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.

Comparison of Effects between Total Maxillary Setback Osteotomy and Anterior Maxillary Segmental Osteotomy on Nasolabial Morphology.

BACKGROUND: The authors aimed to compare the effects of total maxillary setback osteotomy (TMSO) and anterior maxillary segmental osteotomy (AMSO) on nasolabial morphology. METHODS: This retrospective clinical trial enrolled 130 patients undergoing maxillary surgery using TMSO or AMSO. Ten nasolabial-related parameters and nasal airway volume were measured preoperatively and postoperatively. The soft-tissue digital model was reconstructed using Geomagic Studio and Dolphin image 11.0. Statistical analysis was performed using IBM SPSS Version 27.0. RESULTS: A total of 75 patients underwent TMSO, and 55 underwent AMSO. Both techniques achieved optimal repositioning of the maxilla. Except for the dorsal nasal length, the dorsal nasal height, the length of the nasal columella, and the upper lip thickness, the remaining parameters were significantly different in the TMSO group. In the AMSO group, only the nasolabial angle, the alar base width, and the greatest alar width showed significant differences. There was a significant difference in the nasal airway volume for the TMSO group. The results of matching maps are consistent with the statistical results. CONCLUSIONS: TMSO has a more significant impact on both nose and upper lip soft tissues, whereas AMSO has a more significant impact on the upper lip and less on the nasal soft tissue. There is a significant decrease in nasal airway volume after TMSO, whereas AMSO showed less decrease. This retrospective study is helpful for clinicians and patients to understand the different changes in nasolabial morphology caused by the two interventions, which is essential for effective intervention and physician-patient communication. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, III.

Artificial Intelligence Splint in Orthognathic Surgery for Skeletal Class III Malocclusion: Design and Application.

BACKGROUND: Digital splints are indispensable in orthognathic surgery. However, the present design process of splints is time-consuming and has low reproducibility. To solve these problems, an algorithm for artificial intelligent splints has been developed in this study, making the automatic design of splints accessible. METHODS: Firstly, the algorithm and program of the artificial intelligence splint were created. Then a total of 54 patients with skeletal class III malocclusion were included in this study from 2018 to 2020. Pre and postoperative radiographic examinations were performed. The cephalometric measurements were recorded and the difference between virtual simulation and postoperative images was measured. The time cost and differences between artificial intelligent splints and digital splints were analyzed through both model surgery and radiographic images. RESULTS: The results showed that the efficiency of designing splints is significantly improved. And the mean difference between artificial intelligent splints and digital splints was <0.15 mm in model surgery. Meanwhile, there was no significant difference between the artificial intelligent splints and digital splints in radiological image analysis. CONCLUSIONS: In conclusion, compared with digital splints, artificial intelligent splints could save time for preoperative design while ensuring accuracy. The authors believed that it is conducive to the presurgical design of orthognathic surgery.

Hsa_circ_0007460 affects the survival of intracellular Mycobacterium tuberculosis by regulating autophagy and apoptosis of macrophages.

Circular RNA (circRNA) is a category of non-coding RNAs characterized by the absence of a 5'-cap and 3'-poly(A) tail, and participates in the physiological processes of various human diseases. Nonetheless, the diagnostic and functional significance of circRNAs in active pulmonary tuberculosis (ATB) remains uncertain. Consequently, the purpose of this study is to investigate whether hsa_circ_0007460 can be employed as a potential diagnostic biomarker in ATB patients and explore its function. The result of real-time quantitative fluorescent PCR (RT-qPCR) validated a notable increase in the expression of hsa_circ_0007460 in the peripheral blood of 32 ATB patients, as well as in THP-1 human macrophages infected with Bacillus Calmette Guerin (BCG) which is an attenuated strain of Mycobacterium bovis. Additionally, the receiver operating curve (ROC) illustrated that the area under the ROC curve (AUC), sensitivity and specificity were 0.7474, 76.67%, and 78.13% respectively. RNase R, Actinomycin D and other experiments confirmed that hsa_circ_0007460 was stabler than its linear mRNA, indicating that hsa_circ_0007460 has potential as a diagnostic biomarker of ATB. Furthermore, Western blot (WB), Cell Counting Kit-8 (CCK-8), plate counting, and immunofluorescence experiments revealed that hsa_circ_0007460 could regulate apoptosis and autophagy of macrophages. The downstream miRNAs and mRNAs were subsequently predicted using bioinformatics, and the hsa circ 0007460/hsa-miR-3127-5p/PATZ1 axis was built. These above results suggest that hsa_circ_0007460 is substantially up-regulated in the peripheral blood of patients with ATB and can be utilized as a potential diagnostic biomarker. In addition, hsa_circ_0007460 can promote apoptosis of macrophages and inhibit autophagy of macrophages, thereby promoting the survival of BCG.

Surgical Guides and Prebent Titanium Improve the Planning for the Treatment of Dentofacial Deformities Secondary to Condylar Osteochondroma.

PURPOSE: To investigate current Computer-Aided Design and Computer-Aided Manufacturing (CAD/CAM) technologies applied in the treatment of dentofacial deformities secondary to condylar osteochondroma and introduce a modified method with additional pre-bent titanium miniplates to improve the accuracy of operation. METHODS: Literature review about the application of CAD/CAM in the treatment of condylar osteochondroma and secondary dentofacial deformities was conducted. And 8 patients with condylar osteochondroma and secondary dentofacial deformities were treated by the CAD/CAM cutting and drilling surgical guides as well as pre-bent titanium miniplates. Pre- and post-operative 3D-cephalometric measurement were recorded and the difference between virtual simulation and postoperative modeling images was measured. Follow-up and radiographic examinations were performed. RESULTS: A total of 17 studies (including 216 patients) about the application of CAD/CAM in the treatment of dentofacial deformities secondary to condylar osteochondroma have been reported since 2010, including the 8 present patients. In our study, all patients were satisfied with the surgical outcome, without obvious relapse or evidence of temporomandibular joint disorder or other complications during follow-up; all patients avoided condylar reconstruction and sagittal split of ramus osteotomy on the ipsilateral mandible side. Comparison between simulated plans and actual postoperative outcomes showed surgical simulation plan was accurately transferred to the actual surgery. CONCLUSIONS: The application of CAD/CAM cutting and drilling guides as well as pre-bent titanium plates could achieve more accurate and favorable outcomes, improving the clinical planning and surgical execution for patients with condylar osteochondroma and secondary dentofacial deformities.

Computational analysis of mRNA expression profiles identifies microRNA-29a/c as predictor of colorectal cancer early recurrence.

Colorectal cancer (CRC) is one of the leading malignant cancers with a rapid increase in incidence and mortality. The recurrences of CRC after curative resection are sometimes unavoidable and often take place within the first year after surgery. MicroRNAs may serve as biomarkers to predict early recurrence of CRC, but identifying them from over 1,400 known human microRNAs is challenging and costly. An alternative approach is to analyze existing expression data of messenger RNAs (mRNAs) because generally speaking the expression levels of microRNAs and their target mRNAs are inversely correlated. In this study, we extracted six mRNA expression data of CRC in four studies (GSE12032, GSE17538, GSE4526 and GSE17181) from the gene expression omnibus (GEO). We inferred microRNA expression profiles and performed computational analysis to identify microRNAs associated with CRC recurrence using the IMRE method based on the MicroCosm database that includes 568,071 microRNA-target connections between 711 microRNAs and 20,884 gene targets. Two microRNAs, miR-29a and miR-29c, were disclosed and further meta-analysis of the six mRNA expression datasets showed that these two microRNAs were highly significant based on the Fisher p-value combination (p = 9.14 × 10(-9) for miR-29a and p = 1.14 × 10(-6) for miR-29c). Furthermore, these two microRNAs were experimentally tested in 78 human CRC samples to validate their effect on early recurrence. Our empirical results showed that the two microRNAs were significantly down-regulated (p = 0.007 for miR-29a and p = 0.007 for miR-29c) in the early-recurrence patients. This study shows the feasibility of using mRNA profiles to indicate microRNAs. We also shows miR-29a/c could be potential biomarkers for CRC early recurrence.