Hybrid collaborative filtering methods for recommending search terms to clinicians.
Ontology highlight
ABSTRACT:
SUBMITTER: Ren Z
PROVIDER: S-EPMC7970303 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The past decade has seen substantial growth in online transactions. Accordingly, many professionals and researchers utilize deep learning models to design and develop recommender systems to suit the needs of online personal services. These systems can model the interactions between users and items. However, existing approaches focus on either modeling global or local item correlation and rarely consider both cases, thus failing to represent user-item correlation very well. Therefore, this article proposes a deep collaborative recommendation system based on a convolutional neural network with an outer product matrix and a hybrid feature selection module to capture local and global higher-order interaction between users and items. Moreover, we incorporated the weights of generalized matrix factorization to optimize the overall network performance and prevent overfitting. Finally, we conducted extensive experiments on two real-world datasets with different sparsity to confirm that our proposed approach outperforms the baseline methods we have used in the experiment.
| S-EPMC10496003 | biostudies-literature
Project description:MotivationHomology search for RNAs can use secondary structure information to increase power by modeling base pairs, as in covariance models, but the resulting computational costs are high. Typical acceleration strategies rely on at least one filtering stage using sequence-only search.ResultsHere we present the multi-segment CYK (MSCYK) filter, which implements a heuristic of ungapped structural alignment for RNA homology search. Compared to gapped alignment, this approximation has lower computation time requirements (O(N⁴) reduced to O(N³), and space requirements (O(N³) reduced to O(N²). A vector-parallel implementation of this method gives up to 100-fold speed-up; vector-parallel implementations of standard gapped alignment at two levels of precision give 3- and 6-fold speed-ups. These approaches are combined to create a filtering pipeline that scores RNA secondary structure at all stages, with results that are synergistic with existing methods.
| S-EPMC3208395 | biostudies-literature
Project description:As an important factor for improving recommendations, time information has been introduced to model users' dynamic preferences in many papers. However, the sequence of users' behaviour is rarely studied in recommender systems. Due to the users' unique behavior evolution patterns and personalized interest transitions among items, users' similarity in sequential dimension should be introduced to further distinguish users' preferences and interests. In this paper, we propose a new collaborative filtering recommendation method based on users' interest sequences (IS) that rank users' ratings or other online behaviors according to the timestamps when they occurred. This method extracts the semantics hidden in the interest sequences by the length of users' longest common sub-IS (LCSIS) and the count of users' total common sub-IS (ACSIS). Then, these semantics are utilized to obtain users' IS-based similarities and, further, to refine the similarities acquired from traditional collaborative filtering approaches. With these updated similarities, transition characteristics and dynamic evolution patterns of users' preferences are considered. Our new proposed method was compared with state-of-the-art time-aware collaborative filtering algorithms on datasets MovieLens, Flixster and Ciao. The experimental results validate that the proposed recommendation method is effective and outperforms several existing algorithms in the accuracy of rating prediction.
| S-EPMC4873175 | biostudies-literature
Project description:In bottom-up proteomics, data are acquired on peptides resulting from proteolysis. In XIC-based quantification, the quality of the protein abundance estimation depends on how peptide data are filtered and on which quantification method is used to sum up peptide intensities into protein abundances. So far, these two questions have been addressed independently. Here, we studied to which extent the relative performances of the quantification methods depend on the filters applied on peptide intensity data. To this end, we performed a spike-in experiment using Universal Protein Standard (UPS1) to evaluate the performances of five quantification methods, including TOP3, iBAQ, Average of all peptide intensities or log-intensities and intensity modeling, in five datasets obtained after application of four peptide filters based on peptide sharing between proteins, retention time variability, peptides occurrence and peptide intensity profiles. We showed that estimated protein abundances were not equally affected by filters depending on the computation mode (sum or average) and the type of data (intensity or log intensity) used in the quantification methods and that filters could have contrasting effects depending on the quantification objective (absolute or relative). Our results also indicate that intensity modeling was the most robust method, providing the best results in absence of any filter, but that the different quantification methods can reach similar performances when appropriate peptide filters are used. Altogether, our findings provide clues to best handle intensity data according to the quantification objective and to the experimental design.
2018-11-14 | PXD009740 | Pride
Project description:ImportanceHalf of emergency nurses report high burnout and intend to leave their job in the next year. Whether emergency nurses would recommend their workplace to other clinicians may be an important indicator of a hospital's ability to recruit clinicians.ObjectiveTo examine why emergency nurses do not recommend their hospital to other clinicians as a good place to work.Design, setting, and participantsThis qualitative study used directed content analysis of open-text responses (n = 142) from the RN4CAST-NY/IL survey of registered nurses licensed in New York and Illinois between April 13 and June 22, 2021. Inductive and deductive analytic approaches guided study theme development informed by the Social Ecological Model. The collected data were analyzed from April to June 2023.Main outcomes and measuresNurses who answered "probably not" or "definitely not" to the survey question, "Would you recommend your place of employment as a good place to work?" were prompted to provide a rationale in an open-text response.ResultsIn this qualitative study of 142 emergency nurses (mean [SD] age, 43.5 [12.5] years; 113 [79.6%] female; mean [SD] experience, 14.0 [12.2] years), 94 (66.2%) were licensed to work in New York and the other 48 (33.8%) in Illinois. Five themes and associated subthemes emerged from the data. Themes conveyed understaffing of nurses and ancillary support (theme 1: unlimited patients with limited support); inadequate responsiveness from unit management to work environment safety concerns (theme 2: unanswered calls for help); perceptions that nurses' licenses were in jeopardy given unsafe working conditions and compromised care quality (theme 3: license always on the line); workplace violence on a patient-to-nurse, clinician-to-nurse, and systems level (theme 4: multidimensional workplace violence); and nurse reports of being undervalued by hospital management and unfulfilled at work in delivering suboptimal care to patients in unsafe working conditions (theme 5: undervalued and unfulfilled).Conclusions and relevanceThis study found that emergency department nurses did not recommend their workplace to other clinicians as a good place to work because of poor nurse and ancillary staffing, nonresponsive hospital leadership, unsafe working conditions, workplace violence, and a lack of feeling valued. These findings inform aspects of the work environment that employers can address to improve nurse recruitment and retention.
| S-EPMC11004828 | biostudies-literature
Project description:ObjectiveA full-text search engine can be a useful tool for augmenting the reuse value of unstructured narrative data stored in electronic health records (EHR). A prominent barrier to the effective utilization of such tools originates from users' lack of search expertise and/or medical-domain knowledge. To mitigate the issue, the authors experimented with a 'collaborative search' feature through a homegrown EHR search engine that allows users to preserve their search knowledge and share it with others. This feature was inspired by the success of many social information-foraging techniques used on the web that leverage users' collective wisdom to improve the quality and efficiency of information retrieval.DesignThe authors conducted an empirical evaluation study over a 4-year period. The user sample consisted of 451 academic researchers, medical practitioners, and hospital administrators. The data were analyzed using a social-network analysis to delineate the structure of the user collaboration networks that mediated the diffusion of knowledge of search.ResultsThe users embraced the concept with considerable enthusiasm. About half of the EHR searches processed by the system (0.44 million) were based on stored search knowledge; 0.16 million utilized shared knowledge made available by other users. The social-network analysis results also suggest that the user-collaboration networks engendered by the collaborative search feature played an instrumental role in enabling the transfer of search knowledge across people and domains.ConclusionApplying collaborative search, a social information-foraging technique popularly used on the web, may provide the potential to improve the quality and efficiency of information retrieval in healthcare.
| S-EPMC3078661 | biostudies-literature
Project description:Many healthcare facilities enforce security on their electronic health records (EHRs) through a corrective mechanism: some staff nominally have almost unrestricted access to the records, but there is a strict ex post facto audit process for inappropriate accesses, i.e., accesses that violate the facility's security and privacy policies. This process is inefficient, as each suspicious access has to be reviewed by a security expert, and is purely retrospective, as it occurs after damage may have been incurred. This motivates automated approaches based on machine learning using historical data. Previous attempts at such a system have successfully applied supervised learning models to this end, such as SVMs and logistic regression. While providing benefits over manual auditing, these approaches ignore the identity of the users and patients involved in a record access. Therefore, they cannot exploit the fact that a patient whose record was previously involved in a violation has an increased risk of being involved in a future violation. Motivated by this, in this paper, we propose a collaborative filtering inspired approach to predicting inappropriate accesses. Our solution integrates both explicit and latent features for staff and patients, the latter acting as a personalized "finger-print" based on historical access patterns. The proposed method, when applied to real EHR access data from two tertiary hospitals and a file-access dataset from Amazon, shows not only significantly improved performance compared to existing methods, but also provides insights as to what indicates an inappropriate access.
| S-EPMC3967851 | biostudies-literature
Project description:A fundamental challenge in emotion research is measuring feeling states with high granularity and temporal precision without disrupting the emotion generation process. Here we introduce and validate a new approach in which responses are sparsely sampled and the missing data are recovered using a computational technique known as collaborative filtering (CF). This approach leverages structured covariation across individual experiences and is available in Neighbors, an open-source Python toolbox. We validate our approach across three different experimental contexts by recovering dense individual ratings using only a small subset of the original data. In dataset 1, participants (n=316) separately rated 112 emotional images on 6 different discrete emotions. In dataset 2, participants (n=203) watched 8 short emotionally engaging autobiographical stories while simultaneously providing moment-by-moment ratings of the intensity of their affective experience. In dataset 3, participants (n=60) with distinct social preferences made 76 decisions about how much money to return in a hidden multiplier trust game. Across all experimental contexts, CF was able to accurately recover missing data and importantly outperformed mean and multivariate imputation, particularly in contexts with greater individual variability. This approach will enable new avenues for affective science research by allowing researchers to acquire high dimensional ratings from emotional experiences with minimal disruption to the emotion-generation process.Supplementary informationThe online version contains supplementary material available at 10.1007/s42761-022-00161-2.
| S-EPMC9743951 | biostudies-literature
Project description:Glycopeptides in peptide or digested protein samples pose a number of analytical and bioinformatics challenges beyond those posed by unmodified peptides or peptides with smaller posttranslational modifications. Exact structural elucidation of glycans is generally beyond the capability of a single mass spectrometry experiment, so a reasonable level of identification for tandem mass spectrometry, taken by several glycopeptide software tools, is that of peptide sequence and glycan composition, meaning the number of monosaccharides of each distinct mass, e.g., HexNAc(2)Hex(5) rather than man5. Even at this level, however, glycopeptide analysis poses challenges: finding glycopeptide spectra when they are a tiny fraction of the total spectra; assigning spectra with unanticipated glycans, not in the initial glycan database; and finding, scoring, and labeling diagnostic peaks in tandem mass spectra. Here, we discuss recent improvements to Byonic, a glycoproteomics search program, that address these three issues. Byonic now supports filtering spectra by m/z peaks, so that the user can limit attention to spectra with diagnostic peaks, e.g., at least two out of three of 204.087 for HexNAc, 274.092 for NeuAc (with water loss), and 366.139 for HexNAc-Hex, all within a set mass tolerance, e.g., ± 0.01 Da. Also, new is glycan "wildcard" search, which allows an unspecified mass within a user-set mass range to be applied to N- or O-linked glycans and enables assignment of spectra with unanticipated glycans. Finally, the next release of Byonic supports user-specified peak annotations from user-defined posttranslational modifications. We demonstrate the utility of these new software features by finding previously unrecognized glycopeptides in publicly available data, including glycosylated neuropeptides from rat brain.
| S-EPMC8724605 | biostudies-literature
Project description:BackgroundIn the context of the COVID-19 infodemic, the global profusion of monikers and hashtags for COVID-19 have found their way into daily communication and contributed to a backlash against China and the Chinese people.ObjectiveThis study examines public engagement in crisis communication about COVID-19 during the early epidemic stage and the practical strategy of social mobilization to mitigate the infodemic.MethodsWe retrieved the unbiased values of the top-ranked search phrases between December 30, 2019, and July 15, 2020, which normalized the anonymized, categorized, and aggregated samples from Google Search data. This study illustrates the most-searched terms, including the official COVID-19 terms, the stigmatized terms, and other controls, to measure the collective behavioral propensities to stigmatized terms and to explore the global reaction to the COVID-19 epidemic in the real world. We calculated the ratio of the cumulative number of COVID-19 cases to the regional population as the cumulative rate (R) of a specific country or territory and calculated the Gini coefficient (G) to measure the collective heterogeneity of crowd behavior.ResultsPeople around the world are using stigmatizing terms on Google Search, and these terms were used earlier than the official names. Many stigmatized monikers against China (eg, "Wuhan pneumonia," G=0.73; "Wuhan coronavirus," G=0.60; "China pneumonia," G=0.59; "China coronavirus," G=0.52; "Chinese coronavirus," G=0.50) had high collective heterogeneity of crowd behavior between December 30, 2019, and July 15, 2020, while the official terms "COVID-19" (G=0.44) and "SARS-CoV-2" (G=0.42) have not become de facto standard usages. Moreover, the pattern of high consistent usage was observed in 13 territories with low cumulative rates (R) between January 16 and July 15, 2020, out of 58 countries and territories that have reported confirmed cases of COVID-19. In the scientific literature, multifarious naming practices may have provoked unintended negative impacts by stigmatizing Chinese people. The World Health Organization; the United Nations Educational, Scientific and Cultural Organization; and the media initiated campaigns for fighting back against the COVID-19 infodemic with the same mission but in diverse voices.ConclusionsInfodemiological analysis can articulate the collective propensities to stigmatized monikers across search behaviors, which may reflect the collective sentiment of backlash against China and Chinese people in the real world. The full-fledged official terms are expected to fight back against the resilience of negative perceptual bias amid the COVID-19 epidemic. Such official naming efforts against the infodemic should be met with a fair share of identification in scientific conventions and sociocultural paradigms. As an integral component of preparedness, appropriate nomenclatures should be duly assigned to the newly identified coronavirus, and social mobilization in a uniform voice is a priority for combating the next infodemic.
| S-EPMC7674145 | biostudies-literature