ABSTRACT
OBJECTIVES: To evaluate the performance of an artificial intelligence (AI) model in predicting orthognathic surgical outcomes compared to conventional prediction methods. MATERIALS AND METHODS: Preoperative and posttreatment lateral cephalograms from 705 patients who underwent combined surgical-orthodontic treatment were collected. Predictors included 254 input variables, including preoperative skeletal and soft-tissue characteristics, as well as the extent of orthognathic surgical repositioning. Outcomes were 64 Cartesian coordinate variables of 32 soft-tissue landmarks after surgery. Conventional prediction models were built applying two linear regression methods: multivariate multiple linear regression (MLR) and multivariate partial least squares algorithm (PLS). The AI-based prediction model was based on the TabNet deep neural network. The prediction accuracy was compared, and the influencing factors were analyzed. RESULTS: In general, MLR demonstrated the poorest predictive performance. Among 32 soft-tissue landmarks, PLS showed more accurate prediction results in 16 soft-tissue landmarks above the upper lip, whereas AI outperformed in six landmarks located in the lower border of the mandible and neck area. The remaining 10 landmarks presented no significant difference between AI and PLS prediction models. CONCLUSIONS: AI predictions did not always outperform conventional methods. A combination of both methods may be more effective in predicting orthognathic surgical outcomes.
Subject(s)
Anatomic Landmarks , Artificial Intelligence , Cephalometry , Orthognathic Surgical Procedures , Humans , Female , Cephalometry/methods , Male , Orthognathic Surgical Procedures/methods , Linear Models , Treatment Outcome , Adult , Young Adult , Adolescent , Neural Networks, Computer , Algorithms , Retrospective Studies , Least-Squares Analysis , ForecastingABSTRACT
OBJECTIVES: To evaluate an artificial intelligence (AI) model in predicting soft tissue and alveolar bone changes following orthodontic treatment and compare the predictive performance of the AI model with conventional prediction models. MATERIALS AND METHODS: A total of 1774 lateral cephalograms of 887 adult patients who had undergone orthodontic treatment were collected. Patients who had orthognathic surgery were excluded. On each cephalogram, 78 landmarks were detected using PIPNet-based AI. Prediction models consisted of 132 predictor variables and 88 outcome variables. Predictor variables were demographics (age, sex), clinical (treatment time, premolar extraction), and Cartesian coordinates of the 64 anatomic landmarks. Outcome variables were Cartesian coordinates of the 22 soft tissue and 22 hard tissue landmarks after orthodontic treatment. The AI prediction model was based on the TabNet deep neural network. Two conventional statistical methods, multivariate multiple linear regression (MMLR) and partial least squares regression (PLSR), were each implemented for comparison. Prediction accuracy among the methods was compared. RESULTS: Overall, MMLR demonstrated the most accurate results, while AI was least accurate. AI showed superior predictions in only 5 of the 44 anatomic landmarks, all of which were soft tissue landmarks inferior to menton to the terminal point of the neck. CONCLUSIONS: When predicting changes following orthodontic treatment, AI was not as effective as conventional statistical methods. However, AI had an outstanding advantage in predicting soft tissue landmarks with substantial variability. Overall, results may indicate the need for a hybrid prediction model that combines conventional and AI methods.
Subject(s)
Anatomic Landmarks , Artificial Intelligence , Cephalometry , Orthodontics, Corrective , Humans , Cephalometry/methods , Male , Female , Adult , Orthodontics, Corrective/methods , Treatment Outcome , Neural Networks, Computer , Young Adult , Adolescent , Linear Models , Alveolar Process/anatomy & histology , Alveolar Process/diagnostic imaging , Least-Squares AnalysisABSTRACT
OBJECTIVES: Since developing AI procedures demands significant computing resources and time, the implementation of a careful experimental design is essential. The purpose of this study was to investigate factors influencing the development of AI in orthodontics. MATERIALS AND METHODS: A total of 162 AI models were developed, with various combinations of sample sizes (170, 340, 679), input variables (40, 80, 160), output variables (38, 76, 154), training sessions (100, 500, 1000), and computer specifications (new vs. old). The TabNet deep-learning algorithm was used to develop these AI models, and leave-one-out cross-validation was applied in training. The goodness-of-fit of the regression models was compared using the adjusted coefficient of determination values, and the best-fit model was selected accordingly. Multiple linear regression analyses were employed to investigate the relationship between the influencing factors. RESULTS: Increasing the number of training sessions enhanced the effectiveness of the AI models. The best-fit regression model for predicting the computational time of AI, which included logarithmic transformation of time, sample size, and training session variables, demonstrated an adjusted coefficient of determination of 0.99. CONCLUSION: The study results show that estimating the time required for AI development may be possible using logarithmic transformations of time, sample size, and training session variables, followed by applying coefficients estimated through several pilot studies with reduced sample sizes and reduced training sessions.
ABSTRACT
OBJECTIVES: To compare facial growth prediction models based on the partial least squares and artificial intelligence (AI). MATERIALS AND METHODS: Serial longitudinal lateral cephalograms from 410 patients who had not undergone orthodontic treatment but had taken serial cephalograms were collected from January 2002 to December 2022. On every image, 46 skeletal and 32 soft-tissue landmarks were identified manually. Growth prediction models were constructed using multivariate partial least squares regression (PLS) and a deep learning method based on the TabNet deep neural network incorporating 161 predictor, and 156 response, variables. The prediction accuracy between the two methods was compared. RESULTS: On average, AI showed less prediction error by 2.11 mm than PLS. Among the 78 landmarks, AI was more accurate in 63 landmarks, whereas PLS was more accurate in nine landmarks, including cranial base landmarks. The remaining six landmarks showed no statistical difference between the two methods. Overall, soft-tissue landmarks, landmarks in the mandible, and growth in the vertical direction showed greater prediction errors than hard-tissue landmarks, landmarks in the maxilla, and growth changes in the horizontal direction, respectively. CONCLUSIONS: PLS and AI methods seemed to be valuable tools for predicting growth. PLS accurately predicted landmarks with low variability in the cranial base. In general, however, AI outperformed, particularly for those landmarks in the maxilla and mandible. Applying AI for growth prediction might be more advantageous when uncertainty is considerable.
Subject(s)
Artificial Intelligence , Face , Humans , Least-Squares Analysis , Face/diagnostic imaging , Mandible , Maxilla/diagnostic imagingABSTRACT
OBJECTIVES: The influence of gender-dependent metabolic risk factors on arterial stiffness has not been fully determined. This study was performed to investigate the relationship between components of metabolic syndrome and brachial-ankle pulse wave velocity (baPWV) according to gender. METHODS: A total of 537 subjects (54.4±7.5 years and 70.6% men) who underwent baPWV measurement during routine check-ups were analyzed. RESULTS: BaPWV was 1363±229cm/s in men and 1387±269cm/s in women (p=0.313). The prevalence of metabolic syndrome was not different according to gender (23% in men versus 27% in women, p=0.335). In multiple linear regression analyses, after adjustment for age, baPWV was significantly associated with systolic and diastolic blood pressures, fasting glucose, and triglyceride in both genders. Waist circumference was associated with baPWV in women but not in men. High-density lipoprotein levels were not associated with baPWV in either gender. Subjects with metabolic syndrome had a higher baPWV than those without metabolic syndrome for women aged <55 years, but not for all men and women aged ≥55 years. As the number of the components of metabolic syndrome increased, baPWV increased proportionally in both genders. However, this correlation was more strong in women than that in men (ß=0.408 versus ß=0.146 after adjustment for age). CONCLUSION: In middle-aged Koreans, women showed stronger associations between each component of metabolic syndrome and baPWV than men. The association of each component of metabolic syndrome to arterial stiffness may differ between men and women.
Subject(s)
Metabolic Syndrome/physiopathology , Pulse Wave Analysis , Sex Factors , Vascular Stiffness/physiology , Adult , Aged , Ankle/blood supply , Blood Glucose/analysis , Blood Pressure/physiology , Brachial Artery , Fasting/blood , Female , Humans , Lipoproteins, HDL/blood , Male , Metabolic Syndrome/blood , Middle Aged , Pulse Wave Analysis/methods , Risk Factors , Triglycerides/blood , Waist CircumferenceABSTRACT
We report on a 21-year-old man with fever, dyspnea, and pleuritic chest pain. An electrocardiography showed ST elevation in multiple lead and thoracic echocardiography revealed moderate pericardial effusion. He was initially diagnosed with acute pericarditis, and treated with nonsteroidal anti-inflammatory drugs and colchicines with clinical and laboratory improvement. After 1 month of medication, his symptoms recurred. An echocardiography showed constrictive physiology and the patient was treated with steroid on the top of current medication. The patient had been well for 7 months until dyspnea and edema developed, when an echocardiography showed marked increased pericardial thickness and constriction. Pericardial biopsy was performed and primary malignant pericardial mesothelioma was diagnosed. Malignancy should be considered in the differential diagnosis of recurrent pericarditis.
ABSTRACT
Benign cystic teratoma is recognized as one of the most common tumors in women during the reproductive age and frequently is treated by pelviscopic operation. Malignant transformation of a benign cystic teratoma is a rare event, and adenocarcinoma is extremely rare, and distinguishing this malignant change from benign disease preoperatively is nearly impossible even by the use of radiological imaging or various tumor markers. Therefore, patients should be informed that if a laparoscopic cystectomy is undertaken, a prompt second staging operation should be performed if the definitive pathology reveals an unexpected malignancy. We present a case with thyroid papillary carcinoma of follicular variant arising from mature cystic teratoma removed by laparoscopic salpingo-oophorectomy followed by staging laparotomy. We briefly reviewed literatures with regard to malignant transformation of a benign cystic teratoma.