With the development of artificial intelligence (AI) technology, it has a wide range of explorations in orthodontics. AI has greater application prospects in precise measurement, multidimensional diagnosis, treatment planning and efficacy prediction. At the same time, there are certain limitations in the application of AI, such as risks caused by individual variability, black box properties and unclear delineation of medical responsibilities. This paper summarized the history and current status of AI applications in orthodontics and discussed future development trends, to provide reference for clinical orthodontics.
Humans ; Artificial Intelligence ; Orthodontics ; Dental Care ; Forecasting ; Delivery of Health Care

Objective: To establish a comprehensive diagnostic classification model of lateral cephalograms based on artificial intelligence (AI) to provide reference for orthodontic diagnosis. Methods: A total of 2 894 lateral cephalograms were collected in Department of Orthodontics, Capital Medical University School of Stomatology from January 2015 to December 2021 to construct a data set, including 1 351 males and 1 543 females with a mean age of (26.4± 7.4) years. Firstly, 2 orthodontists (with 5 and 8 years of orthodontic experience, respectively) performed manual annotation and calculated measurement for primary classification, and then 2 senior orthodontists (with more than 20 years of orthodontic experience) verified the 8 diagnostic classifications including skeletal and dental indices. The data were randomly divided into training, validation, and test sets in the ratio of 7∶2∶1. The open source DenseNet121 was used to construct the model. The performance of the model was evaluated by classification accuracy, precision rate, sensitivity, specificity and area under the curve (AUC). Visualization of model regions of interest through class activation heatmaps. Results: The automatic classification model of lateral cephalograms was successfully established. It took 0.012 s on average to make 8 diagnoses on a lateral cephalogram. The accuracy of 5 classifications was 80%-90%, including sagittal and vertical skeletal facial pattern, mandibular growth, inclination of upper incisors, and protrusion of lower incisors. The acuracy rate of 3 classifications was 70%-80%, including maxillary growth, inclination of lower incisors and protrusion of upper incisors. The average AUC of each classification was ≥0.90. The class activation heat map of successfully classified lateral cephalograms showed that the AI model activation regions were distributed in the relevant structural regions. Conclusions: In this study, an automatic classification model for lateral cephalograms was established based on the DenseNet121 to achieve rapid classification of eight commonly used clinical diagnostic items.
Male ; Female ; Humans ; Young Adult ; Adult ; Artificial Intelligence ; Deep Learning ; Cephalometry ; Maxilla ; Mandible/diagnostic imaging*

Objective: To develop a multi-classification orthodontic image recognition system using the SqueezeNet deep learning model for automatic classification of orthodontic image data. Methods: A total of 35 000 clinical orthodontic images were collected in the Department of Orthodontics, Capital Medical University School of Stomatology, from October to November 2020 and June to July 2021. The images were from 490 orthodontic patients with a male-to-female ratio of 49∶51 and the age range of 4 to 45 years. After data cleaning based on inclusion and exclusion criteria, the final image dataset included 17 453 face images (frontal, smiling, 90° right, 90° left, 45° right, and 45° left), 8 026 intraoral images [frontal occlusion, right occlusion, left occlusion, upper occlusal view (original and flipped), lower occlusal view (original and flipped) and coverage of occlusal relationship], 4 115 X-ray images [lateral skull X-ray from the left side, lateral skull X-ray from the right side, frontal skull X-ray, cone-beam CT (CBCT), and wrist bone X-ray] and 684 other non-orthodontic images. A labeling team composed of orthodontic doctoral students, associate professors, and professors used image labeling tools to classify the orthodontic images into 20 categories, including 6 face image categories, 8 intraoral image categories, 5 X-ray image categories, and other images. The data for each label were randomly divided into training, validation, and testing sets in an 8∶1∶1 ratio using the random function in the Python programming language. The improved SqueezeNet deep learning model was used for training, and 13 000 natural images from the ImageNet open-source dataset were used as additional non-orthodontic images for algorithm optimization of anomaly data processing. A multi-classification orthodontic image recognition system based on deep learning models was constructed. The accuracy of the orthodontic image classification was evaluated using precision, recall, F1 score, and confusion matrix based on the prediction results of the test set. The reliability of the model's image classification judgment logic was verified using the gradient-weighted class activation mapping (Grad-CAM) method to generate heat maps. Results: After data cleaning and labeling, a total of 30 278 orthodontic images were included in the dataset. The test set classification results showed that the precision, recall, and F1 scores of most classification labels were 100%, with only 5 misclassified images out of 3 047, resulting in a system accuracy of 99.84%(3 042/3 047). The precision of anomaly data processing was 100% (10 500/10 500). The heat map showed that the judgment basis of the SqueezeNet deep learning model in the image classification process was basically consistent with that of humans. Conclusions: This study developed a multi-classification orthodontic image recognition system for automatic classification of 20 types of orthodontic images based on the improved SqueezeNet deep learning model. The system exhibitted good accuracy in orthodontic image classification.
Humans ; Male ; Female ; Child, Preschool ; Child ; Adolescent ; Young Adult ; Adult ; Middle Aged ; Deep Learning ; Reproducibility of Results ; Radiography ; Algorithms ; Cone-Beam Computed Tomography

Children in the mixed dentition grow rapidly, and various types of malocclusion often appear in this period. At the same time, there are many environmental factors affecting the development of the occlusion at this stage. Functional abnormalities related to lip, tongue, articulation and breathing, and impacted teeth should be actively intervened and blocked to avoid the continued development of the deformity. Appropriate orthopedic devices should be used in patients with skeletal malocclusion, if necessary, for growth modification and the influence of congenital factors and the prognosis of treatment should be fully evaluated. Over-intervention of the temporary malocclusions in the mixed dentition should be avoided. In conclusion, early orthodontic treatment in the mixed dentition requires a comprehensive assessment of the treatment need, risks, timing, cost and the ultimate benefit of the patient. The timing of orthodontic treatment is not the sooner the better. The indications must be strictly controlled, and the necessity and limitations must be carefully considered.
Child ; Dentition, Mixed ; Humans ; Malocclusion/therapy* ; Tongue ; Tongue Habits ; Tooth, Impacted

Intestinal flora is the largest microbial community in human body， which consists of more than 1 000 species. Its structure and metabolites change dynamically with the age， diet and intestinal environment of the host. Study shows that the intestinal microbes play a pivotal role in regulating human physiological and pathological processes， and intestinal flora imbalance may be the key factors affecting the occurrence and development of bone and joint diseases， including osteoporosis， osteoarthritis， rheumatoid arthritis and gouty arthritis. At present， calcitonin， estrogen， nonsteroidal anti-inflammatory drugs， immunosuppressants， xanthine oxidase inhibitors and other western drugs are mostly used to treat the above diseases. However， long-term use of western drugs leads to poor compliance and obvious gastrointestinal adverse reactions among patients. Traditional Chinese medicine （TCM） predominates in the treatment of bone and joint diseases due to its low price， high efficacy and slight side effects， with the advantages of multi-targets， multi-mechanism and multi-levels. In recent years， many scholars have carried out experiments and clinical studies on the treatment of bone and joint diseases by TCMs on the basis of the liver and kidney theory such as "tonifying liver and kidney and strengthening muscles and bones". Gratifying results have been achieved. However， the mechanism of action has not been fully clarified. Intestinal flora becomes a hot spot in medical research， and a close relationship between intestinal flora and bone and joint diseases has been unveiled. Relevant literature in China and abroad showed that TCM has a significant effect on the treatment of bone and joint diseases by regulating intestinal flora. In this paper， the relationship between intestinal flora and bone and joint diseases was summarized and the intervention of TCM active ingredients and compounds on intestinal flora was reviewed to facilitate the prevention and treatment of bone and joint diseases by TCM.

Chronic inflammatory demyelinating polyneuropathy (CIDP) with positive anti-contactin-associated protein-1 (Caspr1) antibody is a rare autoimmune antibody mediated peripheral neuropathy. A 62-year-old male patient was reported in this article, whose clinical manifestations were subacute onset, abnormal distal limb motor sensation, and increased cerebrospinal fluid protein level. The patient had a good response to plasma exchange. Electromyography of lower limbs showed that motor involvement was dominant, motor conduction velocity slowed down, compound motor active potential (CMAP) and sensory nerve active potential amplitude decreased, and F wave was not elicited; electromyography of upper limbs without symptoms showed that CMAP amplitude of median nerve decreased, and conduction velocity was normal. There are few reports of anti-Caspr1 positive CIDP in the world. The article summarized the characteristics of the patient and reviewed the relevant literature, in order to improve clinicians′ understanding and diagnosis and treatment ability of the disease.

Objective To investigate the effect of CYP46A1 on the pathogenesis of Alzheimer's disease.Methods Recombinant lentiviral vectors which including anthropogenic CYP46A1 were injected into bilateral hippocampus of 3-monthold male 5XFAD transgenic mice,while empty vectors were injected into the corresponding position of the control group.After two months,the ability of learning and memory were tested by Morris water maze and T maze experiments,and amyloid plaque and inflammatory infiltration in the brain were detected by immunohistochemical staining and ELISA respectively.Results Compared with the control group,CYP46A1 virus injection significantly increased the CYP46A1 mRNA and protein expression in hippocampus.In addition,CYP46A1 overexpression significantly decreased the latency to find the platform in Morris water maze test and increased the correct rate to choose in T maze test.Aβ immunohistochemical staining and plaques area statistics demonstrated that the amyloid plaque area of hippocampus in CYP46A1 overexpression mice was significantly reduced,and there was a significantly decrease of hippocampal astrocytes expression by means of GFAP staining.Furthermore,hippocampal CYP46A1 overexpression significantly decreased the expression level of Aβ40,Aβ42,IL-1β and TNF-α,while compare with the control group.Conclusion CYP46A1 overexpression in hippocampus can promote the cognitive impairment,as well as ameliorate the brain inflammatory infiltration in 5XFAD transgenic mice,suggesting that CYP46A1 has anti-Alzheimer's disease like effects.

BACKGROUNDSome esophageal cancer patients complicated with depression exhibit cognitive impairments. Frontal electroencephalogram (EEG) may be used as a reliable biomarker for prefrontal-mediated cognitive functions. This study was to investigate alterations of EEG and frontal cognitive impairment in esophageal cancer patients complicated with depression and to assess their correlation.

METHODSSixty-five esophageal cancer patients with depression (study group) and 62 healthy controls (control group) were included in this study. The study group were assigned into psychotic depressed (PD, n = 32) and nonpsychotic depressed (NPD, n = 33) subgroups based on complication with psychotic symptoms (Brief Psychiatric Rating Scale [BPRS] >35). EEG examination, Beck self-rating depression scale, and BPRS were used to assess clinical symptoms. Chi-square test, two independent sample t-test, one-way analysis of variance, and Kruskal-Wallis test were utilized to compare the variables between two groups. EEG abnormalities and scores of frontal cognitive function test were analyzed by partial correlation analysis in the PD and NPD subgroups.

RESULTSCompared with control group, the study group displayed greater scores either in the Stroop test (19.89 ± 2.05 vs. 24.12 ± 2.19, P = 0.006) or Color Trails Test (CTT; 11.92 ± 1.01 vs. 15.02 ± 1.63, P = 0.008), and reduced score (35.05 ± 2.01 vs. 32.11 ± 2.38, P = 0.007) in the verbal fluency test (VFT). Compared to NPD subgroup, PD subgroup exhibited increased scores in Stroop test (22.89 ± 2.07 vs. 25.38 ± 2.32, P = 0.009) and CTT (13.16 ± 1.71 vs. 15.82 ± 1.13, P = 0.008). Moreover, increased scores in Stroop test and CTT as well as scores in VFT were associated with the severity of depression. The study group had an abnormal frontal EEG, such as α forward, α asymmetry, α moderation, and increased θ activity relative to control group. Similarly, compared with NPD subgroup, PD subgroup displayed α forward, α asymmetry, and α moderation. The correlation test revealed that α forward and α asymmetry were negatively associated with VFT score, but positively correlated with the scores of CTT and the Stroop test in PD subgroup. In addition, α asymmetry in NPD subgroup was positively related to CTT scores.

CONCLUSIONThis study indicated that frontal cognitive impairment in esophageal cancer patients complicated with depression is associated with EEG alterations.

White spot lesions (WSLs), due to enamel demineralization, occur frequently in orthodontic treatment. We recently developed a novel rechargeable dental composite containing nanoparticles of amorphous calcium phosphate (NACP) with long-term calcium (Ca) and phosphate (P) ion release and caries-inhibiting capability. The objectives of this study were to develop the first NACP-rechargeable orthodontic cement and investigate the effects of recharge duration and frequency on the efficacy oftion re-release. The rechargeable cement consisted of pyromellitic glycerol dimethacrylate (PMGDM) and ethoxylated bisphenol A dimethacrylate (EBPADMA). NACP was mixed into the resin at 40% by mass. Specimens were tested for orthodontic bracket shear bond strength (SBS) to enamel, Ca and P ion initial release, recharge and re-release. The new orthodontic cement exhibited an SBS similar to commercial orthodontic cement without CaP release (P>0.1). Specimens after one recharge treatment (e.g., 1 min immersion in recharge solution repeating three times in one day, referred to as"1 min 3 times") exhibited a substantial and continuous re-release of Ca and P ions for 14 days without further recharge. The ion re-release did not decrease with increasing the number of recharge/re-release cycles (P>0.1). The ion re-release concentrations at 14 days versus various recharge treatments were as follows:1 min 3 times>3 min 2 times>1 min 2 times>6 min 1 time>3 min 1 time>1 min 1 time. In conclusion, although previous studies have shown that NACP nanocomposite remineralized tooth lesions and inhibited caries, the present study developed the first orthodontic cement with Ca and P ion recharge and long-term release capability. This NACP-rechargeable orthodontic cement is a promising therapy to inhibit enamel demineralization and WSLs around orthodontic brackets.

Conclusions The maximum resistance strength of the bone-bonding screw could suffice for orthodontics.