This paper creates 3D models of Kitchon Root Controlled Auxiliary Archwire (Kitchon-RCAA) with different material properties and assembles them onto the main archwire equipped with brackets. By setting different loading methods and conducting Finite Element Analysis (FEA), the range of Orthodontic Torque/Support Force (OT/SF) values can be obtained. From the obtained values, it can be seen that changes in material properties have a significant impact on the mechanical properties of Kitchon-RCAA. When the properties of the Kitchon-RCAA material change two or more times, the mechanical values generated by Kitchon-RCAA cannot be directly added from two or more separate changes in the properties of the material. Therefore, it is necessary to simulate the model after each parameter change to obtain new results. And then the maxillary bio-model is reconstructed in reverse based on Cone Beam Computerized Tomography (CBCT) images. The biomechanical data equivalent to the mechanical mechanics generated by the root control assisted archwire is also added to the corresponding tooth positions, making indirect orthodontic behavior of Kitchon-RCAA on teeth possible. From the obtained results, it can be seen that the von Mises stress and total deformation magnitude for both normal teeth and corresponding Periodontal Ligament (PDL) position show a stable trend, while the Right Cuspid (R-C) and corresponding PDL with malformed root have a large stress concentration and may have a mold penetration problem. Overall, this paper not only analyses the mechanical behavior of the Kitchon-RCAA, this article not only analyzed the mechanical behavior of Kitchon-RCAA, but also its effect on the indirect biomechanical behavior of the teeth and PDL. And in combination with simulation result nephograms, it also enables predictability and visualization of orthodontic results. This helps dentists to provide safer and more reliable individualized orthodontic treatment plans for patients.
Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness. In this work, we propose to use pre-trained language models for knowledge graph completion. We treat triples in knowledge graphs as textual sequences and propose a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples. Our method takes entity and relation descriptions of a triple as input and computes scoring function of the triple with the KG-BERT language model. Experimental results on multiple benchmark knowledge graphs show that our method can achieve state-of-the-art performance in triple classification, link prediction and relation prediction tasks.
Clinical text classification is an fundamental problem in medical natural language processing. Existing studies have cocnventionally focused on rules or knowledge sources-based feature engineering, but only a limited number of studies have exploited effective representation learning capability of deep learning methods. In this study, we propose a new approach which combines rule-based features and knowledge-guided deep learning models for effective disease classification. Critical Steps of our method include recognizing trigger phrases, predicting classes with very few examples using trigger phrases and training a convolutional neural network (CNN) with word embeddings and Unified Medical Language System (UMLS) entity embeddings. We evaluated our method on the 2008 Integrating Informatics with Biology and the Bedside (i2b2) obesity challenge. The results demonstrate that our method outperforms the state-of-the-art methods. We showed that CNN model is powerful for learning effective hidden features, and CUIs embeddings are helpful for building clinical text representations. This shows integrating domain knowledge into CNN models is promising.
Acute kidney injury (AKI) in critically ill patients is associated with significant morbidity and mortality. Development of novel methods to identify patients with AKI earlier will allow for testing of novel strategies to prevent or reduce the complications of AKI. We developed data-driven prediction models to estimate the risk of new AKI onset. We generated models from clinical notes within the first 24 hours following intensive care unit (ICU) admission extracted from Medical Information Mart for Intensive Care III (MIMIC-III). From the clinical notes, we generated clinically meaningful word and concept representations and embeddings, respectively. Five supervised learning classifiers and knowledge-guided deep learning architecture were used to construct prediction models. The best configuration yielded a competitive AUC of 0.779. Our work suggests that natural language processing of clinical notes can be applied to assist clinicians in identifying the risk of incident AKI onset in critically ill patients upon admission to the ICU.
Abstract Traditional Chinese Medicine (TCM) has been developed for several thousand years and plays a significant role in health care for Chinese people. This paper studies the problem of classifying TCM clinical records into 5 main disease categories in TCM. We explored a number of state-of-the-art deep learning models and found that the recent Bidirectional Encoder Representations from Transformers can achieve better results than other deep learning models and other state-of-the-art methods. We further utilized an unlabeled clinical corpus to fine-tune the BERT language model before training the text classifier. The method only uses Chinese characters in clinical text as input without preprocessing or feature engineering. We evaluated deep learning models and traditional text classifiers on a benchmark data set. Our method achieves a state-of-the-art accuracy 89.39% ± 0.35%, Macro F1 score 88.64% ± 0.40% and Micro F1 score 89.39% ± 0.35%. We also visualized attention weights in our method, which can reveal indicative characters in clinical text.
This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating ODHSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many existing rule-based clinical NLP systems. We experimented our system on the corpus from i2b2's Obesity Challenge as a pilot study. Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants. This standardization enables a consistent application of numerous rule-based and machine learning based classification techniques downstream.
Abstract Background The T-loop has been used clinically to close gap between teeth. And it is a typical orthodontic archwire bending method. However, the design of the T-loop parameters for different patients is based on the clinical experience of the dentists. The variation in dentists' clinical experience is the main reason for inadequate orthodontic treatment, even high incidence of postoperative complications. Methods Firstly, the tooth movement prediction model is established based on the analysis of the T-loop structure and the waxy model dynamic resistance. As well as the reverse reconstruction of the complete maxillary 3D model based on the patient CBCT images, the oral biomechanical FEM analysis is completed. A maxillary waxy dental model is manufactured to realize the water-bath measurement experiment in vitro mimicking the oral bio-environment. Thus, the calculated, simulation and experimental data are obtained, as well as obtaining a cloud of total deformation from the simulation analysis. Results The growth trend of the 11 sets of simulation data is the same as that of the experimental data. And all of them show that the tooth displacement is positively correlated with the cross-sectional size of the archwire, and the clearance distance. As well as the higher Young's modulus of the archwire material, the greater the tooth displacement. And the effect of archwire parameters on tooth displacement derived from simulation and experimental data is consistent with the prediction model. The experimental and calculated data are also compared and analyzed, and the two kinds of data are basically consistent in terms of growth trends and fluctuations, with deviation rates ranging from 2.17 to 10.00%. Conclusions This study shows that the accuracy and reliability of the tooth movement prediction model can be verified through the comparative analysis and deviation calculation of the obtained calculated, simulation and experimental data, which can assist dentists to safely and efficiently perform orthodontic treatment on patients. And the FEM analysis can achieve predictability of orthodontic treatment results.
Pre-trained contextual language models such as BERT have dramatically improved performances for many NLP tasks recently. However, few have explored BERT on specific medical domain tasks such as early prediction for Acute Kidney Injury (AKI). Since much of the clinical information is contained in clinical notes that are largely unstructured text, in this paper, we present an AKI domain-specific pre-trained language model based on BERT (AKI-BERT) that could be used to mine the clinical notes for AKI early prediction. Our experiments on MIMIC-III dataset demonstrate that AKI-BERT can yield performance improvements for AKI early prediction.
Abstract Background Diabetes mellitus is a prevalent metabolic disease characterized by chronic hyperglycemia. The avalanche of healthcare data is accelerating precision and personalized medicine. Artificial intelligence and algorithm-based approaches are becoming more and more vital to support clinical decision-making. These methods are able to augment health care providers by taking away some of their routine work and enabling them to focus on critical issues. However, few studies have used predictive modeling to uncover associations between comorbidities in ICU patients and diabetes. This study aimed to use Unified Medical Language System (UMLS) resources, involving machine learning and natural language processing (NLP) approaches to predict the risk of mortality. Methods We conducted a secondary analysis of Medical Information Mart for Intensive Care III (MIMIC-III) data. Different machine learning modeling and NLP approaches were applied. Domain knowledge in health care is built on the dictionaries created by experts who defined the clinical terminologies such as medications or clinical symptoms. This knowledge is valuable to identify information from text notes that assert a certain disease. Knowledge-guided models can automatically extract knowledge from clinical notes or biomedical literature that contains conceptual entities and relationships among these various concepts. Mortality classification was based on the combination of knowledge-guided features and rules. UMLS entity embedding and convolutional neural network (CNN) with word embeddings were applied. Concept Unique Identifiers (CUIs) with entity embeddings were utilized to build clinical text representations. Results The best configuration of the employed machine learning models yielded a competitive AUC of 0.97. Machine learning models along with NLP of clinical notes are promising to assist health care providers to predict the risk of mortality of critically ill patients. Conclusion UMLS resources and clinical notes are powerful and important tools to predict mortality in diabetic patients in the critical care setting. The knowledge-guided CNN model is effective (AUC = 0.97) for learning hidden features.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)