Automatic Classification of Thyroid Findings Using Static and Contextualized Ensemble Natural Language Processing Systems: Development Study.

BACKGROUND: In the case of Korean institutions and enterprises that collect nonstandardized and nonunified formats of electronic medical examination results from multiple medical institutions, a group of experienced nurses who can understand the results and related contexts initially classified the reports manually. The classification guidelines were established by years of workers' clinical experiences and there were attempts to automate the classification work. However, there have been problems in which rule-based algorithms or human labor-intensive efforts can be time-consuming or limited owing to high potential errors. We investigated natural language processing (NLP) architectures and proposed ensemble models to create automated classifiers. OBJECTIVE: This study aimed to develop practical deep learning models with electronic medical records from 284 health care institutions and open-source corpus data sets for automatically classifying 3 thyroid conditions: healthy, caution required, and critical. The primary goal is to increase the overall accuracy of the classification, yet there are practical and industrial needs to correctly predict healthy (negative) thyroid condition data, which are mostly medical examination results, and minimize false-negative rates under the prediction of healthy thyroid conditions. METHODS: The data sets included thyroid and comprehensive medical examination reports. The textual data are not only documented in fully complete sentences but also written in lists of words or phrases. Therefore, we propose static and contextualized ensemble NLP network (SCENT) systems to successfully reflect static and contextual information and handle incomplete sentences. We prepared each convolution neural network (CNN)-, long short-term memory (LSTM)-, and efficiently learning an encoder that classifies token replacements accurately (ELECTRA)-based ensemble model by training or fine-tuning them multiple times. Through comprehensive experiments, we propose 2 versions of ensemble models, SCENT-v1 and SCENT-v2, with the single-architecture-based CNN, LSTM, and ELECTRA ensemble models for the best classification performance and practical use, respectively. SCENT-v1 is an ensemble of CNN and ELECTRA ensemble models, and SCENT-v2 is a hierarchical ensemble of CNN, LSTM, and ELECTRA ensemble models. SCENT-v2 first classifies the 3 labels using an ELECTRA ensemble model and then reclassifies them using an ensemble model of CNN and LSTM if the ELECTRA ensemble model predicted them as "healthy" labels. RESULTS: SCENT-v1 outperformed all the suggested models, with the highest F1 score (92.56%). SCENT-v2 had the second-highest recall value (94.44%) and the fewest misclassifications for caution-required thyroid condition while maintaining 0 classification error for the critical thyroid condition under the prediction of the healthy thyroid condition. CONCLUSIONS: The proposed SCENT demonstrates good classification performance despite the unique characteristics of the Korean language and problems of data lack and imbalance, especially for the extremely low amount of critical condition data. The result of SCENT-v1 indicates that different perspectives of static and contextual input token representations can enhance classification performance. SCENT-v2 has a strong impact on the prediction of healthy thyroid conditions.

Molecular Characteristics of Light Cycle Oil Hydrodesulfurization over Silica-Alumina-Supported NiMo Catalysts.

A detailed understanding of the catalytic upgrading of light cycle oil (LCO) is important to achieve effective deep hydrodesulfurization (HDS) when LCO is mixed with straight run gas oil in the diesel pool. Herein, HDS of polyaromatic-rich LCO was studied at the molecular level over three NiMo catalysts on silica-alumina supports, which were synthesized on the pilot scale using different silica/alumina mixing procedures. Gas chromatography with atomic emission detection and two-dimensional gas chromatography with time-of-flight mass spectrometry were used to evaluate the HDS performance through determining the feed and product compositions, respectively, at the molecular level. Furthermore, the textural properties of the catalysts were evaluated using Raman spectroscopy, transmission electron microscopy, and the temperature-programmed desorption of NH3. The performance of the best catalyst was attributed to its higher content of octahedrally coordinated Mo oxide species, a lower number of layered stacks, and the more acidic sites on the surface. In addition, the hydrotreating reactivity of various family groups in LCO over the catalyst was investigated.

Epidemiology of violence in pediatric and adolescent nasal fracture compared with adult nasal fracture: An 8-year study.

BACKGROUND: The epidemiology of nasal fractures varies according to factors such as the era and area of the study, as well as the age of the patient. We compared the characteristics and causes of pediatric nasal fractures. METHODS: A total of 2,321 patients with nasal fractures from 2010 to 2017 were examined. The patients were divided into age groups using the Korean school system of age classification. The causes of injury were divided into five groups: violence, fall or slip down, sports, road traffic accidents, and others. Fractures were classified using the Stranc and Robertson standard: vector of force and plane of fracture. RESULTS: Violence was the most common cause of nasal fracture in patients older than 12 years. Violence was a significantly less frequent cause among patients younger than 12 years old than among adolescent and adult patients. Nasal fractures due to violence were not observed in patients younger than 10 years. Plane 2 and lateral force fractures were the most common; however, in patients younger than 12 years, frontal force fractures were significantly more frequent than were lateral force fractures. CONCLUSION: As children may simply be injured due to a fall or slip down, it is important for the parents and guardians to ensure their safety. As they become older, children should abstain from violence and be monitored. It is therefore very important to ensure that the environment is free of violence in order to prevent such injuries.

Correlation Between Soft Tissue Injury and the Type of Nasal Fracture Based on Stranc-Robertson Classification.

Nasal fractures are the most common facial bone fractures, and soft tissue injuries are frequently accompanied. This study intends to make a deep analysis on the relationship between the 2.Patients diagnosed with nasal fracture between 2015 and 2017 were included. Patients younger than 17 years and those with previous facial fractures or aesthetic surgeries were excluded. Nasal fractures were classified according to the Stranc-Robertson (S-R) classification, and the severity of soft tissue injury was evaluated by length and depth. The authors compared the frequency of soft tissue injury between frontal and lateral groups. Second, the authors investigated whether the incidence of soft tissue injuries increases as a function of the increase in the S-R classification both in frontal and lateral group (from plane I to III). The authors also analyzed the difference in severity of soft tissue injuries in each group. Pearson chi-square analysis, linear by linear and Jonckheere-Terpstra tests were used for statistical analysis.Of 621 patients, 296 were frontal plane and 325 were lateral plane. The frontal group had a higher incidence of soft tissue injury than the lateral group (P = 0.004). The incidence of soft tissue injury and severity by depth increased as a function of the increase in the S-R classification only in the frontal group (P = 0.046, 0.019).In nasal fractures, frontal impact is more associated with frequency and severity of soft tissue injury than lateral impact. This seems to be related to the anatomical characteristics of nasal area and mechanism of injuries in each group.

Application of a paste-type acellular dermal matrix for coverage of chronic ulcerative wounds.

BACKGROUND: Chronic wounds occur due to failure of the normal healing process, associated with a lack of deposition of cellular components and a suitable microenvironment such as the extracellular matrix (ECM). Acellular dermal matrix (ADM) is viewed as an ECM substitute, and a paste-type ADM has recently been introduced. We hypothesized that CGPaste, an injectable paste-type ADM, could serve as a scaffold and promote wound healing. METHODS: We retrospectively studied seven patients in whom CGPaste was applied between 2017 and 2018, who had pressure ulcers, necrotizing fasciitis, diabetic foot ulcers, traumatic defects, and osteomyelitis. The goal of applying CGPaste was to achieve complete wound healing with re-epithelialization or growth of granulation tissue, depending upon the wound bed status. CGPaste was injected based on the wound size along with the application of a dressing. RESULTS: Four of the seven patients showed granulation tissue on their wound bed, while the other three patients had a bony wound bed. The mean wound area was 453.57 mm2 and the depth was 10.71 mm. Wound healing occurred in five of the seven patients (71.43%). The mean duration of complete healing was 2.4 weeks. Two patients showed failure due to paste absorption (29.57%); these patients had wound beds comprising bone with relatively large and deep wounds (40×30 and 30×20 mm2 in area and 15 and 10 mm in depth). CONCLUSIONS: CGPaste is an effective option for coverage of small and deep chronic wounds for which a flap operation or skin grafting is unfeasible.

Correlation Between the Existing Classifications of Nasal Bone Fractures and Subjective Patient Satisfaction.

Since the nose is at the center of the face, small changes to it can cause a big overall change. Therefore, a nasal fracture needs to be operated on when deformity is expected. Although many taxonomies have been developed for nasal bone fractures, no study has aimed to predict individual patient satisfaction. Herein, the authors tried to determine any correlation between the existing classifications of nasal bone fractures and subjective patient satisfaction. A retrospective study and telephone survey were conducted in 149 patients who underwent closed reduction for a pure nasal bone fracture. Pretraumatic, prereduction, and postoperative patient satisfactions were measured on a numerical scale from 1 to 5. The difference between pretraumatic and prereduction satisfactions was calculated to confirm the change in short-term satisfaction after trauma. The difference between pretraumatic and preoperative satisfactions was measured to determine change in long-term satisfaction postoperatively. The Stranc Robertson classification, modified Murray classification, and the presence of septal fracture were used to classify fractures. Independent and Jonckheere-Terpstra t tests were used in statistical analysis. Only 86 of 149 were included in the study. There was no significant difference in patient satisfaction among frontal/lateral (P = 0.70, 0.56), frontal I/II (P = 1.00, 0.24), and lateral I/II groups (P = 0.57, 0.67) according to the Stranc Robertson classification. Septal fracture (P = 0.21, 0.44) and the modified Murray classification (P = 0.14, 0.47) also had no effect on satisfaction. Existing classification systems have the advantage of reflecting and distinguishing the characteristics of fractures, but there is a limit in their ability to reflect subjective patient satisfaction.

Characteristics of nano-sized (Pb, La)TiO3 powder synthesized at room temperature.

We synthesized nano-sized (Pb, La)TiO3 powder using a high energy mechano-chemical technique at room temperature. By the results, nano-sized (Pb, La)TiO3 powder with perovskite structure was successfully synthesized from an oxide mixture using a high energy mechano-chemical technique without any post-annealing. The mechanically-synthesized (Pb, La)TiO3 powder consisted of nanometer sized particles and had very high homogeneity. According to increase of milling time, source phases such as Pb oxides and TiO2 disappeared and the perovskite PLT phase was formed by chemical reaction and the release of OH group.