1
|
Middleton KM, Duren DL, McNulty KP, Oh H, Valiathan M, Sherwood RJ. Cross-sectional data accurately model longitudinal growth in the craniofacial skeleton. Sci Rep 2023; 13:19294. [PMID: 37935807 PMCID: PMC10630296 DOI: 10.1038/s41598-023-46018-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Accepted: 10/26/2023] [Indexed: 11/09/2023] Open
Abstract
Dense, longitudinal sampling represents the ideal for studying biological growth. However, longitudinal samples are not typically possible, due to limits of time, prohibitive cost, or health concerns of repeat radiologic imaging. In contrast, cross-sectional samples have few such drawbacks, but it is not known how well estimates of growth milestones can be obtained from cross-sectional samples. The Craniofacial Growth Consortium Study (CGCS) contains longitudinal growth data for approximately 2000 individuals. Single samples from the CGCS for individuals representing cross-sectional data were used to test the ability to predict growth parameters in linear trait measurements separately by sex. Testing across a range of cross-sectional sample sizes from 5 to the full sample, we found that means from repeated samples were able to approximate growth rates determined from the full longitudinal CGCS sample, with mean absolute differences below 1 mm at cross-sectional sample sizes greater than ~ 200 individuals. Our results show that growth parameters and milestones can be accurately estimated from cross-sectional data compared to population-level estimates from complete longitudinal data, underscoring the utility of such datasets in growth modeling. This method can be applied to other forms of growth (e.g., stature) and to cases in which repeated radiographs are not feasible (e.g., cone-beam CT).
Collapse
Affiliation(s)
- Kevin M Middleton
- Division of Biological Sciences, University of Missouri, Columbia, MO, USA.
| | - Dana L Duren
- Department of Orthopaedic Surgery, University of Missouri School of Medicine, Columbia, MO, USA
- Department of Pathology and Anatomical Sciences, University of Missouri School of Medicine, Columbia, MO, USA
| | - Kieran P McNulty
- Department of Anthropology, University of Minnesota, Minneapolis, MN, USA
| | - Heesoo Oh
- Department of Orthodontics, Arthur A. Dugoni School of Dentistry, University of the Pacific, San Francisco, CA, USA
| | - Manish Valiathan
- Department of Orthodontics, School of Dental Medicine, Case Western Reserve University, Cleveland, OH, USA
| | - Richard J Sherwood
- Department of Orthopaedic Surgery, University of Missouri School of Medicine, Columbia, MO, USA
- Department of Pathology and Anatomical Sciences, University of Missouri School of Medicine, Columbia, MO, USA
- Department of Orthodontics, School of Dental Medicine, Case Western Reserve University, Cleveland, OH, USA
| |
Collapse
|
2
|
Auconi P, Gili T, Capuani S, Saccucci M, Caldarelli G, Polimeni A, Di Carlo G. The Validity of Machine Learning Procedures in Orthodontics: What Is Still Missing? J Pers Med 2022; 12:jpm12060957. [PMID: 35743742 PMCID: PMC9225071 DOI: 10.3390/jpm12060957] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Revised: 05/31/2022] [Accepted: 06/05/2022] [Indexed: 11/16/2022] Open
Abstract
Artificial intelligence (AI) models and procedures hold remarkable predictive efficiency in the medical domain through their ability to discover hidden, non-obvious clinical patterns in data. However, due to the sparsity, noise, and time-dependency of medical data, AI procedures are raising unprecedented issues related to the mismatch between doctors’ mentalreasoning and the statistical answers provided by algorithms. Electronic systems can reproduce or even amplify noise hidden in the data, especially when the diagnosis of the subjects in the training data set is inaccurate or incomplete. In this paper we describe the conditions that need to be met for AI instruments to be truly useful in the orthodontic domain. We report some examples of computational procedures that are capable of extracting orthodontic knowledge through ever deeper patient representation. To have confidence in these procedures, orthodontic practitioners should recognize the benefits, shortcomings, and unintended consequences of AI models, as algorithms that learn from human decisions likewise learn mistakes and biases.
Collapse
Affiliation(s)
- Pietro Auconi
- Private Practice of Orthodontics, 00012 Rome, Italy;
| | - Tommaso Gili
- Networks Unit, IMT School for Advanced Studies Lucca, Piazza San Francesco 19, 55100 Lucca, Italy
- ISC CNR, Department of Physics, University of Rome “Sapienza”, P.le Aldo Moro 5, 00185 Rome, Italy; (S.C.); (G.C.)
- Correspondence:
| | - Silvia Capuani
- ISC CNR, Department of Physics, University of Rome “Sapienza”, P.le Aldo Moro 5, 00185 Rome, Italy; (S.C.); (G.C.)
| | - Matteo Saccucci
- Department of Oral and Maxillo-Facial Sciences, Sapienza University of Rome, Viale Regina Elena 287a, 00161 Rome, Italy; (M.S.); (A.P.); (G.D.C.)
| | - Guido Caldarelli
- ISC CNR, Department of Physics, University of Rome “Sapienza”, P.le Aldo Moro 5, 00185 Rome, Italy; (S.C.); (G.C.)
- Department of Molecular Sciences and Nanosystems, Ca’Foscari University of Venice, Via Torino 155, Venezia Mestre, 30172 Venice, Italy
- ECLT, Ca’ Bottacin, Dorsoduro 3246, 30123 Venice, Italy
| | - Antonella Polimeni
- Department of Oral and Maxillo-Facial Sciences, Sapienza University of Rome, Viale Regina Elena 287a, 00161 Rome, Italy; (M.S.); (A.P.); (G.D.C.)
| | - Gabriele Di Carlo
- Department of Oral and Maxillo-Facial Sciences, Sapienza University of Rome, Viale Regina Elena 287a, 00161 Rome, Italy; (M.S.); (A.P.); (G.D.C.)
| |
Collapse
|
3
|
Gili T, Di Carlo G, Capuani S, Auconi P, Caldarelli G, Polimeni A. Complexity and data mining in dental research: A network medicine perspective on interceptive orthodontics. Orthod Craniofac Res 2021; 24 Suppl 2:16-25. [PMID: 34519158 PMCID: PMC9292769 DOI: 10.1111/ocr.12520] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2021] [Revised: 06/23/2021] [Indexed: 12/19/2022]
Abstract
Procedures and models of computerized data analysis are becoming researchers' and practitioners' thinking partners by transforming the reasoning underlying biomedicine. Complexity theory, Network analysis and Artificial Intelligence are already approaching this discipline, intending to provide support for patient's diagnosis, prognosis and treatments. At the same time, due to the sparsity, noisiness and time-dependency of medical data, such procedures are raising many unprecedented problems related to the mismatch between the human mind's reasoning and the outputs of computational models. Thanks to these computational, non-anthropocentric models, a patient's clinical situation can be elucidated in the orthodontic discipline, and the growth outcome can be approximated. However, to have confidence in these procedures, orthodontists should be warned of the related benefits and risks. Here we want to present how these innovative approaches can derive better patients' characterization, also offering a different point of view about patient's classification, prognosis and treatment.
Collapse
Affiliation(s)
- Tommaso Gili
- Networks UnitIMT School for Advanced Studies LuccaLuccaItaly
- CNR‐ISC Unità SapienzaRomeItaly
| | - Gabriele Di Carlo
- Department of Oral and Maxillo‐Facial SciencesSapienza University of RomeRomeItaly
| | | | | | - Guido Caldarelli
- CNR‐ISC Unità SapienzaRomeItaly
- Department of Molecular Sciences and NanosystemsCa’Foscari University of VeniceVenezia MestreItaly
| | - Antonella Polimeni
- Department of Oral and Maxillo‐Facial SciencesSapienza University of RomeRomeItaly
| |
Collapse
|
4
|
de Frutos-Valle L, Martin C, Alarcón JA, Palma-Fernández JC, Ortega R, Iglesias-Linares A. Sub-clustering in skeletal class III malocclusion phenotypes via principal component analysis in a southern European population. Sci Rep 2020; 10:17882. [PMID: 33087764 PMCID: PMC7578100 DOI: 10.1038/s41598-020-74488-w] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2019] [Accepted: 09/28/2020] [Indexed: 02/08/2023] Open
Abstract
The main aim of this study was to generate an adequate sub-phenotypic clustering model of class III skeletal malocclusion in an adult population of southern European origin. The study design was conducted in two phases, a preliminary cross-sectional study and a subsequent discriminatory evaluation by main component and cluster analysis to identify differentiated skeletal sub-groups with differentiated phenotypic characteristics. Radiometric data from 699 adult patients of southern European origin were analyzed in 212 selected subjects affected by class III skeletal malocclusion. The varimax rotation was used with Kaiser normalization, to prevent variables with more explanatory capacity from affecting the rotation. A total of 21,624 radiographic measurements were obtained as part of the cluster model generation, using a total set of 55 skeletal variables for the subsequent analysis of the major component and cluster analyses. Ten main axes were generated representing 92.7% of the total variation. Three main components represented 58.5%, with particular sagittal and vertical variables acting as major descriptors. Post hoc phenotypic clustering retrieved six clusters: C1:9.9%, C2:18.9%, C3:33%, C4:3.77%, C5:16%, and C6:16%. In conclusion, phenotypic variation was found in the southern European skeletal class III population, demonstrating the existence of phenotypic variations between identified clusters in different ethnic groups.
Collapse
Affiliation(s)
- L de Frutos-Valle
- Section of Orthodontics, Faculty of Odontology, Complutense University, Madrid, Spain
| | - C Martin
- Section of Orthodontics, Faculty of Odontology, Complutense University, Madrid, Spain.,Craniofacial Biology Research Group, BIOCRAN, Complutense University, Plaza Ramón y Cajal, s/n, 28040, Madrid, Spain
| | - J A Alarcón
- Section of Orthodontics, Faculty of Odontology, University of Granada, Campus Universitario de Cartuja, Granada, Spain
| | - J C Palma-Fernández
- Section of Orthodontics, Faculty of Odontology, Complutense University, Madrid, Spain
| | - R Ortega
- Faculty of Odontology, Complutense University, Madrid, Spain
| | - A Iglesias-Linares
- Section of Orthodontics, Faculty of Odontology, Complutense University, Madrid, Spain. .,Craniofacial Biology Research Group, BIOCRAN, Complutense University, Plaza Ramón y Cajal, s/n, 28040, Madrid, Spain.
| |
Collapse
|
5
|
Rutili V, Nieri M, Giuntini V, McNamara JA, Franchi L. A multilevel analysis of craniofacial growth in subjects with untreated Class III malocclusion. Orthod Craniofac Res 2019; 23:181-191. [PMID: 31677327 DOI: 10.1111/ocr.12356] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2019] [Revised: 10/28/2019] [Accepted: 10/30/2019] [Indexed: 12/30/2022]
Abstract
OBJECTIVE To analyse the craniofacial growth of a long-term semi-longitudinal sample of Caucasian subjects with untreated Class III malocclusion. SETTING AND SAMPLE POPULATION A total of 144 Caucasian subjects (of North American and Italian origin) with untreated Class III malocclusion. MATERIALS AND METHODS Subjects aged 2 years and 9 months up to 21 years and 7 months were selected. A multilevel model was used to calculate growth curves for ten variables for both each individual subject and for the whole sample. RESULTS There was a statistically significant increase for total mandibular length (Co-Gn. T2-T1 = 8.4 mm), midfacial length (Co-A. T2-T1 = 3.4 mm) and lower anterior facial height (ANS-Me. T2-T1 = 3.8 mm). The multilevel analysis showed two points of acceleration of growth (about 3-5 years of age and 11-15 years of age) for seven out of ten variables. For Co-Gn and Co-A variables, males presented points of maximum growth delayed by 1 year in comparison with females, with a greater duration (1 year longer) and a greater total growth of about 5 mm. Active mandibular growth continued for a long time after the pubertal spurt: increases in mandibular length ended at about 17 years of age in females and at 21 years and 7 months in males. CONCLUSIONS Untreated Class III malocclusion showed a specific growth curve, especially for the mandible, whose excesses added up over time. In males, the amounts of mandibular and midfacial growth during the whole observation time were greater and lasted longer than in females.
Collapse
Affiliation(s)
- Valentina Rutili
- Section of Dentistry (Orthodontics), Department of Experimental and Clinical Medicine, The University of Florence, Italy
| | - Michele Nieri
- Section of Dentistry (Orthodontics), Department of Experimental and Clinical Medicine, The University of Florence, Italy
| | - Veronica Giuntini
- Section of Dentistry (Orthodontics), Department of Experimental and Clinical Medicine, The University of Florence, Italy
| | - James A McNamara
- Department of Orthodontics and Pediatric Dentistry, School of Dentistry, The University of Michigan, Ann Arbor, Michigan.,Emeritus of Cell and Developmental Biology, School of Medicine, The University of Michigan, Ann Arbor, Michigan.,Center for Human Growth and Development, The University of Michigan, Ann Arbor, Michigan.,Private Practice of Orthodontics, Ann Arbor, Michigan
| | - Lorenzo Franchi
- Section of Dentistry (Orthodontics), Department of Experimental and Clinical Medicine, The University of Florence, Italy.,Department of Orthodontics and Pediatric Dentistry, School of Dentistry, The University of Michigan, Ann Arbor, Michigan
| |
Collapse
|