Item Recommendation Research Articles

Clinical decision support for severe trauma patients: Machine learning based definition of a bundle of care for hemorrhagic shock and traumatic brain injury.

Deviation from guidelines is frequent in emergency situations, and this may lead to increased mortality. Probably because of time constraints, 55% is the greatest reported guidelines compliance rate in severe trauma patients. This study aimed to identify among all available recommendations a reasonable bundle of items that should be followed to optimize the outcome of hemorrhagic shocks (HSs) and severe traumatic brain injuries (TBIs). We first estimated the compliance with French and European guidelines using the data from the French TraumaBase registry. Then, we used a machine learning procedure to reduce the number of recommendations into a minimal set of items to be followed to minimize 7-day mortality. We evaluated the bundles using an external validation cohort. This study included 5,924 trauma patients (1,414 HS and 4,955 TBI) between 2011 and August 2019 and studied compliance to 36 recommendation items. Overall compliance rate to recommendation items was 71.6% and 66.9% for HS and TBI, respectively. In HS, compliance was significantly associated with 7-day decreased mortality in univariate analysis but not in multivariate analysis (risk ratio [RR], 0.91; 95% confidence interval [CI], 0.90-1.17; p = 0.06). In TBI, compliance was significantly associated with decreased mortality in univariate and multivariate analysis (RR, 0.85; 95% CI, 0.75-0.92; p = 0.01). For HS, the bundle included 13 recommendation items. In the validation cohort, when this bundle was applied, patients were found to have a lower 7-day mortality rate (RR, 0.46; 95% CI, 0.27-0.63; p = 0.01). In TBI, the bundle included seven items. In the validation cohort, when this bundle was applied, patients had a lower 7-day mortality rate (RR, 0.55; 95% CI, 0.34-0.71; p = 0.02). Using a machine-learning procedure, we were able to identify a subset of recommendations that minimizes 7-day mortality following traumatic HS and TBI. These two bundles remain to be evaluated in a prospective manner. Care Management, level II.

EQUAL Score Scedosporiosis/Lomentosporiosis 2021: a European Confederation of Medical Mycology (ECMM) tool to quantify guideline adherence.

BackgroundInvasive scedosporiosis and lomentosporiosis are life-threatening fungal infections in immunocompromised patients with complex diagnostic and treatment patterns.ObjectivesTo develop a scoring tool to facilitate and quantify adherence to current guideline recommendations for diagnosis, treatment and follow-up of invasive scedosporiosis and lomentosporiosis.MethodsExperts from European Confederation of Medical Mycology (ECMM) excellence centres reviewed current guidelines for scedosporiosis and lomentosporiosis. Recommendations for diagnosis, treatment and follow-up were summarized, assembled and weighted according to their strength of recommendation and level of evidence (strongly recommended = 3 points; moderately recommended = 2 points; marginally recommended = 1 point; recommended against = 0 points). Additional items considered of high importance for clinical management were also weighted.ResultsA total of 170 recommendations were identified. A 21-item tool was developed and embedded into the EQUAL score card. Nine items for diagnosis with 18 achievable points were assembled. For treatment, three general recommendation items with a maximal score of 9 were identified, while for specific antifungal treatment the two fungal pathogens were separated. Three and four items were established for scedosporiosis and lomentosporiosis, respectively, with a maximum achievable score of 3 due to the separation of different treatment options with the maximum point value of 3 for voriconazole-based treatment. Follow-up comprised two items (4 points maximum). Key recommendations for clinical outcome were weighted accordingly.ConclusionsWe propose the EQUAL Score Scedosporiosis/Lomentosporiosis to quantify adherence to current guideline recommendations for management of these rare infections. The score remains to be validated in real-life patient cohorts and correlated with patient outcome.

Pointer-Based Item-to-Item Collaborative Filtering Recommendation System Using a Machine Learning Model

The creation of digital marketing has enabled companies to adopt personalized item recommendations for their customers. This process keeps them ahead of the competition. One of the techniques used in item recommendation is known as item-based recommendation system or item–item collaborative filtering. Presently, item recommendation is based completely on ratings like 1–5, which is not included in the comment section. In this context, users or customers express their feelings and thoughts about products or services. This paper proposes a machine learning model system where 0, 2, 4 are used to rate products. 0 is negative, 2 is neutral, 4 is positive. This will be in addition to the existing review system that takes care of the users’ reviews and comments, without disrupting it. We have implemented this model by using Keras, Pandas and Sci-kit Learning libraries to run the internal work. The proposed approach improved prediction with [Formula: see text] accuracy for Yelp datasets of businesses across 11 metropolitan areas in four countries, along with a mean absolute error (MAE) of [Formula: see text], precision at [Formula: see text], recall at [Formula: see text] and F1-Score at [Formula: see text]. Our model shows scalability advantage and how organizations can revolutionize their recommender systems to attract possible customers and increase patronage. Also, the proposed similarity algorithm was compared to conventional algorithms to estimate its performance and accuracy in terms of its root mean square error (RMSE), precision and recall. Results of this experiment indicate that the similarity recommendation algorithm performs better than the conventional algorithm and enhances recommendation accuracy.

Attribute interaction aware matrix factorization method for recommendation

Matrix factorization (MF) models are effective and easy to expand and are widely used in industry, such as rating prediction and item recommendation. The basic MF model is relatively simple. In practical applications, side information such as attributes or implicit feedback is often combined to improve accuracy by modifying the model and optimizing the algorithm. In this paper, we propose an attribute interaction-aware matrix factorization (AIMF) method for recommendation tasks. We partition the original rating matrix into different sub-matrices according to the attribute interactions, train each sub-matrix independently, and merge all the latent vectors to generate the final score. Since the generated sub-matrices vary in size, an adaptive regularization coefficient optimization strategy and an adaptive latent vector dimension optimization strategy are proposed for sub-matrix training, and a variety of latent vector merging methods are put forward. The method AIMF has two advantages. When the original rating matrix is particularly large, the training time complexity of the MF-based model becomes higher and the update cost of the model is also higher. In AIMF, because each sub-matrix is usually much smaller than the original rating matrix, the training time complexity is greatly reduced after using parallel computing technology. Secondly, in AIMF, it is not necessary to modify the matrix factorization model to incorporate attributes and their interactive information into the model to improve the performance. The experimental results on the two classic public datasets MovieLens 1M and MovieLens 100k show that AIMF can not only effectively improve the accuracy of recommendation, but also make full use of parallel computing technology to improve training efficiency without modifying the matrix factorization model.

Enhancing long tail item recommendation in collaborative filtering: An econophysics-inspired approach

• A novel viewpoint of econophysics principles is formulated to address long tail effect. • Rating injection strategy inspired from econophysics principles is proposed. • Performance of the proposed method is evaluated on long tail and non-long tail items. • Proposed approach immensely improved the number of long tail items in recommendations. • The proposed principles can be applied as an add-on to state-of-the-art recommendation technique. Recommender systems have been immensely successful in overcoming information overload problem through personalized suggestions to consumers. Traditional recommendation algorithms tend to recommend more popular items. A significant number of items in an enterprise are non-popular (long tail items) due to lack of visibility in recommendations. These long tail items are left unsold and result in a significant loss to the business. The consumers on the other end are deprived of receiving relevant item recommendations. In this paper, we propose two approaches inspired from econophysics to recommend long tail items. The proposed approaches selectively inject ratings to the long tail items to diminish the bias towards the popular items by utilizing the existing rating information. Subsequently, the injected rating datasets are used to provide recommendations. The results on real-world datasets show that the proposed approaches outperform the existing techniques in mitigating long tail effect with little or no drop in accuracy.

Methodological quality of multivariate prognostic models for intracranial haemorrhages in intensive care units: a systematic review

ObjectivesPatients with severe spontaneous intracranial haemorrhages, managed in intensive care units, face ethical issues regarding the difficulty of anticipating their recovery. Prognostic tools help clinicians in counselling patients and relatives...

A generic Bayesian-based framework for enhancing top-N recommender algorithms

Personalized top-N recommender algorithms have been investigated widely in decades. The core task of different recommender algorithms is to estimate user-item preference scores and then to suggest, for each user, top-N items that have high preference scores. However, little attention was paid to the recommendation of items with low preference scores. In this work, we use the bayesian estimation theory to build the relationship between the estimated preference scores and the actual recommendation accuracy. We then propose a novel metric RNR (Recall-to-Noise Ratio) to recommend items with low estimated preference scores. An interesting counterintuitive phenomenon is found that user-item links with low preference scores may achieve higher accuracy than high preference score ones in the recommendation. Based on RNR, we design a generic framework that could recommend user-item links that have low preference scores without the loss of recommendation accuracy. The effectiveness of the proposed framework is illustrated by both theoretical analysis and empirical experiments.

Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-start Users

Static recommendation methods like collaborative filtering suffer from the inherent limitation of performing real-time personalization for cold-start users. Online recommendation, e.g., multi-armed bandit approach, addresses this limitation by interactively exploring user preference online and pursuing the exploration-exploitation (EE) trade-off. However, existing bandit-based methods model recommendation actions homogeneously. Specifically, they only consider the items as the arms, being incapable of handling the item attributes , which naturally provide interpretable information of user’s current demands and can effectively filter out undesired items. In this work, we consider the conversational recommendation for cold-start users, where a system can both ask the attributes from and recommend items to a user interactively. This important scenario was studied in a recent work [54]. However, it employs a hand-crafted function to decide when to ask attributes or make recommendations. Such separate modeling of attributes and items makes the effectiveness of the system highly rely on the choice of the hand-crafted function, thus introducing fragility to the system. To address this limitation, we seamlessly unify attributes and items in the same arm space and achieve their EE trade-offs automatically using the framework of Thompson Sampling. Our Conversational Thompson Sampling (ConTS) model holistically solves all questions in conversational recommendation by choosing the arm with the maximal reward to play. Extensive experiments on three benchmark datasets show that ConTS outperforms the state-of-the-art methods Conversational UCB (ConUCB) [54] and Estimation—Action—Reflection model [27] in both metrics of success rate and average number of conversation turns.

Improving the Applicability and Feasibility of Clinical Practice Guidelines in Primary Care: Recommendations for Guideline Development and Implementation.

ObjectiveTo give recommendations for the development of primary care clinical practice guideline (CPG) to improve applicability and feasibility of primary care CPGs in China.DesignA two-round Delphi survey.MethodsA two-round Delphi survey including guideline development methodologists and clinical practitioners from six countries was conducted. In round one, participants were asked to raise special considerations for the development of primary care CPGs through open-ended questions. In round two, participants were asked to rate the level of agreement on each recommendation item generated by round one and to raise additional recommendations. Opinions from participants were reviewed by thematic analysis. Integrated results from the Delphi survey were validated by participants.ResultsThe necessity of developing recommendations for the development of primary care CPGs were consistently recognized by participants. The main recommendations of guideline development were generated as follows: (1) considering the context of primary care institutions and the applicability of existing guidelines for primary care in planning guideline; (2) involving primary care practitioners and patients in guideline groups; (3) considering the variation of health-care resources between primary care settings when developing recommendations; (4) presenting the difference of recommendations between primary care CPG and general CPG; (5) implementing more active education and training; and (6) considering the changing of primary care medical resource when updating guideline.ConclusionIn this study, we present recommendations to inform the development of clinical practice guidelines in primary care settings. Next steps will include merging these recommendations with general guideline development methods to inform the development of guidelines for primary care.

BSO-MV: An Optimized Multiview Clustering Approach for Items Recommendation in Social Networks

Clustering-based approaches have been demonstrated to be efficient and scalable to large-scale data sets. However, clustering-based recommender systems suffer from relatively low accuracy and coverage. To address these issues, we propose in this article an optimized multiview clustering approach for the recommendation of items in social networks. First, the selection of the initial medoids is optimized using the Bees Swarm optimization algorithm (BSO) in order to generate better partitions (i.e. refining the quality of medoids according to the objective function). Then, the multiview clustering (MV) is applied, where users are iteratively clustered from the views of both rating patterns and social information (i.e. friendships and trust). Finally, a framework is proposed for testing the different alternatives, namely: (1) the standard recommendation algorithms; (2) the clustering-based and the optimized clustering-based recommendation algorithms using BSO; and (3) the MV and the optimized MV (BSO-MV) algorithms. Experimental results conducted on two real-world datasets demonstrate the effectiveness of the proposed BSO-MV algorithm in terms of improving accuracy, as it outperforms the existing related approaches and baselines.

Advances and Challenges for Model and Data Engineering

Advances and Challenges for Model and Data Engineering

Recommendation System Based on Generative Adversarial Network with Graph Convolutional Layers

A graph convolutional generative adversarial network (GCGAN) is proposed to provide recommendations for new users or items. To maintain scalability, the discriminator was improved to capture the latent features of users and items, using graph convolution from a minibatch-sized bipartite graph. In the experiment using MovieLens, it was confirmed that the proposed GCGAN had better performance than the conventional CFGAN, when MovieLens 1M was employed with sufficient data. The proposed method is characterized in such a manner that it can learn domain information of both, users and items, and it does not require to relearn a model for a new node. Further, it can be developed for any service having such conditions, in the information recommendation field.

New Vector-Space Embeddings for Recommender Systems

In this work, we propose a novel recommender system model based on a technology commonly used in natural language processing called word vector embedding. In this technology, a word is represented by a vector that is embedded in an n-dimensional space. The distance between two vectors expresses the level of similarity/dissimilarity of their underlying words. Since item similarities and user similarities are the basis of designing a successful collaborative filtering, vector embedding seems to be a good candidate. As opposed to words, we propose a vector embedding approach for learning vectors for items and users. There have been very few recent applications of vector embeddings in recommender systems, but they have limitations in the type of formulations that are applicable. We propose a novel vector embedding that is versatile, in the sense that it is applicable for the prediction of ratings and for the recommendation of top items that are likely to appeal to users. It could also possibly take into account content-based features and demographic information. The approach is a simple relaxation algorithm that optimizes an objective function, defined based on target users’, items’ or joint user–item’s similarities in their respective vector spaces. The proposed approach is evaluated using real life datasets such as “MovieLens”, “ModCloth”, “Amazon: Magazine_Subscriptions” and “Online Retail”. The obtained results are compared with some of the leading benchmark methods, and they show a competitive performance.

Vulcont: A recommender system based on context history ontology

The usage of recommenders systems is already widespread. Every day people are exposed to different item offerings based on the prediction of their interests and decisions. Context information, such as location, goals, and close entities, plays a key role in the recommendations' accuracy. The use of context histories allows one to identify similar context histories and predict contexts. This article proposes Vulcont, a recommender system based on a context histories' ontology. Vulcont merges the benefits of ontology reasoning with context histories to measure the context history similarity, based on the semantic and ontology properties provided by the context’s domain. Vulcont considers synonymous and classes' relations to measure similarity. After that, a collaborative filtering approach identifies sequences' frequency to identify potential items for recommendation. The proposed recommendation is evaluated and discussed in four scenarios in an offline experiment, which explores the semantic value of context histories. The main contribution of Vulcont is the use of semantic relations and the properties of ontology in a similarity measurement of context histories, which is a data structure more complete than that of single contexts.

Variational learning from implicit bandit feedback

Recommendations are prevalent in Web applications (e.g., search ranking, item recommendation, advertisement placement). Learning from bandit feedback is challenging due to the sparsity of feedback limited to system-provided actions. In this work, we focus on batch learning from logs of recommender systems involving both bandit and organic feedbacks. We develop a probabilistic framework with a likelihood function for estimating not only explicit positive observations but also implicit negative observations inferred from the data. Moreover, we introduce a latent variable model for organic-bandit feedbacks to robustly capture user preference distributions. Next, we analyze the behavior of the new likelihood under two scenarios, i.e., with and without counterfactual re-weighting. For speedier item ranking, we further investigate the possibility of using Maximum-a-Posteriori (MAP) estimate instead of Monte Carlo (MC)-based approximation for prediction. Experiments on both real datasets as well as data from a simulation environment show substantial performance improvements over comparable baselines.

Guidelines for the diagnosis and treatment of pancreatic cancer in China(2021)

The incidence of pancreatic cancer has been rising worldwide,while its clinical diagnosis and treatment remain a great challenge. To present the update and improvements in the clinical diagnosis and treatment of pancreatic cancer in recent years, Chinese Pancreatic Surgery Association,Chinese Society of Surgery,Chinese Medical Association updated "Guidelines for the diagnosis and treatment of pancreatic cancer in China （2021）" based on the Guideline of Management of Pancreatic Cancer in China which had been published in 2014. This updated guideline was formulated after reviewing evidence-based and problem-oriented literatures published from 2015-2021,mainly focusing on highlight issues regarding diagnosis and surgical treatment of pancreatic cancer,conversion strategies for locally advanced pancreatic cancer,treatment of pancreatic cancer with oligo metastasis,adjuvant and neoadjuvant therapy,standardized processing of surgical specimens and evaluation of surgical margin status,systemic treatment for unresectable pancreatic cancer,genetic testing,as well as postoperative follow up of patients with pancreatic cancer. Forty recommendation items were finally proposed based on the above issues,and the quality of evidence and strength of recommendations were graded using the Grades of Recommendation,Assessment,Development,and Evaluation system. This guideline aims to improve the ability of clinical diagnosis and therapy,especially surgical treatment of pancreatic cancer in China,and furtherly improve the prognosis of pancreatic cancer patients.

Clinical Practice Guideline for Postoperative Rehabilitation in Older Patients With Hip Fractures.

ObjectiveThe incidence of hip fractures is increasing worldwide with the aging population, causing a challenge to healthcare systems due to the associated morbidities and high risk of mortality. After hip fractures in frail geriatric patients, existing comorbidities worsen and new complications are prone to occur. Comprehensive rehabilitation is essential for promoting physical function recovery and minimizing complications, which can be achieved through a multidisciplinary approach. Recommendations are required to assist healthcare providers in making decisions on rehabilitation post-surgery. Clinical practice guidelines regarding rehabilitation (physical and occupational therapies) and management of comorbidities/complications in the postoperative phase of hip fractures have not been developed. This guideline aimed to provide evidence-based recommendations for various treatment items required for proper recovery after hip fracture surgeries. MethodsReflecting the complex perspectives associated with rehabilitation post-hip surgeries, 15 key questions (KQs) reflecting the complex perspectives associated with post-hip surgery rehabilitation were categorized into four areas: multidisciplinary, rehabilitation, community-care, and comorbidities/complications. Relevant literature from four databases (PubMed, EMBASE, Cochrane Library, and KoreaMed) was searched for articles published up to February 2020. The evidence level and recommended grade were determined according to the grade of recommendation assessment, development, and evaluation method. ResultsA multidisciplinary approach, progressive resistance exercises, and balance training are strongly recommended. Early ambulation, weigh-bearing exercises, activities of daily living training, community-level rehabilitation, management of comorbidities/complication prevention, and nutritional support were also suggested. This multidisciplinary approach reduced the total healthcare cost.ConclusionThis guideline presents comprehensive recommendations for the rehabilitation of adult patients after hip fracture surgery.

Accurate Item Recommendation Algorithm of itemrank based on tag and context information

The traditional itemrank recommendation algorithm only uses the two-dimensional relationship between user and item to achieve recommendation, without considering the important information (such as label information and context information) that plays an important role in the association between user and item, so the accuracy of recommendation needs to be improved. Therefore, in this paper, tag information and context information are integrated into the link relationship between user and item, and a user–context–item tag association graph is constructed. An itemrank recommendation algorithm is proposed by integrating tag and context information. Firstly, ap-ml-rbf-relm model is used to determine user labels, and then deep neural network is used to determine the relationship between tags. Finally, item and label are calculated The association weight between the signatures is used to implement the recommendation service for the target users. Experimental results on public datasets show that the proposed algorithm is better than the traditional recommendation algorithm in recommendation accuracy.

Pairwise deep learning to rank for top-N recommendation

Recent researches indicate that pairwise learning to rank methods could achieve high performance in dealing with data sparsity and long tail distribution in item recommendation, although suffering from problems such as high computational complexity and insufficient samples, which may cause low convergence and inaccuracy. To further improve the performance in computational capability and recommendation accuracy, in this article, a novel deep neural network based recommender architecture referred to as PDLR is proposed, in which the item corpus will be partitioned into two collections of positive instances and negative items respectively, and pairwise comparison will be performed between the positive instances and negative samples to learn the preference degree for each user. With the powerful capability of neural network, PDLR could capture rich interactions between each user and items as well as the intricate relations between items. As a result, PDLR could minimize the ranking loss, and achieve significant improvement in ranking accuracy. In practice, experimental results over four real world datasets also demonstrate the superiority of PDLR in contrast to state-of-the-art recommender approaches, in terms of Rec@N, Prec@N, AUC and NDCG@N.

Investigating the impact of recommender systems on user-based and item-based popularity bias

Recommender Systems are decision support tools that adopt advanced algorithms in order to help users to find less-explored items that can be interesting for them. While recommender systems may offer a range of attractive benefits, they may also intensify undesired effects, such as the Popularity Bias, where a few popular users/items get more popular and many unpopular users/items get more unpopular.In this paper, we study the impact of different recommender algorithms on the popularity bias in different application domains and recommendation scenarios. We have designed a comprehensive evaluation methodology by considering two different recommendation scenarios, i.e., the user-based scenario (e.g., recommending users to users to follow), and the item-based scenario (e.g., recommending items to users to consume). We have used two large datasets, Twitter and Movielens, and compared a wide range of classical and modern recommender algorithms by considering a diverse range of metrics, such as PR-AUC, RCE, Gini index, and Entropy Score.The results have shown a substantial difference between different scenarios and different recommendation domains. According to our observations, while the recommendation of users to users may increase the popularity bias in the system, the recommendation of items to users may indeed decrease it. Moreover, while we have measured a different level of popularity bias in different languages (i.e., English, Spanish, Portuguese, and Japaneses), the above-noted phenomena has been consistently observed in all of these languages.