ABSTRACT
Artificial intelligence has been applied to medical diagnosis and decision-making but it has not been used for classification of Class III malocclusions in children. OBJECTIVE: This study aims to propose an innovative machine learning (ML)-based diagnostic model for automatically classifies dental, skeletal and functional Class III malocclusions. METHODS: The collected data related to 46 cephalometric feature measurements from 4-14-year-old children (n = 666). The data set was divided into a training set and a test set in a 7:3 ratio. Initially, we employed the Recursive Feature Elimination (RFE) algorithm to filter the 46 input parameters, selecting 14 significant features. Subsequently, we constructed 10 ML models and trained these models using the 14 significant features from the training set through ten-fold cross-validation, and evaluated the models' average accuracy in test set. Finally, we conducted an interpretability analysis of the optimal model using the ML model interpretability tool SHapley Additive exPlanations (SHAP). RESULTS: The top five models ranked by their area under the curve (AUC) values were: GPR (0.879), RBF SVM (0.876), QDA (0.876), Linear SVM (0.875) and L2 logistic (0.869). The DeLong test showed no statistical difference between GPR and the other models (p > 0.05). Therefore GPR was selected as the optimal model. The SHAP feature importance plot revealed that he top five features were SN-GoMe (the ratio of the length of the anterior skull base SN to that of the mandibular base GoMe), U1-NA (maxillary incisor angulation to NA plane), Overjet (the distance between two lines perpendicular to the functional occlusal plane from U1 and L), ANB (the difference between angles SNA and SNB), and AB-NPo (the angle between the AB and N-Pog line). CONCLUSIONS: Our findings suggest that ML models based on cephalometric data could effectively assist dentists to classify dental, functional and skeletal Class III malocclusions in children. In addition, features such as SN_GoMe, U1_NA and Overjet can as important indicators for predicting the severity of Class III malocclusions.
ABSTRACT
There is growing interest in the impact of climate change on agricultural labor supply in China, rigorous empirical evidence for this issue is insufficient. This potentially important channel through which climate change may affect agricultural labor supply has not received attention. Using a panel survey data of 100 administrative villages and 2977 farmers in China, we find that temperature and precipitation do affect farmers' labor allocation, 1°C increase from the current average temperature will reduce agricultural labor supply by 0.252%, and 1mm increase from the current average rainfall will reduce agricultural labor supply by 0.001%. Climate change also leads to the decline of net agricultural income, which creates distorted incentives for households to over-supply labor to non-agriculture. Moreover, farmers with relatively lower risk tolerance preferred to reduce the current supply of agricultural labor when net agricultural income is projected to decrease under climate change scenarios.
Subject(s)
Agriculture , Climate Change , Farmers , China , Humans , Income , TemperatureABSTRACT
With the development of the shipbuilding industry, it is necessary to improve tribological properties of polyether ether ketone (PEEK) as a water-lubricated bearing material. In this study, the sulfonated PEEK (SPEEK) with three distinct chemical structures was synthesized through direct sulfonated polymerization, and high fault tolerance and a controllable sulfonation degree ensured the batch stability. The tribological and mechanical properties of SPEEK with varying side groups (methyl and tert-butyl) and rigid segments (biphenyl) were compared after sintering in a vacuum furnace. Compared to the as-made PEEK, as the highly electronegative sulfonic acid group enhanced the hydration lubrication, the friction coefficient and wear rate of SPEEK were significantly reduced by 30% and 50% at least without affecting the mechanical properties. And lower steric hindrance and entanglement between molecular chains were proposed to be partially responsible for the lowest friction behavior of SPEEK with methyl side groups, making it a promising and competitive option for water-lubricated bearings.
ABSTRACT
Cases of atopic dermatitis (AD)-like rash induced by IL-17A inhibitor secukinumab treatment (SI-AD) have been recently reported in psoriasis patients. To identify immune and inflammatory factors expression in SI-AD. A panel of 15 immune and inflammatory factors in peripheral blood samples from various groups, including patients with patients with SI-AD, psoriasis with secukinumab (S-stable), advanced psoriasis patients (Advanced) and healthy controls (HC). Interleukin-10 (IL-10), IL-4 and IL-17A were detected in skin tissue biopsy samples by immunohistochemistry and real-time quantitative polymerase chain reaction. The immunoglobulin E levels in the SI-AD patients exceeded normal values. The IL-10 levels in SI-AD patients were higher than those in S-stable patients, advanced patients and HC. The IL-4 levels in SI-AD patients were higher than that in S-stable patients and HC. The IL-17A levels in SI-AD patients were higher than those in advanced psoriasis patients and HC, but no significant differences were observed between SI-AD patients and S-stable patients. IL-10 and IL-4 levels were higher in AD-like rashes than in healthy skin, while IL-17A did not differ significantly between the two. Upon discontinuing secukinumab, and switching to oral cyclosporine, antihistamines, Janus kinase 1 inhibitor and topical glucocorticoids, SI-AD patients experienced significant improvement in their skin lesions. Upon reexamination, all 15 immune and inflammatory factors returned to normal levels. Immune shift from Th17 towards Th2 may occur in SI-AD, as indicated by abnormal expression of multiple immune and inflammatory factors observed in peripheral blood and skin tissues.
Subject(s)
Dermatitis, Atopic , Exanthema , Psoriasis , Humans , Dermatitis, Atopic/metabolism , Interleukin-10 , Interleukin-17/metabolism , Interleukin-4ABSTRACT
Introduction: Incidence and prevalence data are needed for the planning, funding, delivery and evaluation of injury prevention and health care programs. The objective of this study was to estimate the Canadian traumatic spinal cord injury (TSCI) incidence, prevalence and trends over time using national-level health administrative data. Methods: ICD-10 CA codes were used to identify the cases for the hospital admission and discharge incidence rates of TSCI in Canada from 2005 to 2016. Provincial estimates were calculated using the location of the admitting facility. Age and sex-specific incidence rates were set to the 2015/2016 rates for the 2017 to 2019 estimates. Annual incidence rates were used as input for the prevalence model that applied annual survivorship rates derived from life expectancy data. Results: For 2019, it was estimated that there were 1,199 cases (32.0 per million) of TSCI admitted to hospitals, with 123 (10% of admissions) in-hospital deaths and 1,076 people with TSCI (28.7 per million) were discharged in Canada. The estimated number of people living with TSCI was 30,239 (804/million); 15,533 (52%) with paraplegia and 14,706 (48%) with tetraplegia. Trends included an increase in the number of people injured each year from 874 to 1,199 incident cases (37%), an older average age at injury rising from 46.6 years to 54.3 years and a larger proportion over the age of 65 changing from 22 to 38%, during the 15-year time frame. Conclusion: This study provides a standard method for calculating the incidence and prevalence of TSCI in Canada using national-level health administrative data. The estimates are conservative based on the limitations of the data but represent a large Canadian sample over 15 years, which highlight national trends. An increasing number of TSCI cases among the elderly population due to falls reported in this study can inform health care planning, prevention strategies, and future research.
ABSTRACT
In recent years, research on applications of three-way decision (e.g., TWD) has attracted the attention of many scholars. In this paper, we combine TWD with multi-attribute decision-making (MADM). First, we utilize the essential idea of TOPSIS in MADM theory to propose a pair of new ideal relation models based on TWD, namely, the three-way ideal superiority model and the three-way ideal inferiority model. Second, in order to reduce errors caused by the subjectivity of decision-makers, we develop two new methods to calculate the state sets for the two proposed ideal relation models. Third, we employ aggregate relative loss functions to calculate the thresholds of each object, divide all objects into three different territories and sort all objects. Then, we use a concrete example of building appearance selection to verify the rationality and feasibility of our proposed models. Furthermore, we apply comparative analysis, Spearman's rank correlation analysis and experiment analysis to illustrate the consistency and superiority of our methods.
ABSTRACT
Microalgae-based technology is an environmental-friendly and cost-effective method for treating antibiotics-contaminated wastewater. This work investigated the removal of levofloxacin (LEV) by an oleaginous microalgae Chromochloris zofingiensis under photoautotrophic and heterotrophic conditions. The results showed that the significantly higher biomass production, accumulation of extracellular polymeric substance and LEV removal efficiency were achieved in heterotrophic C. zofingiensis compared with the photoautotrophic ones. The removal efficiencies under the heterotrophic condition were 97%, 88% and 76% at 1, 10, and 100 mg/L LEV, respectively. HPLC-MS/MS and RNA-Seq analyses suggested that LEV could be bioaccumulated and biodegraded by heterotrophic C. zofingiensis through the reactions of defluorination, hydroxylation, demethylation, ring cleavage, oxidation, dehydrogenation, denitrification, and decarboxylation. The chemical composition of the algal biomass obtained after LEV treatment indicated the potential of this alga for removing LEV from wastewaters and simultaneously producing biodiesel, astaxanthin, and other products. Collectively, this research shows that the heterotrophic C. zofingiensis can be identified as a promising candidate for removing LEV in wastewater remediation.
Subject(s)
Chlorella , Microalgae , Biofuels , Biomass , Extracellular Polymeric Substance Matrix , Levofloxacin , Tandem Mass SpectrometryABSTRACT
The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method aims at generating a set of high-quality 3D object proposals by exploiting stereo imagery. We formulate the problem as minimizing an energy function that encodes object size priors, placement of objects on the ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. We then exploit a CNN on top of these proposals to perform object detection. In particular, we employ a convolutional neural net (CNN) that exploits context and depth information to jointly regress to 3D bounding box coordinates and object pose. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. When combined with the CNN, our approach outperforms all existing results in object detection and orientation estimation tasks for all three KITTI object classes. Furthermore, we experiment also with the setting where LIDAR information is available, and show that using both LIDAR and stereo leads to the best result.
ABSTRACT
In this paper, we propose a novel edge preserving and multi-scale contextual neural network for salient object detection. The proposed framework is aiming to address two limits of the existing CNN based methods. First, region-based CNN methods lack sufficient context to accurately locate salient object since they deal with each region independently. Second, pixel-based CNN methods suffer from blurry boundaries due to the presence of convolutional and pooling layers. Motivated by these, we first propose an end-to-end edge-preserved neural network based on Fast R-CNN framework (named RegionNet) to efficiently generate saliency map with sharp object boundaries. Later, to further improve it, multi-scale spatial context is attached to RegionNet to consider the relationship between regions and the global scenes. Furthermore, our method can be generally applied to RGB-D saliency detection by depth refinement. The proposed framework achieves both clear detection boundary and multi-scale contextual robustness simultaneously for the first time, and thus achieves an optimized performance. Experiments on six RGB and two RGB-D benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance.In this paper, we propose a novel edge preserving and multi-scale contextual neural network for salient object detection. The proposed framework is aiming to address two limits of the existing CNN based methods. First, region-based CNN methods lack sufficient context to accurately locate salient object since they deal with each region independently. Second, pixel-based CNN methods suffer from blurry boundaries due to the presence of convolutional and pooling layers. Motivated by these, we first propose an end-to-end edge-preserved neural network based on Fast R-CNN framework (named RegionNet) to efficiently generate saliency map with sharp object boundaries. Later, to further improve it, multi-scale spatial context is attached to RegionNet to consider the relationship between regions and the global scenes. Furthermore, our method can be generally applied to RGB-D saliency detection by depth refinement. The proposed framework achieves both clear detection boundary and multi-scale contextual robustness simultaneously for the first time, and thus achieves an optimized performance. Experiments on six RGB and two RGB-D benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance.