Stroke is the leading cause of death and disability among people in China, and it leads to heavy burdens for patients, their families and society. An accurate prediction of the risk of stroke has important implications for early intervention and treatment. In light of recent advances in machine learning, the application of this technique in stroke prediction has achieved plentiful promising results. To detect the relationship between potential factors and the risk of stroke and examine which machine learning method significantly can enhance the prediction accuracy of stroke. We employed six machine learning methods including logistic regression, naive Bayes, decision tree, random forest, K-nearest neighbor and support vector machine, to model and predict the risk of stroke. Participants were 233 patients from Sichuan and Chongqing. Four indicators (accuracy, precision, recall and F1 metric) were examined to evaluate the predictive performance of the different models. The empirical results indicate that random forest yields the best accuracy, recall and F1 in predicting the risk of stroke, with an accuracy of .7548, precision of .7805, recall of .7619 and F1 of .7711. Additionally, the findings show that age, cerebral infarction, PM 8 (an anti-atrial fibrillation drug), and drinking are independent risk factors for stroke. Further studies should adopt a broader assortment of machine learning methods to analyze the risk of stroke, by which better accuracy can be expected. In particular, RF can successfully enhance the forecasting accuracy for stroke.
Limited land resources and dense population result in high living density in Hong Kong, where the current housing supply is not able to fulfill the growing housing demand, which leads to a crowded living environment and an elevated housing price. Thus, there is an urgent need to accelerate the delivery of new housing. Moreover, this high density living might increase psychological stress, due to the reduction in privacy and limited social interactions. Under these circumstances, creating co-living communities using the Modular Integrated Construction (MiC) methods could be beneficial in addressing these issues. Co-living facilitates social interactions and reduces living costs through the sharing of living spaces, while applying the MiC method shortens the construction process, mitigates labour shortage and on-site pollution through its modularised design and off-site production. This study aims to introduce a framework of creating a co-living community, through the case study of a pilot co-living project called “InnoCell” located in Hong Kong and designed by Leigh & Orange Ltd. In this project, diversified communal services are integrated to accommodate the increasing needs for social activities in addition to providing shelter. MiC methods of construction are applied to the living units, which shorten the construction time, mitigate the noise and air pollution on site, allow better quality control and minimise substandard works through off-site production. Daylight and air ventilation conditions are also examined to evaluate the indoor environmental conditions. In micro and macro perspectives, InnoCell will not only influence the residents’ lifestyle, but is also likely to initiate a new trend of living in Hong Kong. This study introduces a well-considered co-living design framework with the application of MiC methods, which could be further explored in other regions, especially other high-density cities, e.g. New York, London, and Singapore, etc.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.