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.

ECG-ViEW II, a freely accessible electrocardiogram database.

The Electrocardiogram Vigilance with Electronic data Warehouse II (ECG-ViEW II) is a large, single-center database comprising numeric parameter data of the surface electrocardiograms of all patients who underwent testing from 1 June 1994 to 31 July 2013. The electrocardiographic data include the test date, clinical department, RR interval, PR interval, QRS duration, QT interval, QTc interval, P axis, QRS axis, and T axis. These data are connected with patient age, sex, ethnicity, comorbidities, age-adjusted Charlson comorbidity index, prescribed drugs, and electrolyte levels. This longitudinal observational database contains 979,273 electrocardiograms from 461,178 patients over a 19-year study period. This database can provide an opportunity to study electrocardiographic changes caused by medications, disease, or other demographic variables. ECG-ViEW II is freely available at http://www.ecgview.org.

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.