Recent effective therapies enable most rheumatoid arthritis (RA) patients to achieve remission; however, some patients experience relapse. We aimed to predict relapse in RA patients through machine learning (ML) using data on ultrasound (US) examination and blood test. Overall, 210 patients with RA in remission at baseline were dichotomized into remission (n = 150) and relapse (n = 60) based on the disease activity at 2-year follow-up. Three ML classifiers [Logistic Regression, Random Forest, and extreme gradient boosting (XGBoost)] and data on 73 features (14 US examination data, 54 blood test data, and five data on patient information) at baseline were used for predicting relapse. The best performance was obtained using the XGBoost classifier (area under the receiver operator characteristic curve (AUC) = 0.747), compared with Random Forest and Logistic Regression (AUC = 0.719 and 0.701, respectively). In the XGBoost classifier prediction, ten important features, including wrist/metatarsophalangeal superb microvascular imaging scores, were selected using the recursive feature elimination method. The performance was superior to that predicted by researcher-selected features, which are conventional prognostic markers. These results suggest that ML can provide an accurate prediction of relapse in RA patients, and the use of predictive algorithms may facilitate personalized treatment options.
The Tohoku Disaster has had wide ranging and interconnected effects on social, environmental, and economic systems. Because Japan was arguably one of the world's most prepared nations in dealing with natural disasters, experts and policy makers have been struggling to answer questions like "How could Japan have been more resilient?" and "How could Japan have been better prepared?" This paper seeks to address two key gaps related to the integration of resilience into disaster management and public policy: (i) Few studies have provided an overarching analytical or structural framework for the inclusion of resilience into public policy and disaster management and (ii) few institutions have provided guidance as to the specific operational components of resilience and how to implement it. The paper outlines an analytical framework and an overarching structure for resilience-based disaster management and public policy, focusing on the structure and components of resilience. Then, it examines how resilience can be incorporated into actionable disaster management policies, drawing on analyses of the experiences and lessons from the Tohoku Disaster.
A U.S.-Japan expert workshop on mobile alert and warning was held online 8–10 September 2021. Funded by the Japan Foundation’s Center for Global Partnership (CGP) and responding to the Sendai Framework for Disaster Risk Reduction 2015–2030, the workshop compared U.S. and Japanese mobile alert and warning contexts, systems, policies, and messages to investigate possibilities for international harmonization of mobile device-based early warning. The workshop’s sessions revealed two interrelated issues that repeatedly surfaced among workshop participants: culture and policy. The workshop illuminated several possibilities and problems confronting U.S., Japanese, and global stakeholders as they develop, deploy, and seek to improve the effectiveness of mobile alert and warning systems and messages.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.