Search

Objective: The cardioprotective effects of nuts are well established. However, the positive impacts of nuts in preventing CVD at a younger age, a condition known as premature coronary artery disease (PCAD), is still debated. Therefore, we aim to determine the association between nuts and PCAD occurrence and its severity in different Iranian ethnicities. Design: This case–control study was conducted within the framework of the Iran-premature coronary artery disease (I-PAD) study, an ongoing multi-centric study on Iranian patients of different ethnicities. Setting: This multi-centric case–control study was conducted in among 3253 persons under the age of 70 years in women and 60 years in men from different ethnicities in Iran. Participants: Information on nut consumption was collected using a validated FFQ. Subjects were selected from among the candidates for angiography. Cases were those whose coronary angiography showed stenosis of more than 75 % in at least one vessel or more than 50 % of the left main artery, while the control group participants had normal angiography results. Results: In the crude model, compared to the first quartile, the highest quartile of nut consumption was significantly associated with a lower risk of PCAD (OR = 0·26, 95 % CI (0·21, 0·32); P for trend = 0·001). In the top quartile of nut intake, a substantial decrease in PCAD was observed after controlling for putative confounders (OR = 0·32; 95 % CI (0·24, 0·43); P for trend = 0·001). Additionally, a 75 % decrease in the risk of severe PCAD was observed in the participants in the highest quartile of nut intake. Conclusion: A significant inverse association was observed between nut intake and the risk and severity of PCAD in the Iranian population. Large-scale clinical trials are required to confirm these findings. [ABSTRACT FROM AUTHOR]

Efficiently exploiting all sources of information such as labeled instances, classes' representation, and relations of them has a high impact on the performance of Multi-Label Text Classification (MLTC) systems. Most of the current approaches use labeled documents as the primary source of information for MLTC. We investigate the effectiveness of different sources of information— such as the labeled training data, textual labels of classes, and taxonomy relations of classes— for MLTC. More specifically, first, for each document–class pair, different features are extracted using different sources of information. The features reflect the similarity of classes and documents. Then, MLTC is considered to be a ranking problem, and a learning to rank (LTR) approach is used for ranking classes regarding documents and selecting labels of documents. An important characteristic of many MLTC instances is that documents can belong to multiple classes and there are implicit relations between classes. We apply score propagation on top of LTR to incorporate co-occurrence patterns of classes in labeled documents. Our main findings are the following. First, using an LTR approach integrating all features, we observe significantly better performance than previous systems for MLTC. Specifically, we show that simple classification approaches fail when there is a high number of classes. Second, the analysis of feature weights reveals the relative importance of various sources of evidence, also giving insight into the underlying classification problem. Interestingly, the results indicate that the titles of documents are more informative than all other sources of information. Third, a lean-and-mean system using only four features is able to perform at 96% of the large LTR model that we propose in this paper. Fourth, using the co-occurrence information of classes helps in classifying documents more accurately. Our results show that the co-occurrence information is more helpful when the underlying classifier has a poor performance. [ABSTRACT FROM AUTHOR]

Comparable corpora are key translation resources for both languages and domains with limited linguistic resources. The existing approaches for building comparable corpora are mostly based on ranking candidate documents in the target language for each source document using a cross-lingual retrieval model. These approaches also exploit other evidence of document similarity, such as proper names and publication dates, to build more reliable alignments. However, the importance of each evidence in the scores of candidate target documents is determined heuristically. In this paper, we employ a learning to rank method for ranking candidate target documents with respect to each source document. The ranking model is constructed by defining each evidence for similarity of bilingual documents as a feature whose weight is learned automatically. Learning feature weights can significantly improve the quality of alignments, because the reliability of features depends on the characteristics of both source and target languages of a comparable corpus. We also propose a method to generate appropriate training data for the task of building comparable corpora. We employed the proposed learning-based approach to build a multi-domain English- Persian comparable corpus which covers twelve different domains obtained from Open Directory Project. Experimental results show that the created alignments have high degrees of comparability. Comparison with existing approaches for building comparable corpora shows that our learning-based approach improves both quality and coverage of alignments. [ABSTRACT FROM AUTHOR]