Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features.
Characteristics of the mandible structures have been relevant in anthropological and forensic studies for sex prediction. This study aims to evaluate the coronoid process, condyle, and sigmoid notch patterns in sex prediction through supervised machine learning algorithms. Cephalometric radiographs...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0312824 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846163601558077440 |
|---|---|
| author | Isabela Bittencourt Basso Pedro Felipe de Jesus Freitas Aline Xavier Ferraz Ana Julia Borkovski Ana Laura Borkovski Rosane Sampaio Santos Rodrigo Nunes Rached Erika Calvano Küchler Angela Graciela Deliga Schroder Cristiano Miranda de Araujo Odilon Guariza-Filho |
| author_facet | Isabela Bittencourt Basso Pedro Felipe de Jesus Freitas Aline Xavier Ferraz Ana Julia Borkovski Ana Laura Borkovski Rosane Sampaio Santos Rodrigo Nunes Rached Erika Calvano Küchler Angela Graciela Deliga Schroder Cristiano Miranda de Araujo Odilon Guariza-Filho |
| author_sort | Isabela Bittencourt Basso |
| collection | DOAJ |
| description | Characteristics of the mandible structures have been relevant in anthropological and forensic studies for sex prediction. This study aims to evaluate the coronoid process, condyle, and sigmoid notch patterns in sex prediction through supervised machine learning algorithms. Cephalometric radiographs from 410 dental records of patients were screened to investigate the morphology of the coronoid process, condyle, and sigmoid notch and the Co-Gn distance. The following machine learning algorithms were used to build the predictive models: Decision Tree, Gradient Boosting Classifier, K-Nearest Neighbors (KNN), Logistic Regression, Multilayer Perceptron Classifier, Random Forest Classifier, and Support Vector Machine (SVM). A 5-fold cross-validation approach was adopted to validate each model. Metrics such as area under the curve (AUC), accuracy, recall, precision, and F1 Score were calculated for each model, and ROC curves were constructed. All tested variables demonstrated statistical significance (p < 0.10) and were included in the construction of the predictive model. The Co-Gn variable stood out as the most important among the evaluated independent variables, showing greater relevance in three of the four algorithms used in assessing feature importance. In the analysis of the models' performance, the AUC ranged from 0.82 [95% CI = 0.72-0.93] to 0.66 [95% CI = 0.53-0.76] for the test data, and from 0.83 [95% CI = 0.80-0.87] to 0.71 [95% CI = 0.61-0.75] for cross-validation. The precision of the models ranged from 0.83 [95% CI = 0.75-0.91] to 0.68 [95% CI = 0.58-0.78] in the test phase, and from 0.78 [95% CI = 0.74-0.82] to 0.69 [95% CI = 0.65-0.75] in cross-validation. The SVM, KNN, and Gradient Boosting Classifier algorithms stood out with the highest AUC and precision values in both cross-validation and testing. The use of condyle, coronoid process, and sigmoid notch characteristics, in combination with supervised machine learning predictive models, shows potential for contributing to sex prediction based on morphometric bone characteristics, particularly regarding the distance between the condyle and gnathion. However, given the study's limitations, these findings should be interpreted with caution. |
| format | Article |
| id | doaj-art-2ce92c8fffa94aa0950f5b34e439425e |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-2ce92c8fffa94aa0950f5b34e439425e2024-11-19T05:31:09ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011911e031282410.1371/journal.pone.0312824Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features.Isabela Bittencourt BassoPedro Felipe de Jesus FreitasAline Xavier FerrazAna Julia BorkovskiAna Laura BorkovskiRosane Sampaio SantosRodrigo Nunes RachedErika Calvano KüchlerAngela Graciela Deliga SchroderCristiano Miranda de AraujoOdilon Guariza-FilhoCharacteristics of the mandible structures have been relevant in anthropological and forensic studies for sex prediction. This study aims to evaluate the coronoid process, condyle, and sigmoid notch patterns in sex prediction through supervised machine learning algorithms. Cephalometric radiographs from 410 dental records of patients were screened to investigate the morphology of the coronoid process, condyle, and sigmoid notch and the Co-Gn distance. The following machine learning algorithms were used to build the predictive models: Decision Tree, Gradient Boosting Classifier, K-Nearest Neighbors (KNN), Logistic Regression, Multilayer Perceptron Classifier, Random Forest Classifier, and Support Vector Machine (SVM). A 5-fold cross-validation approach was adopted to validate each model. Metrics such as area under the curve (AUC), accuracy, recall, precision, and F1 Score were calculated for each model, and ROC curves were constructed. All tested variables demonstrated statistical significance (p < 0.10) and were included in the construction of the predictive model. The Co-Gn variable stood out as the most important among the evaluated independent variables, showing greater relevance in three of the four algorithms used in assessing feature importance. In the analysis of the models' performance, the AUC ranged from 0.82 [95% CI = 0.72-0.93] to 0.66 [95% CI = 0.53-0.76] for the test data, and from 0.83 [95% CI = 0.80-0.87] to 0.71 [95% CI = 0.61-0.75] for cross-validation. The precision of the models ranged from 0.83 [95% CI = 0.75-0.91] to 0.68 [95% CI = 0.58-0.78] in the test phase, and from 0.78 [95% CI = 0.74-0.82] to 0.69 [95% CI = 0.65-0.75] in cross-validation. The SVM, KNN, and Gradient Boosting Classifier algorithms stood out with the highest AUC and precision values in both cross-validation and testing. The use of condyle, coronoid process, and sigmoid notch characteristics, in combination with supervised machine learning predictive models, shows potential for contributing to sex prediction based on morphometric bone characteristics, particularly regarding the distance between the condyle and gnathion. However, given the study's limitations, these findings should be interpreted with caution.https://doi.org/10.1371/journal.pone.0312824 |
| spellingShingle | Isabela Bittencourt Basso Pedro Felipe de Jesus Freitas Aline Xavier Ferraz Ana Julia Borkovski Ana Laura Borkovski Rosane Sampaio Santos Rodrigo Nunes Rached Erika Calvano Küchler Angela Graciela Deliga Schroder Cristiano Miranda de Araujo Odilon Guariza-Filho Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features. PLoS ONE |
| title | Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features. |
| title_full | Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features. |
| title_fullStr | Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features. |
| title_full_unstemmed | Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features. |
| title_short | Sex prediction through machine learning utilizing mandibular condyles, coronoid processes, and sigmoid notches features. |
| title_sort | sex prediction through machine learning utilizing mandibular condyles coronoid processes and sigmoid notches features |
| url | https://doi.org/10.1371/journal.pone.0312824 |
| work_keys_str_mv | AT isabelabittencourtbasso sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT pedrofelipedejesusfreitas sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT alinexavierferraz sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT anajuliaborkovski sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT analauraborkovski sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT rosanesampaiosantos sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT rodrigonunesrached sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT erikacalvanokuchler sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT angelagracieladeligaschroder sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT cristianomirandadearaujo sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures AT odilonguarizafilho sexpredictionthroughmachinelearningutilizingmandibularcondylescoronoidprocessesandsigmoidnotchesfeatures |