H igh blood pressure (BP) is an established modifiable risk factor for cardiovascular disease and mortality. However, the association between BP and cardiovascular risk weakens in the elderly.1 A major confounding factor is atherosclerotic peripheral arterial disease (PAD). 2,3 When PAD is present in subclavian and brachial arteries, arm BP cannot be accurately measured, and hypertension therefore cannot be timely diagnosed and properly managed in clinical practice. 4,5 Current technology allows simultaneous BP measurement in 4 limbs, 6,7 which may provide a comprehensive evaluation of BP and generate accurate BP differences between 4 limbs, such as ankle-brachial BP index (ABI) and the interarm and interankle BP differences. ABI is a well-documented diagnostic tool for PAD in lower extremities. 8 The interarm BP difference is also being recognized as an indicator of PAD in the subclavian or brachial arteries. [2][3][4][5][9][10][11] To the best of our knowledge, the diagnostic and prognostic significances of the interankle BP difference have not been investigated in prospective studies.We performed simultaneous BP measurement in 4 limbs in an elderly Chinese population, which was prospectively followed up for mortality. In the present study, we investigated total and cardiovascular mortality in relation to the level of arm BP, ABI, and the interarm and interankle BP differences. Methods Study PopulationOur study was conducted in the framework of the Chronic Disease Detection and Management in the Elderly (≥60 years) Program supported by the municipal government of Shanghai. In a newly urbanized suburban town, 30 kilometers from the city center, we invited all residents of 60 years or older to take part in comprehensive examinations of cardiovascular disease and risk. The Ethics Committee of Ruijin Hospital, Shanghai Jiaotong University School of Medicine approved the study protocol. All subjects gave written informed consent.A total of 3263 subjects (participation rate 90%) were enrolled in the period from 2006 to 2008, and followed up for vital status and cause of death till June 30, 2011. We excluded 130 subjects from the present analysis, because 4-limb BP measurement was not performed (n=45) or because of missing other information (n=85). Thus, the number of participants included in the present analysis was 3133. See Editorial Commentary, pp 1146-1147Abstract-The predictive value of blood pressure (BP) for cardiovascular morbidity and mortality diminishes in the elderly, which may be confounded and compensated by the BP differences across the 4 limbs, markers of peripheral arterial disease. In a prospective elderly (≥60 years) Chinese study, we performed simultaneous 4-limb BP measurement using an oscillometric device in the supine position, and calculated BP differences between the 4 limbs. At baseline, the mean age of the 3133 participants (1383 men) was 69 years. During 4 years (median) of follow-up, all-cause and cardiovascular deaths occurred in 203 and 93 subjects, respectively. In multiple regression...
Nuclei segmentation is a fundamental task in histopathology image analysis. Typically, such segmentation tasks require significant effort to manually generate accurate pixel-wise annotations for fully supervised training. To alleviate such tedious and manual effort, in this paper we propose a novel weakly supervised segmentation framework based on partial points annotation, i.e., only a small portion of nuclei locations in each image are labeled. The framework consists of two learning stages. In the first stage, we design a semi-supervised strategy to learn a detection model from partially labeled nuclei locations. Specifically, an extended Gaussian mask is designed to train an initial model with partially labeled data. Then, selftraining with background propagation is proposed to make use of the unlabeled regions to boost nuclei detection and suppress false positives. In the second stage, a segmentation model is trained from the detected nuclei locations in a weakly-supervised fashion. Two types of coarse labels with complementary information are derived from the detected points and are then utilized to train a deep neural network. The fully-connected conditional random field loss is utilized in training to further refine the model without introducing extra computational complexity during inference. The proposed method is extensively evaluated on two nuclei segmentation datasets. The experimental results demonstrate that our method can achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods while requiring significantly less annotation effort.
There has been growing attention on fairness considerations recently, especially in the context of intelligent decision making systems. Explainable recommendation systems, in particular, may suffer from both explanation bias and performance disparity. In this paper, we analyze different groups of users according to their level of activity, and find that bias exists in recommendation performance between different groups. We show that inactive users may be more susceptible to receiving unsatisfactory recommendations, due to insufficient training data for the inactive users, and that their recommendations may be biased by the training records of more active users, due to the nature of collaborative filtering, which leads to an unfair treatment by the system. We propose a fairness constrained approach via heuristic re-ranking to mitigate this unfairness problem in the context of explainable recommendation over knowledge graphs. We experiment on several real-world datasets with stateof-the-art knowledge graph-based explainable recommendation algorithms. The promising results show that our algorithm is not only able to provide high-quality explainable recommendations, but also reduces the recommendation unfairness in several respects.
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.