Publications
2024
de Oliveira, Pedro Henrique José; Li, Tengfei; Li, Haoyue; Gonçalves, João Roberto; Santos-Pinto, Ary; Junior, Luiz Gonzaga Gandini; Cevidanes, Lucia Soares; Toyama, Claudia; Feltrin, Guilherme Paladini; Campanha, Antonio Augusto; de Oliveira Junior, Melchiades Alves; Bianchi, Jonas
Artificial intelligence as a prediction tool for orthognathic surgery assessment Journal Article
In: Orthodontics & Craniofacial Research, vol. 27, iss. 5, pp. 785-794, 2024, ISSN: 1601-6335.
Abstract | Links | BibTeX | Tags: artificial intelligence, Class II, Class III, orthodontics, Orthognathic Surgery
@article{deOliveira2024,
title = {Artificial intelligence as a prediction tool for orthognathic surgery assessment},
author = {Pedro Henrique José de Oliveira and Tengfei Li and Haoyue Li and João Roberto Gonçalves and Ary Santos-Pinto and Luiz Gonzaga Gandini Junior and Lucia Soares Cevidanes and Claudia Toyama and Guilherme Paladini Feltrin and Antonio Augusto Campanha and Melchiades Alves de Oliveira Junior and Jonas Bianchi},
url = {https://doi.org/10.1111/ocr.12805},
doi = {10.1111/ocr.12805},
issn = {1601-6335},
year = {2024},
date = {2024-04-21},
journal = {Orthodontics & Craniofacial Research},
volume = {27},
issue = {5},
pages = {785-794},
abstract = {Introduction: An ideal orthodontic treatment involves qualitative and quantitative measurements of dental and skeletal components to evaluate patients' discrepancies, such as facial, occlusal, and functional characteristics. Deciding between orthodontics and orthognathic surgery remains challenging, especially in borderline patients. Advances in technology are aiding clinical decisions in orthodontics. The increasing availability of data and the era of big data enable the use of artificial intelligence to guide clinicians' diagnoses. This study aims to test the capacity of different machine learning (ML) models to predict whether orthognathic surgery or orthodontics treatment is required, using soft and hard tissue cephalometric values. Methods: A total of 920 lateral radiographs from patients previously treated with either conventional orthodontics or in combination with orthognathic surgery were used, comprising n = 558 Class II and n = 362 Class III patients, respectively. Thirty-two measures were obtained from each cephalogram at the initial appointment. The subjects were randomly divided into training (n = 552), validation (n = 183), and test (n = 185) datasets, both as an entire sample and divided into Class II and Class III sub-groups. The extracted data were evaluated using 10 machine learning models and by a four-expert panel consisting of orthodontists (n = 2) and surgeons (n = 2). Results: The combined prediction of 10 models showed top-ranked performance in the testing dataset for accuracy, F1-score, and AUC (entire sample: 0.707, 0.706, 0.791; Class II: 0.759, 0.758, 0.824; Class III: 0.822, 0.807, 0.89). Conclusions: The proposed combined 10 ML approach model accurately predicted the need for orthognathic surgery, showing better performance in Class III patients.},
keywords = {artificial intelligence, Class II, Class III, orthodontics, Orthognathic Surgery},
pubstate = {published},
tppubtype = {article}
}
Introduction: An ideal orthodontic treatment involves qualitative and quantitative measurements of dental and skeletal components to evaluate patients' discrepancies, such as facial, occlusal, and functional characteristics. Deciding between orthodontics and orthognathic surgery remains challenging, especially in borderline patients. Advances in technology are aiding clinical decisions in orthodontics. The increasing availability of data and the era of big data enable the use of artificial intelligence to guide clinicians' diagnoses. This study aims to test the capacity of different machine learning (ML) models to predict whether orthognathic surgery or orthodontics treatment is required, using soft and hard tissue cephalometric values. Methods: A total of 920 lateral radiographs from patients previously treated with either conventional orthodontics or in combination with orthognathic surgery were used, comprising n = 558 Class II and n = 362 Class III patients, respectively. Thirty-two measures were obtained from each cephalogram at the initial appointment. The subjects were randomly divided into training (n = 552), validation (n = 183), and test (n = 185) datasets, both as an entire sample and divided into Class II and Class III sub-groups. The extracted data were evaluated using 10 machine learning models and by a four-expert panel consisting of orthodontists (n = 2) and surgeons (n = 2). Results: The combined prediction of 10 models showed top-ranked performance in the testing dataset for accuracy, F1-score, and AUC (entire sample: 0.707, 0.706, 0.791; Class II: 0.759, 0.758, 0.824; Class III: 0.822, 0.807, 0.89). Conclusions: The proposed combined 10 ML approach model accurately predicted the need for orthognathic surgery, showing better performance in Class III patients.
2017
Oh, Heesoo; Baumrind, Sheldon; Korn, Edward L.; Dugoni, Steven; Boero, Roger; Aubert, Maryse; Boyd, Robert
A retrospective study of Class II mixed-dentition treatment Journal Article
In: Angle Orthodontist, vol. 87, no. 1, pp. 56-67, 2017.
Abstract | Links | BibTeX | Tags: Class II, Early treatment, retrospective
@article{Oh2017,
title = {A retrospective study of Class II mixed-dentition treatment},
author = {Heesoo Oh and Sheldon Baumrind and Edward L. Korn and Steven Dugoni and Roger Boero and Maryse Aubert and Robert Boyd},
url = {http://162.214.24.32/~crilorg/wp-content/uploads/2018/11/Oh_A-retrospective-study-of-Class-II-mixed-dentition-treatment.pdf},
year = {2017},
date = {2017-07-08},
journal = {Angle Orthodontist},
volume = {87},
number = {1},
pages = {56-67},
abstract = {Objective: To consider the effectiveness of early treatment using one mixed-dentition approach to the correction of moderate and severe Class II malocclusions.
Materials and Methods: Three groups of Class II subjects were included in this retrospective study: an early treatment (EarlyTx) group that first presented at age 7 to 9.5 years (n ¼ 54), a late treatment (LateTx) group whose first orthodontic visit occurred between ages 12 and 15 (n ¼ 58), and an untreated Class II (UnTx) group to assess the pretreatment comparability of the two treated groups (n¼51). Thirteen conventional cephalometric measurements were reported for each group and Class II molar severity was measured on the study casts of the EarlyTx and LateTx groups.
Results: Successful Class II correction was observed in approximately three quarters of both the EarlyTx group and the LateTx group at the end of treatment. EarlyTx patients had fewer permanent teeth extracted than did the LateTx patients (5.6% vs 37.9%, P , .001) and spent less time in fullbonded appliance therapy in the permanent dentition than did LateTx patients (1.7 6 0.8 vs 2.6 6 0.7years, P , .001). When supervision time is included, the EarlyTx group had longer total treatment time and averaged more visits than did the LateTx group (53.1 6 18. 8 vs 33.7 6 8.3, P, .0001). Fifty-five percent of the LateTx extraction cases involved removal of the maxillary first premolars only and were finished in a Class II molar relationship.
Conclusion: EarlyTx comprehensive mixed-dentition treatment was an effective modality for early correction of Class II malocclusions. (Angle Orthod. 2017;87:56–67)},
keywords = {Class II, Early treatment, retrospective},
pubstate = {published},
tppubtype = {article}
}
Objective: To consider the effectiveness of early treatment using one mixed-dentition approach to the correction of moderate and severe Class II malocclusions.
Materials and Methods: Three groups of Class II subjects were included in this retrospective study: an early treatment (EarlyTx) group that first presented at age 7 to 9.5 years (n ¼ 54), a late treatment (LateTx) group whose first orthodontic visit occurred between ages 12 and 15 (n ¼ 58), and an untreated Class II (UnTx) group to assess the pretreatment comparability of the two treated groups (n¼51). Thirteen conventional cephalometric measurements were reported for each group and Class II molar severity was measured on the study casts of the EarlyTx and LateTx groups.
Results: Successful Class II correction was observed in approximately three quarters of both the EarlyTx group and the LateTx group at the end of treatment. EarlyTx patients had fewer permanent teeth extracted than did the LateTx patients (5.6% vs 37.9%, P , .001) and spent less time in fullbonded appliance therapy in the permanent dentition than did LateTx patients (1.7 6 0.8 vs 2.6 6 0.7years, P , .001). When supervision time is included, the EarlyTx group had longer total treatment time and averaged more visits than did the LateTx group (53.1 6 18. 8 vs 33.7 6 8.3, P, .0001). Fifty-five percent of the LateTx extraction cases involved removal of the maxillary first premolars only and were finished in a Class II molar relationship.
Conclusion: EarlyTx comprehensive mixed-dentition treatment was an effective modality for early correction of Class II malocclusions. (Angle Orthod. 2017;87:56–67)
Materials and Methods: Three groups of Class II subjects were included in this retrospective study: an early treatment (EarlyTx) group that first presented at age 7 to 9.5 years (n ¼ 54), a late treatment (LateTx) group whose first orthodontic visit occurred between ages 12 and 15 (n ¼ 58), and an untreated Class II (UnTx) group to assess the pretreatment comparability of the two treated groups (n¼51). Thirteen conventional cephalometric measurements were reported for each group and Class II molar severity was measured on the study casts of the EarlyTx and LateTx groups.
Results: Successful Class II correction was observed in approximately three quarters of both the EarlyTx group and the LateTx group at the end of treatment. EarlyTx patients had fewer permanent teeth extracted than did the LateTx patients (5.6% vs 37.9%, P , .001) and spent less time in fullbonded appliance therapy in the permanent dentition than did LateTx patients (1.7 6 0.8 vs 2.6 6 0.7years, P , .001). When supervision time is included, the EarlyTx group had longer total treatment time and averaged more visits than did the LateTx group (53.1 6 18. 8 vs 33.7 6 8.3, P, .0001). Fifty-five percent of the LateTx extraction cases involved removal of the maxillary first premolars only and were finished in a Class II molar relationship.
Conclusion: EarlyTx comprehensive mixed-dentition treatment was an effective modality for early correction of Class II malocclusions. (Angle Orthod. 2017;87:56–67)
de Oliveira, Pedro Henrique José; Li, Tengfei; Li, Haoyue; Gonçalves, João Roberto; Santos-Pinto, Ary; Junior, Luiz Gonzaga Gandini; Cevidanes, Lucia Soares; Toyama, Claudia; Feltrin, Guilherme Paladini; Campanha, Antonio Augusto; de Oliveira Junior, Melchiades Alves; Bianchi, Jonas
Artificial intelligence as a prediction tool for orthognathic surgery assessment Journal Article
In: Orthodontics & Craniofacial Research, vol. 27, iss. 5, pp. 785-794, 2024, ISSN: 1601-6335.
@article{deOliveira2024,
title = {Artificial intelligence as a prediction tool for orthognathic surgery assessment},
author = {Pedro Henrique José de Oliveira and Tengfei Li and Haoyue Li and João Roberto Gonçalves and Ary Santos-Pinto and Luiz Gonzaga Gandini Junior and Lucia Soares Cevidanes and Claudia Toyama and Guilherme Paladini Feltrin and Antonio Augusto Campanha and Melchiades Alves de Oliveira Junior and Jonas Bianchi},
url = {https://doi.org/10.1111/ocr.12805},
doi = {10.1111/ocr.12805},
issn = {1601-6335},
year = {2024},
date = {2024-04-21},
journal = {Orthodontics & Craniofacial Research},
volume = {27},
issue = {5},
pages = {785-794},
abstract = {Introduction: An ideal orthodontic treatment involves qualitative and quantitative measurements of dental and skeletal components to evaluate patients' discrepancies, such as facial, occlusal, and functional characteristics. Deciding between orthodontics and orthognathic surgery remains challenging, especially in borderline patients. Advances in technology are aiding clinical decisions in orthodontics. The increasing availability of data and the era of big data enable the use of artificial intelligence to guide clinicians' diagnoses. This study aims to test the capacity of different machine learning (ML) models to predict whether orthognathic surgery or orthodontics treatment is required, using soft and hard tissue cephalometric values. Methods: A total of 920 lateral radiographs from patients previously treated with either conventional orthodontics or in combination with orthognathic surgery were used, comprising n = 558 Class II and n = 362 Class III patients, respectively. Thirty-two measures were obtained from each cephalogram at the initial appointment. The subjects were randomly divided into training (n = 552), validation (n = 183), and test (n = 185) datasets, both as an entire sample and divided into Class II and Class III sub-groups. The extracted data were evaluated using 10 machine learning models and by a four-expert panel consisting of orthodontists (n = 2) and surgeons (n = 2). Results: The combined prediction of 10 models showed top-ranked performance in the testing dataset for accuracy, F1-score, and AUC (entire sample: 0.707, 0.706, 0.791; Class II: 0.759, 0.758, 0.824; Class III: 0.822, 0.807, 0.89). Conclusions: The proposed combined 10 ML approach model accurately predicted the need for orthognathic surgery, showing better performance in Class III patients.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Introduction: An ideal orthodontic treatment involves qualitative and quantitative measurements of dental and skeletal components to evaluate patients' discrepancies, such as facial, occlusal, and functional characteristics. Deciding between orthodontics and orthognathic surgery remains challenging, especially in borderline patients. Advances in technology are aiding clinical decisions in orthodontics. The increasing availability of data and the era of big data enable the use of artificial intelligence to guide clinicians' diagnoses. This study aims to test the capacity of different machine learning (ML) models to predict whether orthognathic surgery or orthodontics treatment is required, using soft and hard tissue cephalometric values. Methods: A total of 920 lateral radiographs from patients previously treated with either conventional orthodontics or in combination with orthognathic surgery were used, comprising n = 558 Class II and n = 362 Class III patients, respectively. Thirty-two measures were obtained from each cephalogram at the initial appointment. The subjects were randomly divided into training (n = 552), validation (n = 183), and test (n = 185) datasets, both as an entire sample and divided into Class II and Class III sub-groups. The extracted data were evaluated using 10 machine learning models and by a four-expert panel consisting of orthodontists (n = 2) and surgeons (n = 2). Results: The combined prediction of 10 models showed top-ranked performance in the testing dataset for accuracy, F1-score, and AUC (entire sample: 0.707, 0.706, 0.791; Class II: 0.759, 0.758, 0.824; Class III: 0.822, 0.807, 0.89). Conclusions: The proposed combined 10 ML approach model accurately predicted the need for orthognathic surgery, showing better performance in Class III patients.
Oh, Heesoo; Baumrind, Sheldon; Korn, Edward L.; Dugoni, Steven; Boero, Roger; Aubert, Maryse; Boyd, Robert
A retrospective study of Class II mixed-dentition treatment Journal Article
In: Angle Orthodontist, vol. 87, no. 1, pp. 56-67, 2017.
@article{Oh2017,
title = {A retrospective study of Class II mixed-dentition treatment},
author = {Heesoo Oh and Sheldon Baumrind and Edward L. Korn and Steven Dugoni and Roger Boero and Maryse Aubert and Robert Boyd},
url = {http://162.214.24.32/~crilorg/wp-content/uploads/2018/11/Oh_A-retrospective-study-of-Class-II-mixed-dentition-treatment.pdf},
year = {2017},
date = {2017-07-08},
journal = {Angle Orthodontist},
volume = {87},
number = {1},
pages = {56-67},
abstract = {Objective: To consider the effectiveness of early treatment using one mixed-dentition approach to the correction of moderate and severe Class II malocclusions.
Materials and Methods: Three groups of Class II subjects were included in this retrospective study: an early treatment (EarlyTx) group that first presented at age 7 to 9.5 years (n ¼ 54), a late treatment (LateTx) group whose first orthodontic visit occurred between ages 12 and 15 (n ¼ 58), and an untreated Class II (UnTx) group to assess the pretreatment comparability of the two treated groups (n¼51). Thirteen conventional cephalometric measurements were reported for each group and Class II molar severity was measured on the study casts of the EarlyTx and LateTx groups.
Results: Successful Class II correction was observed in approximately three quarters of both the EarlyTx group and the LateTx group at the end of treatment. EarlyTx patients had fewer permanent teeth extracted than did the LateTx patients (5.6% vs 37.9%, P , .001) and spent less time in fullbonded appliance therapy in the permanent dentition than did LateTx patients (1.7 6 0.8 vs 2.6 6 0.7years, P , .001). When supervision time is included, the EarlyTx group had longer total treatment time and averaged more visits than did the LateTx group (53.1 6 18. 8 vs 33.7 6 8.3, P, .0001). Fifty-five percent of the LateTx extraction cases involved removal of the maxillary first premolars only and were finished in a Class II molar relationship.
Conclusion: EarlyTx comprehensive mixed-dentition treatment was an effective modality for early correction of Class II malocclusions. (Angle Orthod. 2017;87:56–67)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Objective: To consider the effectiveness of early treatment using one mixed-dentition approach to the correction of moderate and severe Class II malocclusions.
Materials and Methods: Three groups of Class II subjects were included in this retrospective study: an early treatment (EarlyTx) group that first presented at age 7 to 9.5 years (n ¼ 54), a late treatment (LateTx) group whose first orthodontic visit occurred between ages 12 and 15 (n ¼ 58), and an untreated Class II (UnTx) group to assess the pretreatment comparability of the two treated groups (n¼51). Thirteen conventional cephalometric measurements were reported for each group and Class II molar severity was measured on the study casts of the EarlyTx and LateTx groups.
Results: Successful Class II correction was observed in approximately three quarters of both the EarlyTx group and the LateTx group at the end of treatment. EarlyTx patients had fewer permanent teeth extracted than did the LateTx patients (5.6% vs 37.9%, P , .001) and spent less time in fullbonded appliance therapy in the permanent dentition than did LateTx patients (1.7 6 0.8 vs 2.6 6 0.7years, P , .001). When supervision time is included, the EarlyTx group had longer total treatment time and averaged more visits than did the LateTx group (53.1 6 18. 8 vs 33.7 6 8.3, P, .0001). Fifty-five percent of the LateTx extraction cases involved removal of the maxillary first premolars only and were finished in a Class II molar relationship.
Conclusion: EarlyTx comprehensive mixed-dentition treatment was an effective modality for early correction of Class II malocclusions. (Angle Orthod. 2017;87:56–67)
Materials and Methods: Three groups of Class II subjects were included in this retrospective study: an early treatment (EarlyTx) group that first presented at age 7 to 9.5 years (n ¼ 54), a late treatment (LateTx) group whose first orthodontic visit occurred between ages 12 and 15 (n ¼ 58), and an untreated Class II (UnTx) group to assess the pretreatment comparability of the two treated groups (n¼51). Thirteen conventional cephalometric measurements were reported for each group and Class II molar severity was measured on the study casts of the EarlyTx and LateTx groups.
Results: Successful Class II correction was observed in approximately three quarters of both the EarlyTx group and the LateTx group at the end of treatment. EarlyTx patients had fewer permanent teeth extracted than did the LateTx patients (5.6% vs 37.9%, P , .001) and spent less time in fullbonded appliance therapy in the permanent dentition than did LateTx patients (1.7 6 0.8 vs 2.6 6 0.7years, P , .001). When supervision time is included, the EarlyTx group had longer total treatment time and averaged more visits than did the LateTx group (53.1 6 18. 8 vs 33.7 6 8.3, P, .0001). Fifty-five percent of the LateTx extraction cases involved removal of the maxillary first premolars only and were finished in a Class II molar relationship.
Conclusion: EarlyTx comprehensive mixed-dentition treatment was an effective modality for early correction of Class II malocclusions. (Angle Orthod. 2017;87:56–67)
2024 |
de Oliveira, Pedro Henrique José; Li, Tengfei; Li, Haoyue; Gonçalves, João Roberto; Santos-Pinto, Ary; Junior, Luiz Gonzaga Gandini; Cevidanes, Lucia Soares; Toyama, Claudia; Feltrin, Guilherme Paladini; Campanha, Antonio Augusto; de Oliveira Junior, Melchiades Alves; Bianchi, Jonas: Artificial intelligence as a prediction tool for orthognathic surgery assessment. In: Orthodontics & Craniofacial Research, vol. 27, iss. 5, pp. 785-794, 2024, ISSN: 1601-6335. (Type: Journal Article | Abstract | Links | BibTeX | Tags: artificial intelligence, Class II, Class III, orthodontics, Orthognathic Surgery)@article{deOliveira2024,Introduction: An ideal orthodontic treatment involves qualitative and quantitative measurements of dental and skeletal components to evaluate patients' discrepancies, such as facial, occlusal, and functional characteristics. Deciding between orthodontics and orthognathic surgery remains challenging, especially in borderline patients. Advances in technology are aiding clinical decisions in orthodontics. The increasing availability of data and the era of big data enable the use of artificial intelligence to guide clinicians' diagnoses. This study aims to test the capacity of different machine learning (ML) models to predict whether orthognathic surgery or orthodontics treatment is required, using soft and hard tissue cephalometric values. Methods: A total of 920 lateral radiographs from patients previously treated with either conventional orthodontics or in combination with orthognathic surgery were used, comprising n = 558 Class II and n = 362 Class III patients, respectively. Thirty-two measures were obtained from each cephalogram at the initial appointment. The subjects were randomly divided into training (n = 552), validation (n = 183), and test (n = 185) datasets, both as an entire sample and divided into Class II and Class III sub-groups. The extracted data were evaluated using 10 machine learning models and by a four-expert panel consisting of orthodontists (n = 2) and surgeons (n = 2). Results: The combined prediction of 10 models showed top-ranked performance in the testing dataset for accuracy, F1-score, and AUC (entire sample: 0.707, 0.706, 0.791; Class II: 0.759, 0.758, 0.824; Class III: 0.822, 0.807, 0.89). Conclusions: The proposed combined 10 ML approach model accurately predicted the need for orthognathic surgery, showing better performance in Class III patients. |
2017 |
Oh, Heesoo; Baumrind, Sheldon; Korn, Edward L.; Dugoni, Steven; Boero, Roger; Aubert, Maryse; Boyd, Robert: A retrospective study of Class II mixed-dentition treatment. In: Angle Orthodontist, vol. 87, no. 1, pp. 56-67, 2017. (Type: Journal Article | Abstract | Links | BibTeX | Tags: Class II, Early treatment, retrospective)@article{Oh2017,Objective: To consider the effectiveness of early treatment using one mixed-dentition approach to the correction of moderate and severe Class II malocclusions. Materials and Methods: Three groups of Class II subjects were included in this retrospective study: an early treatment (EarlyTx) group that first presented at age 7 to 9.5 years (n ¼ 54), a late treatment (LateTx) group whose first orthodontic visit occurred between ages 12 and 15 (n ¼ 58), and an untreated Class II (UnTx) group to assess the pretreatment comparability of the two treated groups (n¼51). Thirteen conventional cephalometric measurements were reported for each group and Class II molar severity was measured on the study casts of the EarlyTx and LateTx groups. Results: Successful Class II correction was observed in approximately three quarters of both the EarlyTx group and the LateTx group at the end of treatment. EarlyTx patients had fewer permanent teeth extracted than did the LateTx patients (5.6% vs 37.9%, P , .001) and spent less time in fullbonded appliance therapy in the permanent dentition than did LateTx patients (1.7 6 0.8 vs 2.6 6 0.7years, P , .001). When supervision time is included, the EarlyTx group had longer total treatment time and averaged more visits than did the LateTx group (53.1 6 18. 8 vs 33.7 6 8.3, P, .0001). Fifty-five percent of the LateTx extraction cases involved removal of the maxillary first premolars only and were finished in a Class II molar relationship. Conclusion: EarlyTx comprehensive mixed-dentition treatment was an effective modality for early correction of Class II malocclusions. (Angle Orthod. 2017;87:56–67) |