Search

BackgroundDespite excellent prediction performance, noninterpretability has undermined the value of applying deep-learning algorithms in clinical practice. To overcome this limitation, attention mechanism has been introduced to clinical research as an explanatory modeling method. However, potential limitations of using this attractive method have not been clarified to clinical researchers. Furthermore, there has been a lack of introductory information explaining attention mechanisms to clinical researchers. ObjectiveThe aim of this study was to introduce the basic concepts and design approaches of attention mechanisms. In addition, we aimed to empirically assess the potential limitations of current attention mechanisms in terms of prediction and interpretability performance. MethodsFirst, the basic concepts and several key considerations regarding attention mechanisms were identified. Second, four approaches to attention mechanisms were suggested according to a two-dimensional framework based on the degrees of freedom and uncertainty awareness. Third, the prediction performance, probability reliability, concentration of variable importance, consistency of attention results, and generalizability of attention results to conventional statistics were assessed in the diabetic classification modeling setting. Fourth, the potential limitations of attention mechanisms were considered. ResultsPrediction performance was very high for all models. Probability reliability was high in models with uncertainty awareness. Variable importance was concentrated in several variables when uncertainty awareness was not considered. The consistency of attention results was high when uncertainty awareness was considered. The generalizability of attention results to conventional statistics was poor regardless of the modeling approach. ConclusionsThe attention mechanism is an attractive technique with potential to be very promising in the future. However, it may not yet be desirable to rely on this method to assess variable importance in clinical settings. Therefore, along with theoretical studies enhancing attention mechanisms, more empirical studies investigating potential limitations should be encouraged.

The common data model (CDM) has found widespread application in healthcare studies, but its utilization in cancer research has been limited. This article describes the development and implementation strategy for Cancer Clinical Library Databases (CCLDs), which are standardized cancer-specific databases established under the Korea-Clinical Data Utilization Network for Research Excellence (K-CURE) project by the Korean Ministry of Health and Welfare. Fifteen leading hospitals and fourteen academic associations in Korea are engaged in constructing CCLDs for 10 primary cancer types. For each cancer type-specific CCLD, cancer data experts determine key clinical data items essential for cancer research, standardize these items across cancer types, and create a standardized schema. Comprehensive clinical records covering diagnosis, treatment, and outcomes, with annual updates, are collected for each cancer patient in the target population, and quality control is based on six-sigma standards. To protect patient privacy, CCLDs follow stringent data security guidelines by pseudonymizing personal identification information and operating within a closed analysis environment. Researchers can apply for access to CCLD data through the K-CURE portal, which is subject to Institutional Review Board and Data Review Board approval. The CCLD is considered a pioneering standardized cancer-specific database, significantly representing Korea's cancer data. It is expected to overcome limitations of previous CDMs and provide a valuable resource for multicenter cancer research in Korea. [ABSTRACT FROM AUTHOR]

As environmental problems increase, disposable products are being replaced and recommended with materials with a low environmental load when it discarded. So the demand for bioplastics for building a sustainable society is increasing. This study focuses mainly on the applicability of biodegradable plastics and rosin maleic resin (RMR, DX‐250) blends with potential use in eco‐friendly hot‐melt adhesives (HMA). Poly (butylene adipate‐co‐terephthalate) (PBAT), which has high dimensional stability owing to low crystallinity, is used as the main polymer of the HMA. And rosin maleic resin, which is effective for increasing adhesive properties and compatibility as a tackifier. The HMA based on PBAT and RMR blends are prepared via melt‐blend extrusion. Compatibility and wettability are increased under the influence of RMR, and adhesion properties are improved, compared to that of PBAT. In addition, as confirmed polarizing microscope (POM), the addition of RMR leads to a decrease in crystallinity, which can be expected to be effective for biodegradation. This result PBAT/RMR 7/3 blend significantly enhances the adhesion strength of PBAT from 1.8 to 7.3 MPa. Therefore, PBAT with the blends containing 30 wt.% of RMR has considerable potential application in the HMA field. [ABSTRACT FROM AUTHOR]

This paper provides a comprehensive overview of the Cancer Public Library Database (CPLD), established under the Korean Clinical Data Utilization for Research Excellence project (K-CURE). The CPLD links data from four major population-based public sources: the Korea National Cancer Incidence Database in the Korea Central Cancer Registry, cause-of-death data in Statistics Korea, the National Health Information Database in the National Health Insurance Service, and the National Health Insurance Research Database in the Health Insurance Review & Assessment Service. These databases are linked using an encrypted resident registration number. The CPLD, established in 2022 and updated annually, comprises 1,983,499 men and women newly diagnosed with cancer between 2012 and 2019. It contains data on cancer registration and death, demographics, medical claims, general health checkups, and national cancer screening. The most common cancers among men in the CPLD were stomach (16.1%), lung (14.0%), colorectal (13.3%), prostate (9.6%), and liver (9.3%) cancers. The most common cancers among women were thyroid (20.4%), breast (16.6%), colorectal (9.0%), stomach (7.8%), and lung (6.2%) cancers. Among them, 571,285 died between 2012 and 2020 owing to cancer (89.2%) or other causes (10.8%). Upon approval, the CPLD is accessible to researchers through the K-CURE portal. The CPLD is a unique resource for diverse cancer research to investigate medical use before a cancer diagnosis, during initial diagnosis and treatment, and long-term follow-up. This offers expanded insight into healthcare delivery across the cancer continuum, from screening to end-of-life care. [ABSTRACT FROM AUTHOR]