Machine learning-based decision support system for orthognathic diagnosis and treatment planning.

BACKGROUND: Dento-maxillofacial deformities are common problems. Orthodontic-orthognathic surgery is the primary treatment but accurate diagnosis and careful surgical planning are essential for optimum outcomes. This study aimed to establish and verify a machine learning-based decision support system for treatment of dento-maxillofacial malformations. METHODS: Patients (n = 574) with dento-maxillofacial deformities undergoing spiral CT during January 2015 to August 2020 were enrolled to train diagnostic models based on five different machine learning algorithms; the diagnostic performances were compared with expert diagnoses. Accuracy, sensitivity, specificity, and area under the curve (AUC) were calculated. The adaptive artificial bee colony algorithm was employed to formulate the orthognathic surgical plan, and subsequently evaluated by maxillofacial surgeons in a cohort of 50 patients. The objective evaluation included the difference in bone position between the artificial intelligence (AI) generated and actual surgical plans for the patient, along with discrepancies in postoperative cephalometric analysis outcomes. RESULTS: The binary relevance extreme gradient boosting model performed best, with diagnostic success rates > 90% for six different kinds of dento-maxillofacial deformities; the exception was maxillary overdevelopment (89.27%). AUC was > 0.88 for all diagnostic types. Median score for the surgical plans was 9, and was improved after human-computer interaction. There was no statistically significant difference between the actual and AI- groups. CONCLUSIONS: Machine learning algorithms are effective for diagnosis and surgical planning of dento-maxillofacial deformities and help improve diagnostic efficiency, especially in lower medical centers.

Establishment of a three-dimensional coordinate system for measuring the recurrence rate after orthognathic surgery and evaluation and analysis of the degree of recurrence / 口腔疾病防治

Objective@# To establish a three-dimensional coordinate system that can accurately measure the recurrence rate after orthognathic surgery, and evaluate and analyze the degree of recurrence.@*Methods @#Data from patients who underwent orthognathic surgery in a hospital were selected to reconstruct three-dimensional images with spiral CT. The two researchers used the multiplane assisted positioning method to fix the points three times and screened them using intra-andintreclass correlation coefficients (ICC). Reproducible and accurate landmark points were drawn to establish different coordinate systems and calculate the facial asymmetry index (AI) to determine the coordinate system with the best mid-sagittal plane symmetry. This coordinate system and lateral radiographs were used to separately measure the recurrence rate, and evaluate and analyze the three-dimensional recurrence degree of orthognathic surgery.@*Results @#Ten landmark points that may be repeatedly fixed were obtained, including N (nasion), K (K point), ANS(anterior nasal spine), PNS (posterior nasal spine), Ptm(pterygomaxillary fissure), Gn (gnathion), IZ(IZ point), MZ (MZ point), Ms (mastoideale), Cor (coronion) and and Go (gonion). Three coordinate systems were established, and the most suitable coordinate system was the upper edge point of the left infraorbital foramen. The inner upper edge of the right infraorbital foramen and both sides of the midpoint of the ear points constituted the horizontal plane (HP), which passed through the outermost point of the left zygomatic frontal suture and the outermost point of the right zygomatic frontal suture and was perpendicular to the horizontal plane to constitute the coronal plane (CP). It was perpendicular to the two planes to form a sagittal plane (SP). Two-dimensional and three-dimensional measurements of recurrence were performed on 112 patients, and new three-dimensional recurrence evaluation results were obtained. Less than 40% had low recurrence, 40% to 61% had moderate recurrence, and greater than 61% had high recurrence.@*Conclusion@#This study established a three-dimensional coordinate system suitable for measuring the recurrence rate after orthognathic surgery, obtained a new three-dimensional recurrence evaluation result, and provided a clinical experimental basis for evaluating the effect of orthognathic surgery and improving stability.

Evaluation of factors influencing accuracy of virtual surgical planning in orthognatic surgery.

Three-dimensional virtual surgical planning has become routine practice in orthognatic and reconstructive surgery for the possibility to realize presurgical evaluation of intraoperative bones movements, the prediction of postoperative results and the high level of accuracy. Thanks to surface superimposition between 3D planned and 3D postoperative model of maxillo-facial skeleton, a medium discrepancy less than 1 mm was found in scientific literature, considering 15 different points of maxillofacial skeleton. In our study we decided to evaluate different factors that could invalidate that result in the same cohort of patients, such as sex, kind of dentofacial deformity, asymmetry, type of surgical approach and entity of maxillo-mandibular movements (more or less than 1 mm). We found out no significant differences among groups. We can state that virtual surgical planning and 3D surgical splints are a valid means of diagnosis, treatment and predictivity regardless factors that could influence post-operative results. In conclusion, virtual surgical planning and 3D surgical splints facilitated diagnosis, treatment planning and accuracy regardless of sex, dentofacial deformity class, surgery techniques, entity of advancement and asymmetry.

Research on the precision of virtual surgical planning in two⁃jaw orthognathic surgery / 口腔疾病防治

Objective@#To provide a clinical reference by evaluating the precision of virtual surgical planning in two⁃ jaw orthognathic surgery.@*Methods @#Thirty consecutive patients who required two⁃jaw orthognathic surgery were includ⁃ ed. A composite skull model was reconstructed using data from spiral computed tomography scan and surface scanning of the dental arch. LeFort I osteotomy of the maxilla and bilateral sagittal split ramus osteotomy of the mandible were simulated using Dolphin Imaging 11.7 Premium. Genioplasty was performed if indicated. Virtual plan was then trans⁃ ferred to operation room using 3D⁃printed surgical templates. Frankfort horizontal plane (FHP), midfacial plane (perpen⁃ dicular to the FHP through the nasion), and coronal plane (perpendicular to the FHP through the sella point) were the selected three symmetry planes.Midpoint of the contact of the maxillary and mandibular central incisors (UI, LI), and the mesio⁃buccal cusp of the first maxillary and mandibular molars (U6⁃R,U6⁃L, L6⁃R, L6⁃L) were the six chosen volu⁃metric landmarks. To calculate the linear difference and overall mean linear difference (mean difference of the distance between UI, LI, U6⁃R, U6⁃L, L6⁃R, L6⁃L to FHP, midfacial and coronal plane) between simulated and postoperative models, the distance between selected landmarks and symmetry planes was measured. To calculate the angular differ⁃ ence and overall mean angular difference, values of the angles constructed by the occlusal, palatal, and mandibular plane to FHP and midfacial plane respectively were determined on simulated and postoperative models@* Results@#The virtual surgical planning was successfully transferred to actual surgery with the help of 3D⁃printed surgical templates. All patients were satisfied with the postoperative facial profile and occlusion. The overall mean linear difference was 0.81 mm (0.71 mm for maxilla and 0.91 mm for mandible); and the overall mean angular difference was 0.95° (the mean angular difference relative to FHP was 1.10°, and that relative to midfacial plane was 0.83°)@* Conclusion@#Virtual sur⁃ gical planning facilitated the diagnosis, treatment planning, and precise bony segments repositioning in two⁃jaw orthog⁃ nathic surgery.

Analysis of mental status assessment of patiens with dento-maxillofacial deformities / 中国实用护理杂志

Objective To study the mental status of dento-maxillofacial deformities patients for orthognathic-orthodontic treatment,assess the testing results,and provide reference for doctors and nurses to evaluate mental features of patients.Methods 79 patients from a three-level and first-class hospital in Shanghai were collected from February 2011 to January 2012,who were to undergo orthognathic-orthodontic treatment.All the subjects filled in MMPI questionnaire before the operation.Results Scores of F and Pa subscales in male were significantly lower than the national norm.Scores of K and Mf subscales in female were significantly higher than the national norm.Scores of L,F,Hs,D,Pd,Pa,Pt,Sc,Si subscales were significantly lower than the national norm.Scores of F,Pa,Sc,Ma subscales in male were significantly higher than female.Scores of Mf subscales in female were significantly higher than male.Conclusions The whole personality of dento-maxillofacial deformities patients are normal.However,individualized personality deviation and psychological problems exist,including personality characteristics among different genders.