Prognostic prediction of sepsis patient using transformer with skip connected token for tabular data.

Sepsis is known as a common syndrome in intensive care units (ICU), and severe sepsis and septic shock are among the leading causes of death worldwide. The purpose of this study is to develop a deep learning model that supports clinicians in efficiently managing sepsis patients in the ICU by predicting mortality, ICU length of stay (>14 days), and hospital length of stay (>30 days). The proposed model was developed using 591 retrospective data with 16 tabular data related to a sequential organ failure assessment (SOFA) score. To analyze tabular data, we designed the modified architecture of the transformer that has achieved extraordinary success in the field of languages and computer vision tasks in recent years. The main idea of the proposed model is to use a skip-connected token, which combines both local (feature-wise token) and global (classification token) information as the output of a transformer encoder. The proposed model was compared with four machine learning models (ElasticNet, Extreme Gradient Boosting [XGBoost]), and Random Forest) and three deep learning models (Multi-Layer Perceptron [MLP], transformer, and Feature-Tokenizer transformer [FT-Transformer]) and achieved the best performance (mortality, area under the receiver operating characteristic (AUROC) 0.8047; ICU length of stay, AUROC 0.8314; hospital length of stay, AUROC 0.7342). We anticipate that the proposed model architecture will provide a promising approach to predict the various clinical endpoints using tabular data such as electronic health and medical records.

Inhaled Corticosteroids and Risk of Cardiovascular Disease in Chronic Obstructive Pulmonary Disease: A Systematic Review and Meta-Regression.

Background: Previous studies have reported mixed associations between inhaled corticosteroids (ICSs) and cardiovascular disease (CVD) in people with chronic obstructive pulmonary disease (COPD). Using updated literature, we investigated the association between ICS-containing medications and CVD in COPD patients, stratified by study-related factors. Methods: We searched MEDLINE and EMBASE for studies that reported effect estimates for the association between ICS-containing medications and the risk of CVD in COPD patients. CVD outcomes specifically included heart failure, myocardial infarction, and stroke-related events. We conducted a random-effects meta-analysis and a meta-regression to identify effect-modifying study-related factors. Results: Fifteen studies met inclusion criteria and investigated the association between ICS-containing medications and the risk of CVD. Pooled results from our meta-analysis showed a significant association between ICS-containing medication and reduced risk of CVD (hazard ratio 0.87, 95% confidence intervals 0.78 to 0.97). Study follow-up time, non-ICS comparator, and exclusion of patients with previous CVD modified the association between ICS use and risk of CVD. Conclusions: Overall, we found an association between ICS-containing medications and reduced risk of CVD in COPD patients. Results from the meta-regression suggest that subgroups of COPD patients may benefit from ICS use more than others and further work is needed to determine this.

Deep Learning Model for Predicting Rhythm Outcomes after Radiofrequency Catheter Ablation in Patients with Atrial Fibrillation.

Current guidelines on atrial fibrillation (AF) emphasized that radiofrequency catheter ablation (RFCA) should be decided after fully considering its prognosis. However, a robust prediction model reflecting the complex interactions between the features affecting prognosis remains to be developed. In this paper, we propose a deep learning model for predicting the late recurrence after RFCA in patients with AF. Aiming to predict the late recurrence (LR) of AF within 1 year after pulmonary vein isolation, we designed a multimodal model based on the multilayer perceptron architecture. For quantitative evaluation, we conducted 4-fold cross-validation on data from 177 AF patients including 47 LR patients. The proposed model (area under the receiver operating characteristic curve-AUROC, 0.766) outperformed the acute patient physiologic and laboratory evaluation (APPLE) score (AUROC, 0.605), CHA2DS2-VASc score (AUROC, 0.595), linear regression (AUROC, 0.541), logistic regression (AUROC, 0.546), extreme gradient boosting (AUROC, 0.608), and support vector machine (AUROC, 0.638). The proposed model exhibited better performance than clinical indicators (APPLE and CHA2DS2-VASc score) and machine learning techniques (linear regression, logistic regression, extreme gradient boosting, and support vector machine). The model will support clinical decision-making for selecting good responders to the RFCA intervention.

Secure and reliable blockchain-based eBook transaction system for self-published eBook trading.

As eBook readers have expanded on the market, various online eBook markets have arisen as well. Currently, the online eBook market consists of at least publishers and online platform providers and authors, and these actors inevitably incur intermediate costs between them. In this paper, we introduce a blockchain-based eBook market system that enables self-published eBook trading and direct payments from readers to authors without any trusted party; because authors publish themselves and readers purchase directly from authors, neither actor incurs any intermediate costs. However, because of this trustless environment, the validity, ownership and intellectual property of digital contents cannot be verified and protected, and the safety of purchase transactions cannot be ensured. To address these shortcomings, we propose a secure and reliable eBook transaction system that satisfies the following security requirements: (1) verification of the ownership of each eBook, (2) confidentiality of eBook contents, (3) authorization of a right to read a book, (4) authentication of a legitimate purchaser, (5) verification of the validity and integrity of eBook contents, (6) safety of direct purchase transactions, and (7) preventing eBook piracy and illegal distribution. We provide practical cryptographic protocols for the proposed system and analyze the security and simulated performance of the proposed schemes.