Recipe Recommendation With Hierarchical Graph Attention Network.

Recipe recommendation systems play an important role in helping people find recipes that are of their interest and fit their eating habits. Unlike what has been developed for recommending recipes using content-based or collaborative filtering approaches, the relational information among users, recipes, and food items is less explored. In this paper, we leverage the relational information into recipe recommendation and propose a graph learning approach to solve it. In particular, we propose HGAT, a novel hierarchical graph attention network for recipe recommendation. The proposed model can capture user history behavior, recipe content, and relational information through several neural network modules, including type-specific transformation, node-level attention, and relation-level attention. We further introduce a ranking-based objective function to optimize the model. Thorough experiments demonstrate that HGAT outperforms numerous baseline methods.

A predictive model using left atrial function and B-type natriuretic peptide level in predicting the recurrence of early persistent atrial fibrillation after radiofrequency ablation.

AIM: A predictive model using left atrial function indexes obtained by real-time three-dimensional echocardiography (RT-3DE) and the blood B-type natriuretic peptide (BNP) level was constructed, and its value in predicting recurrence in patients with early persistent atrial fibrillation (AF) after radiofrequency ablation was explored. METHODS: A total of 228 patients with early persistent AF who were scheduled to receive the first circular pulmonary vein ablation (CPVA) were enrolled. Clinical data of patients were collected: (1) The blood BNP level was measured before radiofrequency ablation; (2) RT-3DE was used to obtain the left atrial (LA) time-volume curve; (3) The clinical characteristics, BNP level and LA function parameters were compared, and logistic regression was used to construct a prediction model with combined parameters; (4) The receiver operating characteristic (ROC) curve was used to examine the diagnostic efficacy of the model. RESULTS: (1) 215 patients with early persistent AF completed CPVA and the follow-up. After 3-6 months of follow-up, the patients were divided into sinus rhythm group (160 cases) and recurrence group (55 cases); (2) The recurrence group showed higher minimum LA volume index, diastolic ejection index, and preoperative BNP (all p ≤ .001), while the sinus rhythm group exhibited higher expansion index (PI) and left atrial appendage peak emptying velocity (p ≤ .001); (3) In univariate analysis, BNP level had the best diagnostic performance in predicting the recurrence of AF(AUC = 0.703). We constructed a model based on LA function and BNP level to predict the recurrence of persistent AF after CPVA. This combined model was better than BNP alone in predicting the recurrence of persistent AF after CPVA (AUC: 0.814 vs. 0.703, z = 2.224, p = .026). CONCLUSION: The combined model of LA function and blood BNP level has good predictive value for the recurrence of early persistent AF after CPVA.

Emergence of blind areas in information spreading.

Recently, contagion-based (disease, information, etc.) spreading on social networks has been extensively studied. In this paper, other than traditional full interaction, we propose a partial interaction based spreading model, considering that the informed individuals would transmit information to only a certain fraction of their neighbors due to the transmission ability in real-world social networks. Simulation results on three representative networks (BA, ER, WS) indicate that the spreading efficiency is highly correlated with the network heterogeneity. In addition, a special phenomenon, namely Information Blind Areas where the network is separated by several information-unreachable clusters, will emerge from the spreading process. Furthermore, we also find that the size distribution of such information blind areas obeys power-law-like distribution, which has very similar exponent with that of site percolation. Detailed analyses show that the critical value is decreasing along with the network heterogeneity for the spreading process, which is complete the contrary to that of random selection. Moreover, the critical value in the latter process is also larger than that of the former for the same network. Those findings might shed some lights in in-depth understanding the effect of network properties on information spreading.