Conditional autoencoder asset pricing models for the Korean stock market.

This study analyzes the explanatory power of the latent factor conditional asset pricing model for the Korean stock market using an autoencoder. The autoencoder is a type of neural network in machine learning that can extract latent factors. Specifically, we apply the conditional autoencoder (CA) model that estimates factor exposure as a flexible nonlinear function of covariates. Our main findings are as follows. The CA model showed excellent explanatory power not only in the entire sample but also in several subsamples in the Korean market. Also, because of this explanatory power, it can better explain market anomalies compared to the traditional asset pricing models. As a result of examining investment strategies using pricing error, the CA model measures the expected return of stocks better than the traditional asset pricing model. In addition, the CA model indicates that the firm characteristic variables are important in asset pricing conditional on macro-financial states, such as the global financial crisis and the coronavirus disease 2019 pandemic. The result shows that the major variables considered in the explanation of stock returns through the CA model may vary depending on the time. This is expected to provide a broader perspective on asset pricing through the CA model in the future.

Effects of Cyanobacterial Harmful Algal Bloom Toxin Microcystin-LR on Gonadotropin-Dependent Ovarian Follicle Maturation and Ovulation in Mice.

BACKGROUND: Cyanobacterial harmful algal blooms (CyanoHABs) originate from the excessive growth or bloom of cyanobacteria often referred to as blue-green algae. They have been on the rise globally in both marine and freshwaters in recently years with increasing frequency and severity owing to the rising temperature associated with climate change and increasing anthropogenic eutrophication from agricultural runoff and urbanization. Humans are at a great risk of exposure to toxins released from CyanoHABs through drinking water, food, and recreational activities, making CyanoHAB toxins a new class of contaminants of emerging concern. OBJECTIVES: We investigated the toxic effects and mechanisms of microcystin-LR (MC-LR), the most prevalent CyanoHAB toxin, on the ovary and associated reproductive functions. METHODS: Mouse models with either chronic daily oral or acute intraperitoneal exposure, an engineered three-dimensional ovarian follicle culture system, and human primary ovarian granulosa cells were tested with MC-LR of various dose levels. Single-follicle RNA sequencing, reverse transcription-quantitative polymerase chain reaction, enzyme-linked immunosorbent assay, western blotting, immunohistochemistry (IHC), and benchmark dose modeling were used to examine the effects of MC-LR on follicle maturation, hormone secretion, ovulation, and luteinization. RESULTS: Mice exposed long term to low-dose MC-LR did not exhibit any differences in the kinetics of folliculogenesis, but they had significantly fewer corpora lutea compared with control mice. Superovulation models further showed that mice exposed to MC-LR during the follicle maturation window had significantly fewer ovulated oocytes. IHC results revealed ovarian distribution of MC-LR, and mice exposed to MC-LR had significantly lower expression of key follicle maturation mediators. Mechanistically, in both murine and human granulosa cells exposed to MC-LR, there was reduced protein phosphatase 1 (PP1) activity, disrupted PP1-mediated PI3K/AKT/FOXO1 signaling, and less expression of follicle maturation-related genes. DISCUSSION: Using both in vivo and in vitro murine and human model systems, we provide data suggesting that environmentally relevant exposure to the CyanoHAB toxin MC-LR interfered with gonadotropin-dependent follicle maturation and ovulation. We conclude that MC-LR may pose a nonnegligible risk to women's reproductive health by heightening the probability of irregular menstrual cycles and infertility related to ovulatory disorders. https://doi.org/10.1289/EHP12034.

Fully Automated Segmentation Models of Supratentorial Meningiomas Assisted by Inclusion of Normal Brain Images.

To train an automatic brain tumor segmentation model, a large amount of data is required. In this paper, we proposed a strategy to overcome the limited amount of clinically collected magnetic resonance image (MRI) data regarding meningiomas by pre-training a model using a larger public dataset of MRIs of gliomas and augmenting our meningioma training set with normal brain MRIs. Pre-operative MRIs of 91 meningioma patients (171 MRIs) and 10 non-meningioma patients (normal brains) were collected between 2016 and 2019. Three-dimensional (3D) U-Net was used as the base architecture. The model was pre-trained with BraTS 2019 data, then fine-tuned with our datasets consisting of 154 meningioma MRIs and 10 normal brain MRIs. To increase the utility of the normal brain MRIs, a novel balanced Dice loss (BDL) function was used instead of the conventional soft Dice loss function. The model performance was evaluated using the Dice scores across the remaining 17 meningioma MRIs. The segmentation performance of the model was sequentially improved via the pre-training and inclusion of normal brain images. The Dice scores improved from 0.72 to 0.76 when the model was pre-trained. The inclusion of normal brain MRIs to fine-tune the model improved the Dice score; it increased to 0.79. When employing BDL as the loss function, the Dice score reached 0.84. The proposed learning strategy for U-net showed potential for use in segmenting meningioma lesions.

Prediction of 6-Month Mortality Using Pre-Extracorporeal Membrane Oxygenation Lactate in Patients with Acute Coronary Syndrome Undergoing Veno-Arterial-Extracorporeal Membrane Oxygenation.

BACKGROUND: The effectiveness of extracorporeal membrane oxygenation (ECMO) for patients with refractory cardiogenic shock or cardiac arrest is being established, and serum lactate is well known as a biomarker of end-organ perfusion. We evaluated the efficacy of pre-ECMO lactate for predicting 6-month survival in patients with acute coronary syndrome (ACS) undergoing ECMO. METHODS: We reviewed the medical records of 148 patients who underwent veno-arterial (VA) ECMO for ACS between January 2015 and June 2020. These patients were divided into survivors and non-survivors based on 6-month survival. All clinical data before and during ECMO were compared between the 2 groups. RESULTS: Patients' mean age was 66.0±10.5 years, and 116 (78.4%) were men. The total survival rate was 45.9% (n=68). Cox regression analysis showed that the pre-ECMO lactate level was an independent predictor of 6-month mortality (hazard ratio, 1.210; 95% confidence interval [CI], 1.064-1.376; p=0.004). The area under the receiver operating characteristic curve of pre-ECMO lactate was 0.64 (95% CI, 0.56-0.72; p=0.002; cut-off value=9.8 mmol/L). Kaplan-Meier survival analysis showed that the cumulative survival rate at 6 months was significantly higher among patients with a pre-ECMO lactate level of 9.8 mmol/L or less than among those with a level exceeding 9.8 mmol/L (57.3% vs. 31.8%, p=0.0008). CONCLUSION: A pre-ECMO lactate of 9.8 mmol/L or less may predict a favorable outcome at 6 months in ACS patients undergoing VA-ECMO. Further research aiming to improve the accuracy of predictions of reversibility in patients with high pre-ECMO lactate levels is essential.

Successful Surgical Management of a Tracheo-Innominate Artery Fistula in a Patient with Duchenne Muscular Dystrophy: A Case Report.

Tracheo-innominate artery fistula (TIF) is a rare, life-threatening complication of tracheostomy that makes it difficult to secure the airway due to massive bleeding, constituting a medical emergency. Therefore, most successful surgical treatments include innominate artery debridement and tracheal fistula repair. Herein, we report a case of successful surgical treatment of a TIF while maintaining cerebral blood flow through an artificial vascular graft.

Thoracoscopic pulmonary metastasectomy in metastatic colorectal cancer: Surgical outcomes and prognostic factors.

BACKGROUND: This study aimed to confirm the effectiveness of thoracoscopic metastasectomy for colorectal cancer (CRC) and determine its prognostic factors. METHODS: Of the 181 patients who underwent video-assisted thoracoscopic surgery (VATS) for pulmonary metastases from CRC between 2011 and 2017, 173 were retrospectively reviewed. Surgical outcomes, long-term survival, and the factors affecting the prognosis were analyzed. RESULTS: The patients in the study were predominantly male (n = 104, 60.1%), and the median age was 65 years (range, 25-83 years). The median follow-up time was 46 months (range, 0-114 months). The surgical procedures were 156 wedge resections, five segmentectomies, and 12 lobectomies. Conversion to thoracotomy was required in nine patients. The postoperative complication rate was 2.9%, and the in-hospital mortality rate was 1.2%. The overall 1-, 3-, and 5-year survival rates were 94.8%, 70.6%, and 51.8%, respectively. Univariate analysis showed that the prognostic factors for survival were age (p = 0.027), pathological stage of CRC (p = 0.019), prior extrathoracic metastasis (p = 0.005), preoperative carcinoembryonic antigen level (p = 0.020), number of pulmonary metastases (p = 0.011), and disease-free interval (p = 0.026). In the multivariate analysis, two factors were related to prognosis: age (hazard ratio [HR], 1.881; 95% confidence interval [CI]; 1.189-2.976; p = 0.007) and prior extrathoracic metastasis (HR, 2.170; 95% CI; 1.269-3.711; p = 0.005). CONCLUSIONS: VATS for pulmonary metastasectomy for CRC can be performed relatively safely, and our results regarding long-term survival are comparable with those of other studies. In this study, older age (≥70 years) and prior extrathoracic metastasis were independent prognostic factors of poor prognosis.

Laparoscopic repair of hiatal hernia.

BACKGROUND: Laparoscopic hiatal hernia repair is a complex surgery typically performed by general abdominal surgeons because it typically involves an abdominal approach. Here, we report our experiences on laparoscopic repair of hiatal hernia as thoracic surgeons. METHODS: Based on our experience of minimally invasive esophageal surgery (MIES) for esophageal cancer, we began performing laparoscopic repair of hiatal hernia in 2009. We analyzed the surgery-related data and postoperative outcomes of 18 consecutive patients we operated on from 2009 to 2017. RESULTS: There were 1 male and 17 female patients with a median age of 73 years (range, 37-81 years). Ten of 14 symptomatic patients experienced reflux symptoms, such as heartburn. Four patients had a history of prior abdominal surgery. Hiatal hernia types I, II, III, and IV were observed in 3, 9, 5, and 1 patients, respectively. Two (11.1%) laparoscopic procedures required conversion. Modified Collis gastroplasty was used as an esophageal lengthening procedure in 5 patients (27.8%). Mean operation time was 213.8±70.1 minutes and mean hospital stay was 6.2±1.5 days. There were no postoperative complications. At the last follow-up, 15 patients (83.3%) were asymptomatic; however, 3 (16.7%) complained of reflux or dysphagia. Recurrent hiatal hernia was detected on an esophagogram in only 1 patient at 3.5 years after laparoscopic surgery. CONCLUSIONS: Laparoscopic repair of hiatal hernia is a feasible technique with a satisfactory surgical outcome. Importantly, it can be performed by thoracic surgeons who are experienced in the laparoscopic approach.

Hysteresis data of planar perovskite solar cells fabricated with different solvents.

In this data article, we introduced the hysteresis of planar perovskite solar cells (PSCs) fabricated using dimethylformamide (DMF), gamma-butyrolactone (GBL), methyl-2-pyrrolidinone (NMP), dimethylsulfoxide (DMSO), DMF-DMSO, GBL-DMSO and NMP-DMSO as perovskite precursor solutions according to different scan directions, sweep times, and current stability. The hysteresis analyses of the planar PSCs prepared with a glass-ITO /NiOX/perovskite /PC61BM/BCP/Ag configuration were measured with Keithley 2400 source meter unit under 100 mW/cm2 (AM 1.5 G). The data collected in this article compares the hysteresis of PSCs with different solvents and is directly related to our research article "High-Performance Planar Perovskite Solar Cells: Influence of Solvent upon Performance" (You-Hyun Seo et al., 2017 [1]).