Search

Abstract Vertebral compression fractures (VCFs) of the thoracolumbar spine are commonly caused by osteoporosis or result from traumatic events. Early diagnosis of vertebral compression fractures can prevent further damage to patients. When assessing these fractures, plain radiographs are used as the primary diagnostic modality. In this study, we developed a deep learning based fracture detection model that could be used as a tool for primary care in the orthopedic department. We constructed a VCF dataset using 487 lateral radiographs, which included 598 fractures in the L1-T11 vertebra. For detecting VCFs, Mask R-CNN model was trained and optimized, and was compared to three other popular models on instance segmentation, Cascade Mask R-CNN, YOLOACT, and YOLOv5. With Mask R-CNN we achieved highest mean average precision score of 0.58, and were able to locate each fracture pixel-wise. In addition, the model showed high overall sensitivity, specificity, and accuracy, indicating that it detected fractures accurately and without misdiagnosis. Our model can be a potential tool for detecting VCFs from a simple radiograph and assisting doctors in making appropriate decisions in initial diagnosis.

Abstract The simplified molecular-input line-entry system (SMILES) has been utilized in a variety of artificial intelligence analyses owing to its capability of representing chemical structures using line notation. However, its ease of representation is limited, which has led to the proposal of BigSMILES as an alternative method suitable for the representation of macromolecules. Nevertheless, research on BigSMILES remains limited due to its preprocessing requirements. Thus, this study proposes a conversion workflow of BigSMILES, focusing on its automated generation from SMILES representations of homopolymers. BigSMILES representations for 4,927,181 records are provided, thereby enabling its immediate use for various research and development applications. Our study presents detailed descriptions on a validation process to ensure the accuracy, interchangeability, and robustness of the conversion. Additionally, a systematic overview of utilized codes and functions that emphasizes their relevance in the context of BigSMILES generation are produced. This advancement is anticipated to significantly aid researchers and facilitate further studies in BigSMILES representation, including potential applications in deep learning and further extension to complex structures such as copolymers.

Proactive strategies for predicting solid state drive(SSD) failures are imperative to ensure uninterrupted services in data centers. Traditional methods that rely on rule-based approaches and machine learning algorithms often fail to accurately predict these failures. In this study, we introduce a temporal-contextual attention network(TCAN), a pioneering method that integrates long short-term memory(LSTM) and transformer architectures to address the limitations of existing schemes. TCAN exploits temporal patterns and attribute dependencies and offers a more comprehensive solution for SSD failure prediction. Unlike conventional feature selection methods, TCAN adopts a feature grouping approach that utilizes all available attributes while accounting for its unique characteristics. Specifically, TCAN treats certain features based on their temporal aspects, capturing how these features change over time, whereas other features are used to capture the dependencies and interactions among different attributes. Through extensive evaluation of private datasets from the Tencent data center and comparison with state-of-the-art models, including machine learning and deep learning approaches, TCAN demonstrates superior performance in identifying potential failures. Furthermore, ablation studies and evaluations using public datasets validate their effectiveness and robustness across different datasets. Our findings underscore the importance of considering both temporal features and inter-attribute dependencies for accurate SSD failure prediction, highlighting the potential of TCAN for enhancing storage system reliability and service stability in data center environments.

Screen summarization aims to generate concise textual descriptions that communicate the crucial contents and functionalities of a mobile user interface (UI) screen. A UI screen consists of objects with a hierarchical structure that are tightly interconnected, and each object contains multimodal data such as images, texts, and bounding boxes. Considering these characteristics, previous works encoded the absolute position of objects at the view hierarchy to extract the semantic representation of the UI screen. However, the importance of the hierarchical dependency between objects in the UI structure was overlooked. In this study, we propose an object-wise hierarchical dependency-based Transformer named OHiFormer. OHiFormer considers the objects on the UI screen as tokens in natural language processing and leverages the Transformer to capture the mutual relationships between objects. Moreover, OHiFormer includes a modified self-attention mechanism using structural relative position encoding to represent the hierarchically connected UI. Experimental results demonstrate that OHiFormer outperforms benchmark models in the BLEU 1, BLEU 2, BLEU 3, BLEU 4, ROUGE-L, and CIDEr metrics by 3.63%, 2.1%, 0.12%, 1.8%, 2.38%, and 17.58%, respectively, on the Screen Summarization dataset. Furthermore, our proposed UI structural representation method achieves remarkable performance on complex UIs with numerous objects compared to other structural position encoding methods. Finally, a visualization of the self-attention heatmaps demonstrates how OHiFormer reflects the hierarchical dependencies between objects. By reflecting hierarchical dependencies hidden in the visual layout of the UI, OHiFormer not only improves the quality of summaries but also offers the potential for applications in mobile apps and systems containing numerous interactive objects.

A weather forecaster predicts the weather by analyzing current weather map images generated by a satellite. In this analyzing process, the accuracy of the prediction depends highly on the forecaster’s experience which is needed to recollect similar weather maps from the past. In an attempt to help forecasters to obtain empirical data and analyze the current weather status, this paper proposes a convolutional autoencoder model to find weather maps from the past that are similar to a current weather map by extracting the latent features of each image. To measure the similarity between each pair of images, metrics including mean squared error and structural similarity were used and case studies for searching similar satellite images were conducted and visualized. The paper also demonstrates that searching similar weather maps can be useful guidance to all forecasters when analyzing and predicting the weather.

Abstract The computer-aided diagnosis (CAD) for chest X-rays was developed more than 50 years ago. However, there are still unmet needs for its versatile use in our medical fields. We planned this study to develop a multipotent CAD model suitable for general use including in primary care areas. We planned this study to solve the problem by using computed tomography (CT) scan with its one-to-one matched chest X-ray dataset. The data was extracted and preprocessed by pulmonology experts by using the bounding boxes to locate lesions of interest. For detecting multiple lesions, multi-object detection by faster R-CNN and by RetinaNet was adopted and compared. A total of twelve diagnostic labels were defined as the followings: pleural effusion, atelectasis, pulmonary nodule, cardiomegaly, consolidation, emphysema, pneumothorax, chemo-port, bronchial wall thickening, reticular opacity, pleural thickening, and bronchiectasis. The Faster R-CNN model showed higher overall sensitivity than RetinaNet, nevertheless the values of specificity were opposite. Some values such as cardiomegaly and chemo-port showed excellent sensitivity (100.0%, both). Others showed that the unique results such as bronchial wall thickening, reticular opacity, and pleural thickening can be described in the chest area. As far as we know, this is the first study to develop an object detection model for chest X-rays based on chest area defined by CT scans in one-to-one matched manner, preprocessed and conducted by a group of experts in pulmonology. Our model can be a potential tool for detecting the whole chest area with multiple diagnoses from a simple X-ray that is routinely taken in most clinics and hospitals on daily basis.

Some aspects of traditional aquaculture have negative impacts on the aquatic environment, leading to pollution and disease outbreaks in farmed organisms. Biofloc technology (BFT) is a closed aquaculture system that utilizes specific microbial communities to remove ammonia emitted from aquaculture organisms or adds carbon to the aquaculture system to improve water quality. BFT has benefits, such as increasing production and improving water quality, and reducing disease spread and pollution, without the need for water exchange. However, there are disadvantages, such as rapid changes in water quality due to accumulation of dissolved nutrients and total suspended soils (TSS) and the requirement for expensive aeration equipment to maintain dissolved oxygen. BFT can be enhanced in value and efficiency by combining it with other aquaculture technologies, such as aquaponics and vertical aquaculture to overcome the disadvantages. The integration of biofloc with technologies from the fourth industrial revolution holds potential for further development, while aquaponics and vertical farming can eliminate geographical limitations and accelerate the urbanization of aquaculture. The integration of aquaponics and vertical aquaculture with BFT has potential for development, accelerating the urbanization of aquaculture and removing geographic limitations.

Abstract Background This study aimed to compare obstetric outcomes in Korean women with and without future cardiovascular disease (CVD) within 10 years after pregnancy, and assessed whether pregnancy complications are independent risk factors, and whether the combination of pregnancy complications has an additive function for risk factors for CVD. Methods This was a nationwide population-based study combining the database of the Korea National Health Insurance claims and National Health Screening Programs to assess preeclampsia, low birth weight (LBW), and preterm delivery as risk factors for CVD. Cox proportional hazards models was used to evaluate the risk of total CVD, ischemic heart disease (IHD), and stroke after the pregnancy complications, with adjustment for potential confounding variables. Results Women with CVD were likely to have a higher prevalence of pregnancy complications than women without CVD. The risk of total CVD was associated with preeclampsia (adjusted hazard ratio (HR), 1.60 [95% confidence interval (CI) 1.50–1.72]), LBW (1.20 [1.12–1.28]), and preterm delivery (1.32 [1.22–1.42]), after adjustment for confounders, including cardiovascular risk factors before pregnancy. The risk estimates of pregnancy complications for IHD were higher than those for stroke. In this study, the risk of total CVD was higher in the combined presence of preeclampsia and preterm delivery (2.23 [1.57–3.17] or all three complications (2.06 [1.76–2.40]), relative to no complications. The highest HR was noted in the risk of all pregnancy complications for IHD (2.39 [1.98–2.89]). Conclusion Preeclampsia, preterm delivery, and LBW were independently associated with CVD in young Korean women. In addition, the combination of pregnancy complications had less-than-additive effects on CVD incidence.

Reliability prediction has been studied in many industries for managing stocks and reducing quality assurance costs and production costs. Particularly, in the automotive industry, reliability prediction is performed based on two automobile reliability perspectives, time and mileage. To maximize cost savings, researchers attempted reliability prediction with short-term inputs. However, limited information on short-term inputs resulted in unsatisfactory prediction results for the long warranty periods. Additionally, the overall evaluation metrics could not reflect the pattern-wise performance, such as the increasing failure patterns. This study proposes Complementary Reliability perspective Transformer (CRFormer) based on Transformer encoder to achieve enriched representations from a short-term input sequence. CRFormer fuses different automobile reliability perspective information and automobile features to compensate for the limited information on short-term input. The performance of CRFormer is evaluated based on automobile claim data accumulated over 16 years. Results showed that compared to previous methods in terms of overall, pattern-wise, and pattern similarity evaluation metrics, CRFormer achieved outstanding performance in time and mileage reliability prediction. Lastly, visualization results and survival analysis based on accurate model prediction can be used to support decision-making to reduce quality assurance costs and production costs.

For an unpaired image-to-image translation to work effectively, the latent space of each image domain must be well-designed. The codes of each style must be translated toward the target while preserving the parts corresponding to the source content. In general, most Variational Autoencoder (VAE)-based models use a one-dimensional latent space. However, to apply high dimensional methodologies such as vector quantization, controlling a multidimensional latent space is necessary. In this study, among the VAE-based models that use relatively complex multidimensional latent spaces, we apply an Energy-Based Model and Vector-Quantized VAE v2, with the latter as the main model. We show that among the latent spaces that represent each image domain, the importance of each feature at the top and bottom latent spaces must be interpreted differently for appropriate translation. Therefore, we argue that simply understanding the features of latent space composition well can show effective image translation results. We also present various analyses and visual outcomes of multidimensional latent space transport.

Abstract Background Multiple gestations are associated with an increased incidence of preeclampsia. However, there exists no evidence for an association between multiple gestations and development of hypertension(HTN) later in life. This study aimed to determine whether multiple gestations are associated with HTN beyond the peripartum period. Methods In this retrospective nationwide population-based study, women who delivered a baby between January 1, 2007, and December 31, 2008, and underwent a national health screening examination within one year prior to their pregnancy were included. Subsequently, we tracked the occurrence of HTN during follow-up until December 31, 2015, using International Classification of Diseases-10th Revision codes. Results Among 362,821 women who gave birth during the study period, 4,944 (1.36%) women had multiple gestations. The cumulative incidence of HTN was higher in multiple gestations group compared with singleton group (5.95% vs. 3.78%, p

Abstract Beta-2 adrenergic receptor (B2AR) agonists, used as asthma treatments and tocolytics during pregnancy, have recently been reported to be associated with autism in their offspring. However, the particular link between autism and ritodrine, a common type of B2AR agonist used solely as tocolytics, has never been substantiated with any nationwide database. Thus, we aimed to examine the association between in utero exposure of ritodrine and the risk of autism in their offspring using a national database. This population-based cohort study was conducted by merging the Korea National Health Insurance claims database and National Health Screening Program for Infants and Children database. These databases included all women who had delivered singleton between January 2007 and December 2008 in Korea. Out of the total 770,016 mothers, 30,959 (4.02%) were exposed to ritodrine during pregnancy, and 5583 (0.73%) of their children were identified as having autism, defined until 8 years of age. According to our analysis, the overall cumulative incidence of autism up to 8 years was 1.37% in ritodrine exposure group and 0.70% in ritodrine non-exposure group (p

Abstract Background Pregnant women are at high risk of influenza-related morbidity and mortality. In addition, maternal influenza infection may lead to adverse birth outcomes. However, there is insufficient data on long-term impact of maternal influenza infection. Methods This study was conducted to assess the impact of maternal influenza infection on birth outcomes and long-term influence on infants by merging the Korea National Health Insurance (KNHI) claims database and National Health Screening Program for Infants and Children (NHSP-IC). Mother-offspring pairs were categorized by maternal influenza infection based on the ICD-10 code. Results Multivariate analysis revealed that maternal influenza infection significantly increased the risk of preterm birth (OR 1.408) and low birth weight (OR 1.198) irrespective of gestational age. The proportion of low birth weight neonates was significantly higher in influenza-infected women compared to those without influenza. However, since the fourth health screening (30–80 months after birth), the fraction of underweight was no longer different between children from influenza-infected and non-infected mothers, whereas the rates of overweight increased paradoxically in those born to mothers with influenza infection. Conclusions Maternal influenza infection might have long-term effects on the health of children and adolescents even after infancy.

Objectives The current study aimed to investigate whether pregnancy outcomes are affected by maternal rhesus (Rh) status by comparing the primigravida pregnancy outcomes of Rh-negative women with those of Rh-positive women. Methods The study data were collected from the Korea National Health Insurance Claims Database and the National Health Screening Program for Infants and Children. In total, 1,664,882 primigravida women who gave birth between January 1, 2007 and December 31, 2014, were enrolled in this study. As the risk and severity of sensitization response increases with each subsequent pregnancy, only primigravida women were enrolled. The patients were divided into 2 groups according to Rh status, and the pregnancy outcomes were compared. Results In total, 1,661,320 women in the Rh-positive group and 3,290 in the Rh-negative group were assessed. With regard to adverse pregnancy outcomes, there was no statistically significant difference between the 2 groups in terms of the prevalence of preeclampsia, postpartum hemorrhage, abruptio placenta, placenta previa, and uterine artery embolization. A univariate analysis revealed that none of the adverse pregnancy outcomes were significantly correlated to Rh status (preeclampsia: odds ratio [OR], 1.00, 95% confidence interval [CI], 0.81–1.23; postpartum hemorrhage: OR, 1.10, 95% CI, 0.98–1.24; abruptio placenta: OR, 0.80, 95% CI, 0.46–1.37; and placenta previa: OR, 1.08, 95% CI, 0.78–1.42). The adjusted ORs of postpartum hemorrhage and preterm birth did not significantly differ. Conclusion Maternal Rh status is not associated with adverse outcomes in primigravida women.

Objectives. Prognosticating idiopathic sudden sensorineural hearing loss (ISSNHL) is an important challenge. In our study, a dataset was split into training and test sets and cross-validation was implemented on the training set, thereby determining the hyperparameters for machine learning models with high test accuracy and low bias. The effectiveness of the following five machine learning models for predicting the hearing prognosis in patients with ISSNHL after 1 month of treatment was assessed: adaptive boosting, K-nearest neighbor, multilayer perceptron, random forest (RF), and support vector machine (SVM). Methods. The medical records of 523 patients with ISSNHL admitted to Korea University Ansan Hospital between January 2010 and October 2017 were retrospectively reviewed. In this study, we analyzed data from 227 patients (recovery, 106; no recovery, 121) after excluding those with missing data. To determine risk factors, statistical hypothesis tests (e.g., the two-sample t-test for continuous variables and the chi-square test for categorical variables) were conducted to compare patients who did or did not recover. Variables were selected using an RF model depending on two criteria (mean decreases in the Gini index and accuracy). Results. The SVM model using selected predictors achieved both the highest accuracy (75.36%) and the highest F-score (0.74) on the test set. The RF model with selected variables demonstrated the second-highest accuracy (73.91%) and F-score (0.74). The RF model with the original variables showed the same accuracy (73.91%) as that of the RF model with selected variables, but a lower F-score (0.73). All the tested models, except RF, demonstrated better performance after variable selection based on RF. Conclusion. The SVM model with selected predictors was the best-performing of the tested prediction models. The RF model with selected predictors was the second-best model. Therefore, machine learning models can be used to predict hearing recovery in patients with ISSNHL.

It is essential for seamlessly delivering intended hand motion to surgical robots while actively suppressing undesired hand tremor during microsurgery. To achieve this goal, we propose a novel method for predicting voluntary motion based on deep learning with the signal decomposition and ensemble approach. This approach can thus deal with various forms of voluntary signals, such as either highly stationary or rather highly cyclic at a low range of frequencies. The proposed method comprises a series of signal blocks to decompose complex hand motion into multiple sub-signals using deep neural networks upon their signal characteristics. The signal block yields parameterized sub-signal and predicted voluntary motion. In addition, an ensemble layer allows for accurately predicting future voluntary motion by combining predicted motion from each signal block with the optimal weight. These signal blocks are connected by a decomposition flow in series and also by a forecast flow in parallel to ensemble the prediction output of each block. Given real data sets, we evaluated the prediction performance of the proposed algorithm compared to other data-driven deep learning models. The generalizability of the proposed algorithm was also investigated by applying the trained models to new data sets from new tasks and a different subject, which had not been involved in training procedures. As a result, the proposed algorithm outperforms the other baseline models in terms of prediction error and accuracy. Furthermore, we explored whether the proposed method could suppress tremor via spectral analysis, which shows substantial tremor attenuation more than -10 dB in a frequency of interest, 6-14 Hz. It is also found that the proposed method has the predictive power for dealing with inevitable control delays, where prediction error increased only by 2% per one-time sample, approximately 4.2 ms.

The proportion of the inventory range associated with spare parts is often considered in the industrial context. Therefore, even minor improvements in forecasting the demand for spare parts can lead to substantial cost savings. Despite notable research efforts, demand forecasting remains challenging, especially in areas with irregular demand patterns, such as military logistics. Thus, an advanced model for accurately forecasting this demand was developed in this study. The K-X tank is one of the Republic of Korea Army’s third generation main battle tanks. Data about the spare part consumption of 1,053,422 transactional data points stored in a military logistics management system were obtained. Demand forecasting classification models were developed to exploit machine learning, stacked generalization, and time series as baseline methods. Additionally, various stacked generalizations were established in spare part demand forecasting. The results demonstrated that a suitable selection of methods could help enhance the performance of the forecasting models in this domain.

Abstract Background Obstetric hemorrhage is one of the most common causes of obstetrical morbidity and mortality, and transfusion is the most important management for hemorrhage. The aim of our study was to investigate the pre-pregnancy and pregnancy risk factors for peripartum transfusion. Methods Women who delivered a baby from 2010 to 2014 in Korea and participated in the Korean National Health Screening Program for Infants and Children were included. To analyze pre-pregnant risk factors for peripartum transfusion, an additional analysis was done for women who underwent a National Health Screening Examination within 1 year before pregnancy, including maternal waist circumference, body mass index, blood pressure, laboratory tests and history of smoking. Multivariable logistic regression analysis was used to estimate the risk factors for peripartum transfusion. Results Of the total 1,980,126 women who met the inclusion criteria, 36,868 (1.86%) were transfused at peripartum. In a multivariable regression model, the pregnancy risk factors for peripartum transfusion included maternal age above 35 years [odds ratio (OR): 1.41; 95% confidence interval (CI): 1.32–1.50], preterm birth (OR: 2.39; 95% CI: 2.15–2.65), and maternal hypertension (OR: 2.49; 95% CI: 2.24–2.77). Pre-pregnancy risk factors including fasting glucose level of more than 126 mg/dL (OR: 1.11; 95% CI: 1.02–1.20), current-smoker status (OR: 1.20; 95% CI: 1.06–1.37), and waist-circumference less than 80 cm (OR: 1.18; 95% CI: 1.06–1.30) were independently associated with peripartum blood transfusion. Conclusions Several pre-pregnancy and pregnancy risk factors were associated with peripartum blood transfusion. Some identified factors are modifiable before conception, and our study validated peripartum blood transfusion as a form of triage.

Introduction: Acute pyelonephritis (APN) is a common infection during pregnancy that increases the risk of unfavorable maternal and fetal outcomes. However, it has not been clearly elucidated which demographic and clinical characteristics are associated with the incidence of APN during pregnancy. Objective: This population-based cohort study aimed to determine the risk factors for APN during pregnancy. Methods: Using the database of the Health Insurance Review and Assessment Service of South Korea, we enrolled Korean women who delivered infants between 2010 and 2014 in Korea and had complete health examination records within 1 year of pregnancy. We performed multivariate logistic regression analysis to evaluate the risk factors for APN during pregnancy. Results: Of 370,248 women, 2,526 (0.7% of the total participants) were treated for APN while in hospitalization during pregnancy. Younger age, history of previous APN within 1 year of pregnancy, and abnormal results of health examination before pregnancy, such as high fasting glucose level (>100 mg/dL) and proteinuria, were associated with an increased risk of APN during pregnancy. Conclusion: Certain maternal demographic and clinical characteristics were associated with the incidence of APN during pregnancy, and these should be monitored closely during antenatal care.

Colonoscopy is an effective method for detecting polyps to prevent colon cancer. Existing studies have achieved satisfactory polyp detection performance by aggregating low-level boundary and high-level region information in convolutional neural networks (CNNs) for precise polyp segmentation in colonoscopy images. However, multi-level aggregation provides limited polyp segmentation owing to the distribution discrepancy that occurs when integrating different layer representations. To address this problem, previous studies have employed complementary low- and high- level representations. In contrast to existing methods, we focus on propagating complementary information such that the complementary low-level explicit boundary with abstracted high-level representations diminishes the discrepancy. This study proposes COMMA, which propagates complementary multi-level aggregation to reduce distribution discrepancies. COMMA comprises a complementary masking module (CMM) and a boundary propagation module (BPM) as a multi-decoder. The CMM masks the low-level boundary noises through the abstracted high-level representation and leverages the masked information at both levels. Similarly, the BPM incorporates the lowest- and highest-level representations to obtain explicit boundary information and propagates the boundary to the CMMs to improve polyp detection. CMMs can discriminate polyps more elaborately than prior CMMs based on boundary and complementary representations. Moreover, we propose a hybrid loss function to mitigate class imbalance and noisy annotations in polyp segmentation. To evaluate the COMMA performance, we conducted experiments on five benchmark datasets using five metrics. The results proved that the proposed network outperforms state-of-the-art methods in terms of all datasets. Specifically, COMMA improved mIoU performance by 0.043 on average for all datasets compared to the existing state-of-the-art methods.

Abstract Background A recent concept is that obesity, assessed by body mass index (BMI), is not always a sign of poor health. Thus, in order to use obesity metrics in clinical decision making, it is important to clarify the relationship between waist circumference (WC), a proxy for abdominal obesity, and mortality. Methods Data were used from 8,796,759 subjects aged between 30 and 90 years, who had participated in the Korea National Health Screening Examination between January 1, 2009 and December 31, 2009 and survived at least 1 year post screening. Data from a mean follow-up time of an additional 5.3 years (time at risk) were analyzed for the relationship between WC and mortality according to age, sex, and BMI category. Results An increased WC of more than 90 cm in men and 85 cm in women showed a definite negative influence on mortality. However, the detailed relationship between WC and mortality was J-shaped or U-shaped according to age, sex, and BMI category. In the normal BMI group, the optimal WC range with the lowest mortality was

An accurate vessel fuel consumption prediction is essential for constructing a ship route network and vessel management, leading to efficient sailings. Besides, ship data from monitoring and sensing systems accelerate fuel consumption prediction research. However, the ship data consist of three properties: sequential, irregular time interval, and feature importance, making the predicting problem challenging. In this paper, we propose Time-aware Attention (TA) and Feature-similarity Attention (FA) applied to bi-directional Long Short-Term Memory (LSTM). TA acquires time importance by nonlinear function from irregular time intervals in each sequence and emphasizes data depending on the importance. FA emphasizes data based on similarities of features in the sequence by estimating feature importance with learnable parameters. Finally, we propose the ensemble model of TA and FA-based BiLSTM. The ensemble model, which consists of fully connected layers, is capable of simultaneously capturing different properties of ship data. The experimental results on ship data showed that the proposed model improves the performance in predicting fuel consumption. In addition to model performance, visualization results of attention maps and feature importance help to understand data properties and model characteristics.

OBJECTIVE:By identifying pregnancy-related risk factors for endometrial neoplasia, women's risk of developing this disease after childbirth can be predicted and high-risk women can be screened for early detection. METHODS:Study data from women who gave birth in Korea in 2007 were collected from the Korea National Health Insurance (KNHI) claims database between 2007 and 2015. The adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) for the development of endometrial neoplasia were estimated by multivariate Cox proportional hazards models. RESULTS:Data from 386,614 women were collected for this study. By 2015, 3,370 women from the initial cohort had been diagnosed with endometrial neoplasia secondary to delivery. Multivariate Cox proportional hazards regression revealed that preeclampsia (HR 1.55, 95% CI 1.29, 1.86), advanced maternal age (≥ 35; HR 1.52, 95% CI 1.39, 1.66), multifetal pregnancy (HR 1.81, 95% CI 1.46, 2.23), multiparity (HR 1.16, 95% CI 1.08, 1.24), cesarean section (HR 1.15, 95% CI 1.07, 1.23) and delivery of a large-for-gestational-age infant (HR 1.19, 95% CI 1.02, 1.39) were independent risk factors for future endometrial neoplasia. The risk for endometrial neoplasia increased as the number of risk factors increased (risk factors ≥3: HR 2.11, 95% CI 1.86-2.40). CONCLUSION:This study showed that six pregnancy-related factors-advanced maternal age, multiparity, multifetal pregnancy, cesarean section, delivery of a large-for-gestational-age infant, and preeclampsia-are positively correlated with future development of endometrial neoplasia, including endometrial hyperplasia or cancer. Close observation and surveillance are warranted to enable early diagnosis of endometrial diseases, including endometrial cancer after pregnancy in high-risk women. However, due to unavailability of clinical information, many clinical/epidemiological factors can become confounders. Further research is needed on factors associated with the risk of endometrial neoplasia.

[This corrects the article DOI: 10.1371/journal.pone.0214600.].

Hyperemesis gravidarum is known to be associated with poor perinatal outcomes. This study aimed to identify pre-pregnancy risk factors for hospital admission in women with hyperemesis gravidarum. We enrolled women who had delivered between 1 January 2013 and 31 December 2015, and had undergone a national health screening examination through the National Health Insurance Corporation 1–2 years before their first delivery. Multiple logistic regression analysis was performed to estimate the risk factors for hospital admission due to hyperemesis gravidarum. Of the 216,373 study participants with hyperemesis gravidarum, 2210 (1.02%) pregnant women were hospitalized. These women had lower waist circumference and were underweight based on body mass index compared to pregnant women who did not require hospitalization due to hyperemesis gravidarum. On multivariate analysis, primiparity, multiple pregnancies, female fetus, alcohol consumption, and pre-pregnancy underweight status were associated with an increased risk of hospitalization due to the condition. In this population-based cohort study, we found that hospitalization due to hyperemesis gravidarum was associated with pre-pregnancy lifestyle characteristics. Early recognition and management of these pre-pregnancy factors may help control the need for hospitalization in women with the condition in subsequent pregnancies.

Recently, a number of data analysists have suffered from an insufficiency of historical observations in many real situations. To address the insufficiency of historical observations, self-starting forecasting process can be used. A self-starting forecasting process continuously updates the base models as new observations are newly recorded, and it helps to cope with inaccurate prediction caused by the insufficiency of historical observations. This study compared the properties of several exponentially weighted moving average methods as base models for the self-starting forecasting process. Exponentially weighted moving average methods are the most widely used forecasting techniques because of their superior performance as well as computational efficiency. In this study, we compared the performance of a self-starting forecasting process using different existing exponentially weighted moving average methods under various simulation scenarios and real case datasets. Through this study, we can provide the guideline for determining which exponentially weighted moving average method works best for the self-starting forecasting process.

Previous reports have demonstrated a role for hedgehog signaling in melanoma progression, prompting us to explore the therapeutic benefit of targeting this pathway in melanoma. We profiled a panel of human melanoma cell lines and control melanocytes for altered expression of hedgehog pathway members and determined the consequences of both genetic and pharmacological inhibition of the hedgehog pathway activator Smoothened (SMO) in melanoma, both in vitro and in vivo. We also examined the relationship between altered expression of hedgehog pathway mediators and survival in a well-characterized cohort of metastatic melanoma patients with prospectively collected follow up information. Studies revealed that over 40% of the melanoma cell lines examined harbored significantly elevated levels of the hedgehog pathway mediators SMO, GLI2, and PTCH1 compared to melanocytes (p < 0.05). SMO inhibition using siRNA and the small molecule inhibitor, NVP-LDE-225, suppressed melanoma growth in vitro, particularly in those cell lines with moderate SMO and GLI2 expression. NVP-LDE-225 also induced apoptosis in vitro and inhibited melanoma growth in a xenograft model. Gene expression data also revealed evidence of compensatory up-regulation of two other developmental pathways, Notch and WNT, in response to hedgehog pathway inhibition. Pharmacological and genetic SMO inhibition also downregulated genes involved in human embryonic stem cell pluripotency. Finally, increased SMO expression and decreased expression of the hedgehog pathway repressor GLI3 correlated with shorter post recurrence survival in metastatic melanoma patients. Our data demonstrate that hedgehog pathway inhibition might be a promising targeted therapy in appropriately selected metastatic melanoma patients.