Current food recommender systems tend to prioritize either the user’s dietary preferences or the healthiness of the food, without considering the importance of personalized health requirements. To address this issue, we propose a novel approach to healthy food recommendations that takes into account the user’s personalized health requirements, in addition to their dietary preferences. Our work comprises three perspectives. Firstly, we propose a collaborative recipe knowledge graph (CRKG) with millions of triplets, containing user–recipe interactions, recipe–ingredient associations, and other food-related information. Secondly, we define a score-based method for evaluating the healthiness match between recipes and user preferences. Based on these two prior perspectives, we develop a novel health-aware food recommendation model (FKGM) using knowledge graph embedding and multi-task learning. FKGM employs a knowledge-aware attention graph convolutional neural network to capture the semantic associations between users and recipes on the collaborative knowledge graph and learns the user’s requirements in both preference and health by fusing the losses of these two learning tasks. We conducted experiments to demonstrate that FKGM outperformed four competing baseline models in integrating users’ dietary preferences and personalized health requirements in food recommendations and performed best on the health task.
ObjectiveDisplacement of bone cement following percutaneous vertebral augmentation for Kümmell disease (KD) presents a significant concern, resulting in increasing back pain and compromising daily activities. Unfortunately, current literature does not yet establish a validated and minimally invasive surgical intervention for this issue. This study aims to investigate the effects of a novel hollow pedicle screw combined with kyphoplasty (HPS‐KP) in preventing bone cement displacement following simply percutaneous kyphoplasty for the management of KD.MethodsA total of 22 patients (six males, 16 females, averagely aged 77.18 ± 7.63 years) with KD without neurological deficits treated by HPS‐KP at the hospital between March 2021 and June 2022 were hereby selected, among which, there were three stage I KD cases, 12 stage II KD cases, and seven stage III KD cases according to Li's classification. Bone mineral density (BMD), spinal X‐ray, computed tomography (CT), and magnetic resonance imaging (MRI) were examined before the operation. The operation time, intraoperative blood loss, and postoperative complications were all recorded. The follow‐up focused on visual analog scale (VAS) score, Oswestry dysfunction index (ODI), anterior vertebral height (AVH), middle vertebral height (MVH), posterior vertebral height (PVH), wedge‐shape affected vertebral Cobb angle (WCA), and bisegmental Cobb angle (BCA). One‐way analysis of variance (ANOVA) followed by Bonferroni post‐hoc test was employed for performing multiple comparisons in the present study.ResultsAll patients having received the operation successfully were followed up for more than 8 months (ranging from 8 to 18 months). The operation time, intraoperative blood loss, and BMD (T‐score) were 39.09 ± 5.64 min, 14.09 ± 3.98 ml, and − 3.30 ± 0.90 g/cm3, respectively. Statistically significant differences were observed in the VAS score, ODI, AVH, MVH, and WCA (All p < 0.05), but there was no statistically significant difference in PVH and BCA at different time points (All p > 0.05). During follow‐up, five patients suffered from bone cement leakage, and one presented an adjacent vertebral fracture and no bone cement displacement.ConclusionHPS‐KP could be safe and effective in the treatment of KD without neurological deficits, effectively relieving the symptoms of patients, restoring partial vertebral height, and preventing the occurrence of bone cement displacement.
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.