deep learning-based positioning classification of mandibular third molars.

Project description:Pell and Gregory, and Winter's classifications are frequently implemented to classify the mandibular third molars and are crucial for safe tooth extraction. This study aimed to evaluate the classification accuracy of convolutional neural network (CNN) deep learning models using cropped panoramic radiographs based on these classifications. We compared the diagnostic accuracy of single-task and multi-task learning after labeling 1330 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014-2021). The mandibular third molar classifications were analyzed using a VGG 16 model of a CNN. We statistically evaluated performance metrics [accuracy, precision, recall, F1 score, and area under the curve (AUC)] for each prediction. We found that single-task learning was superior to multi-task learning (all p < 0.05) for all metrics, with large effect sizes and low p-values. Recall and F1 scores for position classification showed medium effect sizes in single and multi-task learning. To our knowledge, this is the first deep learning study to examine single-task and multi-task learning for the classification of mandibular third molars. Our results demonstrated the efficacy of implementing Pell and Gregory, and Winter's classifications for specific respective tasks.

| S-EPMC8758752 | biostudies-literature

A Pilot Randomized Controlled Clinical Trial Comparing Piezo Versus Conventional Rotary Surgery for Removal of Impacted Mandibular Third Molars.

Project description:BackgroundThe extraction of impacted mandibular third molars is a frequent dental surgery, interfering with patients' quality of life. Ultrasonic surgery is an alternative to osteotomy with conventional rotary instruments. This study compares postoperative signals and symptoms after extracting impacted mandibular third molars using ultrasonic surgery or conventional rotary osteotomy.MethodsA pilot randomized controlled clinical trial was conducted. Thirty patients were randomly divided into the test group (ultrasonic technique) and a control group (conventional rotatory technique). All surgeries were timed. Swelling parameters, trismus and paraesthesia were evaluated on the day of surgery and the third, fifth and seventh postoperative days. Intraoperative bleeding was evaluated during surgery. Postoperative pain was evaluated daily by the patient through a visual analogue scale and the number of ingested analgesics.ResultsPain, swelling and trismus present beneficial results with the ultrasonic technique but without statistical significance. Intraoperative bleeding was significantly lower with ultrasonic surgery (t(28) = 3.258; p = 0.003). Operating time was significantly higher in extractions involving osteotomy and cutting crown and roots either with the conventional technique (p = 0.020) or ultrasonic technique (p = 0.039). Regardless of the surgical difficulty, no statistically significant results were detected between techniques regarding the procedure duration.ConclusionsThe beneficial postoperative signs and symptoms make ultrasonic surgery a favourable therapeutic option, especially when the integrity of noble anatomical structures is the most important risk factor. Further studies with larger samples are needed to support the use of piezosurgery as a valid option for impacted mandibular third molar extraction.

| S-EPMC9311873 | biostudies-literature

Effect of Intrasocket Application of Manuka Honey on Postsurgical Pain of Impacted Mandibular Third Molars Surgery: Split-Mouth Randomized Controlled Trial.

Project description:Background and Purpose:Sufficient evidence exists recommending the use of honey in the management of wounds. Studies revealed that the healing effect of honey could be classified by its antibacterial and anti-inflammatory properties of its components. Since surgical extraction of impacted molars is one of the most common operations in the oral cavity and the postoperative pain disturbing the patient may reduce the quality of health service, this study aimed to assess the analgesic potential of Manuka honey application into the extraction socket of impacted mandibular third molars. Methods:This randomized split-mouth controlled study included 33 patients undergoing impacted bilateral lower third molars surgery under local anesthesia (n?=?66). Randomization was carried out by coin flipping. One of the two impacted third molars was assigned to treatment group (Manuka honey applied just before suturing), other side to control group (nothing applied). Postsurgical pain was evaluated using visual analogue scale (VAS) of faces 7 days after extraction. The total analgesic dose used was also evaluated. Results:In treatment group, postoperative VAS scores were significantly lower compared to that in control group regarding first and second days postoperatively (P?<?0.05). Total analgesic intake in the control group was significantly higher (P?=?0.0001). Conclusion:This study demonstrated that intrasocket application of Manuka honey after surgical extraction of impacted lower third molar is an effective method for reducing acute postsurgical pain.

| S-EPMC6328820 | biostudies-literature

Correlation Between Height and Impacted Third Molars and Genetics Role in Third Molar Impaction.

Project description:AimThis study sought to evaluate the relationship between height of an individual and the presence of impaction of maxillary and mandibular third molars, and to determine the role of genetics in third molar impaction.Materials and methodsThis was a case-control study, with cases consisted of 200 subjects with third molar impactions; and 200 controls without third molar impactions. Height of subjects was measured, and saliva samples were collected from all the subjects. DNA was extracted from saliva samples. To investigate the role of selected genes in the etiology of third molar impactions, Taqman Genotyping using SNPs identified for jaw growth, height and tooth agenesis was employed. Five candidate genes were investigated using 11 markers (SNPs).ResultsThe mean height of cases was significantly lower than that of the control subjects (p = 0.04). No difference was found in allele frequency between cases and controls for 10 of the 11 SNPs. However, for rs6504591 the p value was near significance (p = 0.07) with odd ratio of 2.131. Subjects with lower third molar impactions were significantly shorter than those who have fully erupted third molars.ConclusionsSubjects with lower third molar impactions were significantly shorter than those who have fully erupted third molars. We observed that individuals with third molar impaction tend to have T allele at the locus, suggesting that the T allele at the locus may increase the risk for having an impacted third molar. The rs6504591 G/T variation on human chromosome 17 (WNT9B gene) appears to increase risk by twofolds for impaction albeit with inability to detect significance due to small sample size.

| S-EPMC7855106 | biostudies-literature

Improvement of the Impacted Level of Lower Third Molars After Orthodontic Treatment

Project description: Not available

| S-EPMC10509441 | biostudies-literature

Up-to-Date Approach in the Treatment of Impacted Mandibular Molars: A Literature Review.

Project description:Eruption problems in the mandibular molars are rare, but they have to be diagnosed and treated early. Treatment of impacted molars is challenging due to a limited access and complexity of the mechanics that needs to be applied. Methods for managing impacted or tilted mandibular molars include orthodontic repositioning, surgical uprighting, and extraction with or without transplantation of the third molar into the extraction site. This review highlights the methods and clinical procedures of surgical and orthodontic uprighting procedures of mandibular molars with different degrees and levels of impaction. It further discusses the use of the ramus screw as a temporary anchorage device in the uprighting of horizontally impacted mandibular molars.

| S-EPMC7491971 | biostudies-literature

Correlation of Panoramic Radiography, Cone-Beam Computed Tomography, and Three-Dimensional Printing in the Assessment of the Spatial Location of Impacted Mandibular Third Molars.

Project description:The development of radiology, rapid prototyping techniques, and the increasingly common use of 3D printing in dentistry inspires the use of these techniques to improve diagnostic and therapeutic processes. This study aimed to conduct a retrospective comparative analysis of dental panoramic radiographs, cone-beam computed tomography, and 3D printing in preoperative assessment of the procedure's difficulty. Thirty clinical cases with a high degree of difficulty were selected, and based on evaluation with CBCT, a virtual 3D model of the region of surgical procedure was created, which was then printed using a 3D printer. The comparative analysis included the linear measurements performed in dental panoramic radiographs, cone-beam computed tomography, and 3D models in a preoperative assessment of the degree of retention and difficulty of impacted mandibular third molars in the mandible. Linear measurements performed on dental panoramic radiographs were significantly lower than in cone-beam computed tomography and 3D models. No statistically significant differences were obtained in linear measurements between 3D models and cone-beam computed tomography images except for the measurement of the lingual lamina thickness; however, due to the insignificant differences in measurements, with a mean of only 80 µm, the elective procedure of removal of the impacted third molar in the mandible may be safe.

| S-EPMC8466116 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data