Recommendation algorithms regard user-item interaction as a sequence to capture the user’s short-term preferences,but conventional algorithms cannot capture information of constantly-changing user interest in complex...Recommendation algorithms regard user-item interaction as a sequence to capture the user’s short-term preferences,but conventional algorithms cannot capture information of constantly-changing user interest in complex contexts.In these years,combining the knowledge graphwith sequential recommendation has gained momentum.The advantages of knowledge graph-based recommendation systems are that more semantic associations can improve the accuracy of recommendations,rich association facts can increase the diversity of recommendations,and complex relational paths can hence the interpretability of recommendations.But the information in the knowledge graph,such as entities and relations,often fails to be fully utilized and high-order connectivity is unattainable in graph modelling in knowledge graph-based sequential recommender systems.To address the above problems,a knowledge graph-based sequential recommendation algorithm that combines the gated recurrent unit and the graph neural network(KGSRGG)is proposed in the present work.Specifically,entity disambiguation in the knowledge graph is performed on the preprocessing layer;on the embedding layer,the TransR embedding technique is employed to process the user information,item information and the entities and relations in the knowledge graph;on the aggregation layer,the information is aggregated by graph convolutional neural networks and residual connections;and at last,on the sequence layer,a bi-directional gated recurrent unit(Bi-GRU)is utilized to model the user’s sequential preferences.The research results showed that this newalgorithm performed better than existing sequential recommendation algorithms on the MovieLens-1M and Book-Crossing datasets,as measured by five evaluation indicators.展开更多
Background Extracorporeal membrane oxygenation(ECMO)not only significantly improves survival rates in severely ill neonates but also is associated with long-term neurodevelopmental issues.To systematically review the ...Background Extracorporeal membrane oxygenation(ECMO)not only significantly improves survival rates in severely ill neonates but also is associated with long-term neurodevelopmental issues.To systematically review the available literature on the neurodevelopmental outcomes of neonates and infants who have undergone ECMO treatment,with a focus on motor deficits,cognitive impairments,sensory impairments,and developmental delays.This review aims to understand the incidence,prevalence,and risk factors for these problems and to explore current nursing care and management strategies.Data sources A comprehensive literature search was performed across PubMed,EMBASE,and Web of Science using a wide array of keywords and phrases pertaining to ECMO,neonates,infants,and various facets of neurodevelopment.The initial screening involved reviewing titles and abstracts to exclude irrelevant articles,followed by a full-text assessment of potentially relevant literature.The quality of each study was evaluated based on its research methodology and statistical analysis.Moreover,citation searches were conducted to identify potentially overlooked studies.Although the focus was primarily on neonatal ECMO,studies involving children and adults were also included due to the limited availability of neonate-specific literature.Results About 50%of neonates post-ECMO treatment exhibit varying degrees of brain injury,particularly in the frontal and temporoparietal white matter regions,often accompanied by neurological complications.Seizures occur in 18%–23%of neonates within the first 24 hours,and bleeding events occur in 27%–60%of ECMO procedures,with up to 33%potentially experiencing ischemic strokes.Although some studies suggest that ECMO may negatively impact hearing and visual development,other studies have found no significant differences;hence,the influence of ECMO remains unclear.In terms of cognitive,language,and intellectual development,ECMO treatment may be associated with potential developmental delays,including lower composite scores in cognitive and motor functions,as well as potential language and learning difficulties.These studies emphasize the importance of early detection and intervention of potential developmental issues in ECMO survivors,possibly necessitating the implementation of a multidisciplinary follow-up plan that includes regular neuromotor and psychological evaluations.Overall,further multicenter,large-sample,long-term follow-up studies are needed to determine the impact of ECMO on these developmental aspects.Conclusions The impact of ECMO on an infant’s nervous system still requires further investigation with larger sample sizes for validation.Fine-tuned management,comprehensive nursing care,appropriate patient selection,proactive monitoring,nutritional support,and early rehabilitation may potentially contribute to improving the long-term outcomes for these infants.展开更多
文摘Recommendation algorithms regard user-item interaction as a sequence to capture the user’s short-term preferences,but conventional algorithms cannot capture information of constantly-changing user interest in complex contexts.In these years,combining the knowledge graphwith sequential recommendation has gained momentum.The advantages of knowledge graph-based recommendation systems are that more semantic associations can improve the accuracy of recommendations,rich association facts can increase the diversity of recommendations,and complex relational paths can hence the interpretability of recommendations.But the information in the knowledge graph,such as entities and relations,often fails to be fully utilized and high-order connectivity is unattainable in graph modelling in knowledge graph-based sequential recommender systems.To address the above problems,a knowledge graph-based sequential recommendation algorithm that combines the gated recurrent unit and the graph neural network(KGSRGG)is proposed in the present work.Specifically,entity disambiguation in the knowledge graph is performed on the preprocessing layer;on the embedding layer,the TransR embedding technique is employed to process the user information,item information and the entities and relations in the knowledge graph;on the aggregation layer,the information is aggregated by graph convolutional neural networks and residual connections;and at last,on the sequence layer,a bi-directional gated recurrent unit(Bi-GRU)is utilized to model the user’s sequential preferences.The research results showed that this newalgorithm performed better than existing sequential recommendation algorithms on the MovieLens-1M and Book-Crossing datasets,as measured by five evaluation indicators.
基金funded by the National Natural Science Foundation of China(Grant number:82001599)Medical Innovation Research Program of Shanghai,China(Grant number:21Y11907200)Clinical Research Special Project of Shanghai Municipal Health Commission,China(Grant number:202140443).
文摘Background Extracorporeal membrane oxygenation(ECMO)not only significantly improves survival rates in severely ill neonates but also is associated with long-term neurodevelopmental issues.To systematically review the available literature on the neurodevelopmental outcomes of neonates and infants who have undergone ECMO treatment,with a focus on motor deficits,cognitive impairments,sensory impairments,and developmental delays.This review aims to understand the incidence,prevalence,and risk factors for these problems and to explore current nursing care and management strategies.Data sources A comprehensive literature search was performed across PubMed,EMBASE,and Web of Science using a wide array of keywords and phrases pertaining to ECMO,neonates,infants,and various facets of neurodevelopment.The initial screening involved reviewing titles and abstracts to exclude irrelevant articles,followed by a full-text assessment of potentially relevant literature.The quality of each study was evaluated based on its research methodology and statistical analysis.Moreover,citation searches were conducted to identify potentially overlooked studies.Although the focus was primarily on neonatal ECMO,studies involving children and adults were also included due to the limited availability of neonate-specific literature.Results About 50%of neonates post-ECMO treatment exhibit varying degrees of brain injury,particularly in the frontal and temporoparietal white matter regions,often accompanied by neurological complications.Seizures occur in 18%–23%of neonates within the first 24 hours,and bleeding events occur in 27%–60%of ECMO procedures,with up to 33%potentially experiencing ischemic strokes.Although some studies suggest that ECMO may negatively impact hearing and visual development,other studies have found no significant differences;hence,the influence of ECMO remains unclear.In terms of cognitive,language,and intellectual development,ECMO treatment may be associated with potential developmental delays,including lower composite scores in cognitive and motor functions,as well as potential language and learning difficulties.These studies emphasize the importance of early detection and intervention of potential developmental issues in ECMO survivors,possibly necessitating the implementation of a multidisciplinary follow-up plan that includes regular neuromotor and psychological evaluations.Overall,further multicenter,large-sample,long-term follow-up studies are needed to determine the impact of ECMO on these developmental aspects.Conclusions The impact of ECMO on an infant’s nervous system still requires further investigation with larger sample sizes for validation.Fine-tuned management,comprehensive nursing care,appropriate patient selection,proactive monitoring,nutritional support,and early rehabilitation may potentially contribute to improving the long-term outcomes for these infants.
