Deep learning based searching approach for RDF graphs.

PLoS One. 2020;15(3):e0230500

Authors: Soliman H

Abstract
The Internet is a remarkably complex technical system. Its rapid growth has also brought technical issues such as problems to information retrieval. Search engines retrieve requested information based on the provided keywords. Consequently, it is difficult to accurately find the required information without understanding the syntax and semantics of the content. Multiple approaches are proposed to resolve this problem by employing the semantic web and linked data techniques. Such approaches serialize the content using the Resource Description Framework (RDF) and execute the queries using SPARQL to resolve the problem. However, an exact match between RDF content and query structure is required. Although, it improves the keyword-based search; however, it does not provide probabilistic reasoning to find the semantic relationship between the queries and their results. From this perspective, in this paper, we propose a deep learning-based approach for searching RDF graphs. The proposed approach treats document requests as a classification problem. First, we preprocess the RDF graphs to convert them into N-Triples format. Second, bag-of-words (BOW) and word2vec feature modeling techniques are combined for a novel deep representation of RDF graphs. The attention mechanism enables the proposed approach to understand the semantic between RDF graphs. Third, we train a convolutional neural network for the accurate retrieval of RDF graphs using the deep representation. We employ 10-fold cross-validation to evaluate the proposed approach. The results show that the proposed approach is accurate and surpasses the state-of-the-art. The average accuracy, precision, recall, and f-measure are up to 97.12%, 98.17%, 95.56%, and 96.85%, respectively.

PMID: 32203547 [PubMed - as supplied by publisher]

Deep Saliency Hashing for Fine-grained Retrieval.

IEEE Trans Image Process. 2020 Mar 16;:

Authors: Jin S, Yao H, Sun X, Zhou S, Zhang L, Hua X

Abstract
In recent years, hashing methods have been proved to be effective and efficient for large-scale Web media search. However, the existing general hashing methods have limited discriminative power for describing fine-grained objects that share similar overall appearance but have a subtle difference. To solve this problem, we for the first time introduce the attention mechanism to the learning of fine-grained hashing codes. Specifically, we propose a novel deep hashing model, named deep saliency hashing (DSaH), which automatically mines salient regions and learns semantic-preserving hashing codes simultaneously. DSaH is a two-step end-to-end model consisting of an attention network and a hashing network. Our loss function contains three basic components, including the semantic loss, the saliency loss, and the quantization loss. As the core of DSaH, the saliency loss guides the attention network to mine discriminative regions from pairs of images.We conduct extensive experiments on both fine-grained and general retrieval datasets for performance evaluation. Experimental results on fine-grained datasets, including Oxford Flowers, Stanford Dogs, and CUB Birds demonstrate that our DSaH performs the best for the fine-grained retrieval task and beats the strongest competitor (DTQ) by approximately 10% on both Stanford Dogs and CUB Birds. DSaH is also comparable to several state-of-the-art hashing methods on CIFAR-10 and NUS-WIDE.

PMID: 32191885 [PubMed - as supplied by publisher]

NG-Tax 2.0: A Semantic Framework for High-Throughput Amplicon Analysis.

Front Genet. 2019;10:1366

Authors: Poncheewin W, Hermes GDA, van Dam JCJ, Koehorst JJ, Smidt H, Schaap PJ

Abstract
NG-Tax 2.0 is a semantic framework for FAIR high-throughput analysis and classification of marker gene amplicon sequences including bacterial and archaeal 16S ribosomal RNA (rRNA), eukaryotic 18S rRNA and ribosomal intergenic transcribed spacer sequences. It can directly use single or merged reads, paired-end reads and unmerged paired-end reads from long range fragments as input to generate de novo amplicon sequence variants (ASV). Using the RDF data model, ASV's can be automatically stored in a graph database as objects that link ASV sequences with the full data-wise and element-wise provenance, thereby achieving the level of interoperability required to utilize such data to its full potential. The graph database can be directly queried, allowing for comparative analyses of over thousands of samples and is connected with an interactive Rshiny toolbox for analysis and visualization of (meta) data. Additionally, NG-Tax 2.0 exports an extended BIOM 1.0 (JSON) file as starting point for further analyses by other means. The extended BIOM file contains new attribute types to include information about the command arguments used, the sequences of the ASVs formed, classification confidence scores and is backwards compatible. The performance of NG-Tax 2.0 was compared with DADA2, using the plugin in the QIIME 2 analysis pipeline. Fourteen 16S rRNA gene amplicon mock community samples were obtained from the literature and evaluated. Precision of NG-Tax 2.0 was significantly higher with an average of 0.95 vs 0.58 for QIIME2-DADA2 while recall was comparable with an average of 0.85 and 0.77, respectively. NG-Tax 2.0 is written in Java. The code, the ontology, a Galaxy platform implementation, the analysis toolbox, tutorials and example SPARQL queries are freely available at http://wurssb.gitlab.io/ngtax under the MIT License.

PMID: 32117417 [PubMed]

A Dynamic Dashboarding Application for Fleet Monitoring Using Semantic Web of Things Technologies.

Sensors (Basel). 2020 Feb 20;20(4):

Authors: Hautte SV, Moens P, Herwegen JV, Paepe D, Steenwinckel B, Verstichel S, Ongenae F, Hoecke SV

Abstract
In industry, dashboards are often used to monitor fleets of assets, such as trains, machines or buildings. In such industrial fleets, the vast amount of sensors evolves continuously, new sensor data exchange protocols and data formats are introduced, new visualization types may need to be introduced and existing dashboard visualizations may need to be updated in terms of displayed sensors. These requirements motivate the development of dynamic dashboarding applications. These, as opposed to fixed-structure dashboard applications, allow users to create visualizations at will and do not have hard-coded sensor bindings. The state-of-the-art in dynamic dashboarding does not cope well with the frequent additions and removals of sensors that must be monitored-these changes must still be configured in the implementation or at runtime by a user. Also, the user is presented with an overload of sensors, aggregations and visualizations to select from, which may sometimes even lead to the creation of dashboard widgets that do not make sense. In this paper, we present a dynamic dashboard that overcomes these problems. Sensors, visualizations and aggregations can be discovered automatically, since they are provided as RESTful Web Things on a Web Thing Model compliant gateway. The gateway also provides semantic annotations of the Web Things, describing what their abilities are. A semantic reasoner can derive visualization suggestions, given the Thing annotations, logic rules and a custom dashboard ontology. The resulting dashboarding application automatically presents the available sensors, visualizations and aggregations that can be used, without requiring sensor configuration, and assists the user in building dashboards that make sense. This way, the user can concentrate on interpreting the sensor data and detecting and solving operational problems early.

PMID: 32093134 [PubMed]

Epidemiology of sepsis in cancer patients in Victoria, Australia: a population-based study using linked data.

Aust N Z J Public Health. 2020 Feb;44(1):53-58

Authors: Te Marvelde L, Whitfield A, Shepheard J, Read C, Milne RL, Whitfield K

Abstract
OBJECTIVE: To determine the clinical characteristics, outcomes and longitudinal trends of sepsis occurring in cancer patients.
METHOD: Retrospective study using statewide Victorian Cancer Registry data linked to various administrative datasets.
RESULTS: Among 215,763 incident cancer patients, incidence of sepsis within one year of cancer diagnosis was estimated at 6.4%. The incidence of sepsis was higher in men, younger patients, patients diagnosed with haematological malignancies and those with de novo metastatic disease. Of the 13,316 patients with a first admission with sepsis, 55% had one or more organ failures, 29% required care within an intensive care unit and 13% required mechanical ventilation. Treatments associated with the highest sepsis incidence were stem cell/bone marrow transplant (33%), major surgery (4.4%), chemotherapy (1.1%) and radical radiotherapy (0.6%). The incidence of sepsis with organ failure increased between 2008 and 2015, while 90-day mortality decreased.
CONCLUSIONS: Sepsis in patients with cancer has high mortality and occurs most frequently in the first year after cancer diagnosis. Implications for public health: The number of cancer patients diagnosed with sepsis is expected to increase, causing a substantial burden on patients and the healthcare system.

PMID: 31535416 [PubMed - indexed for MEDLINE]

IoT-Stream: A Lightweight Ontology for Internet of Things Data Streams and Its Use with Data Analytics and Event Detection Services.

Sensors (Basel). 2020 Feb 11;20(4):

Authors: Elsaleh T, Enshaeifar S, Rezvani R, Acton ST, Janeiko V, Bermudez-Edo M

Abstract
With the proliferation of sensors and IoT technologies, stream data are increasingly stored and analyzed, but rarely combined, due to the heterogeneity of sources and technologies. Semantics are increasingly used to share sensory data, but not so much for annotating stream data. Semantic models for stream annotation are scarce, as generally semantics are heavy to process and not ideal for Internet of things (IoT) environments, where the data are frequently updated. We present a light model to semantically annotate streams, IoT-Stream. It takes advantage of common knowledge sharing of the semantics, but keeping the inferences and queries simple. Furthermore, we present a system architecture to demonstrate the adoption the semantic model, and provide examples of instantiation of the system for different use cases. The system architecture is based on commonly used architectures in the field of IoT, such as web services, microservices and middleware. Our system approach includes the semantic annotations that take place in the pipeline of IoT services and sensory data analytics. It includes modules needed to annotate, consume, and query data annotated with IoT-Stream. In addition to this, we present tools that could be used in conjunction to the IoT-Stream model and facilitate the use of semantics in IoT.

PMID: 32053898 [PubMed - in process]

ClinEpiDB: an open-access clinical epidemiology database resource encouraging online exploration of complex studies.

Gates Open Res. 2019;3:1661

Authors: Ruhamyankaka E, Brunk BP, Dorsey G, Harb OS, Helb DA, Judkins J, Kissinger JC, Lindsay B, Roos DS, San EJ, Stoeckert CJ, Zheng J, Tomko SS

Abstract
The concept of open data has been gaining traction as a mechanism to increase data use, ensure that data are preserved over time, and accelerate discovery. While epidemiology data sets are increasingly deposited in databases and repositories, barriers to access still remain. ClinEpiDB was constructed as an open-access online resource for clinical and epidemiologic studies by leveraging the extensive web toolkit and infrastructure of the Eukaryotic Pathogen Database Resources (EuPathDB; a collection of databases covering 170+ eukaryotic pathogens, relevant related species, and select hosts) combined with a unified semantic web framework. Here we present an intuitive point-and-click website that allows users to visualize and subset data directly in the ClinEpiDB browser and immediately explore potential associations. Supporting study documentation aids contextualization, and data can be downloaded for advanced analyses. By facilitating access and interrogation of high-quality, large-scale data sets, ClinEpiDB aims to spur collaboration and discovery that improves global health.

PMID: 32047873 [PubMed]

eWoT: A Semantic Interoperability Approach for Heterogeneous IoT Ecosystems Based on the Web of Things.

Sensors (Basel). 2020 Feb 04;20(3):

Authors: Cimmino A, Poveda-Villalón M, García-Castro R

Abstract
With the constant growth of Internet of Things (IoT) ecosystems, allowing them to interact transparently has become a major issue for both the research and the software development communities. In this paper we propose a novel approach that builds semantically interoperable ecosystems of IoT devices. The approach provides a SPARQL query-based mechanism to transparently discover and access IoT devices that publish heterogeneous data. The approach was evaluated in order to prove that it provides complete and correct answers without affecting the response time and that it scales linearly in large ecosystems.

PMID: 32033027 [PubMed - in process]

Lightweight Data-Security Ontology for IoT.

Sensors (Basel). 2020 Feb 01;20(3):

Authors: Gonzalez-Gil P, Martinez JA, Skarmeta AF

Abstract
Although current estimates depict steady growth in Internet of Things (IoT), many works portray an as yet immature technology in terms of security. Attacks using low performance devices, the application of new technologies and data analysis to infer private data, lack of development in some aspects of security offer a wide field for improvement. The advent of Semantic Technologies for IoT offers a new set of possibilities and challenges, like data markets, aggregators, processors and search engines, which rise the need for security. New regulations, such as GDPR , also call for novel approaches on data-security, covering personal data. In this work, we present DS4IoT, a data-security ontology for IoT, which covers the representation of data-security concepts with the novel approach of doing so from the perspective of data and introducing some new concepts such as regulations, certifications and provenance, to classical concepts such as access control methods and authentication mechanisms. In the process we followed ontological methodologies, as well as semantic web best practices, resulting in an ontology to serve as a common vocabulary for data annotation that not only distinguishes itself from previous works by its bottom-up approach, but covers new, current and interesting concepts of data-security, favouring implicit over explicit knowledge representation. Finally, this work is validated by proof of concept, by mapping the DS4IoT ontology to the NGSI-LD data model, in the frame of the IoTCrawler EU project.

PMID: 32024127 [PubMed - in process]

Patient and Kidney Allograft Survival with National Kidney Paired Donation.

Clin J Am Soc Nephrol. 2020 Jan 28;:

Authors: Leeser DB, Thomas AG, Shaffer AA, Veale JL, Massie AB, Cooper M, Kapur S, Turgeon N, Segev DL, Waterman AD, Flechner SM

Abstract
BACKGROUND AND OBJECTIVES: In the United States, kidney paired donation networks have facilitated an increasing proportion of kidney transplants annually, but transplant outcome differences beyond 5 years between paired donation and other living donor kidney transplant recipients have not been well described.
DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: Using registry-linked data, we compared National Kidney Registry (n=2363) recipients to control kidney transplant recipients (n=54,497) (February 2008 to December 2017). We estimated the risk of death-censored graft failure and mortality using inverse probability of treatment weighted Cox regression. The parsimonious model adjusted for recipient factors (age, sex, black, race, body mass index ≥30 kg/m2, diabetes, previous transplant, preemptive transplant, public insurance, hepatitis C, eGFR, antibody depleting induction therapy, year of transplant), donor factors (age, sex, Hispanic ethnicity, body mass index ≥30 kg/m2), and transplant factors (zero HLA mismatch).
RESULTS: National Kidney Registry recipients were more likely to be women, black, older, on public insurance, have panel reactive antibodies >80%, spend longer on dialysis, and be previous transplant recipients. National Kidney Registry recipients were followed for a median 3.7 years (interquartile range, 2.1-5.6; maximum 10.9 years). National Kidney Registry recipients had similar graft failure (5% versus 6%; log-rank P=0.2) and mortality (9% versus 10%; log-rank P=0.4) incidence compared with controls during follow-up. After adjustment for donor, recipient, and transplant factors, there no detectable difference in graft failure (adjusted hazard ratio, 0.95; 95% confidence interval, 0.77 to 1.18; P=0.6) or mortality (adjusted hazard ratio, 0.86; 95% confidence interval, 0.70 to 1.07; P=0.2) between National Kidney Registry and control recipients.
CONCLUSIONS: Even after transplanting patients with greater risk factors for worse post-transplant outcomes, nationalized paired donation results in equivalent outcomes when compared with control living donor kidney transplant recipients.

PMID: 31992572 [PubMed - as supplied by publisher]

Dataset of ontology competency questions to SPARQL-OWL queries translations.

Data Brief. 2020 Apr;29:105098

Authors: Potoniec J, Wiśniewski D, Ławrynowicz A, Keet CM

Abstract
This data article reports on a new set of 234 competency questions for ontology development and their formalisation into a set of 131 SPARQL-OWL queries. This is the largest set of competency questions with their linked queries to date, covering several ontologies of different type in different subject domains developed by different groups of question authors and ontology developers. The dataset is focused specifically on the ontology TBox (terminological part). The dataset may serve as a manually created gold standard for testing and benchmarking, research into competency questions and querying ontologies, and tool development. The data is available in Mendeley Data. Its analysis is presented in "Analysis of Ontology Competency Questions and their formalizations in SPARQL-OWL" [15].

PMID: 31989008 [PubMed]

Explaining an Influential Model of the Significant Relationship Between Religion, Spirituality, and Environmental Peace in Mosque Interior Architecture.

J Relig Health. 2020 Jan 21;:

Authors: MahdiNejad JE, Azemati H, Sadeghi Habibabad A

Abstract
Investigating the components of environmental peace in an architectural work, especially Islamic mosques, requires a detailed understanding of this concept and its influential factors. In the architecture of the mosques of the past, certain patterns have always followed a continuous trend that made a logical relationship with the time before and after, but this continuity and trend are not seen today. The purpose of this study was to investigate the relationship of environmental peace from two aspects of religion and spirituality. Religion means comprehensive instructions and complete guidelines that, on the one hand, show the goal and teaches the human being how to achieve it, and on the other hand, help the human being on problems that are difficult to understand by universal means of understanding (reason, experience, and intuition). Therefore, the identification of the true ultimate goal in human life as well as the determination of the intermediate goals that indicate the path to the ultimate goal is possible only through the recognition and adherence to the right religion, and this fact shows the close relationship between religion and spirituality. The research method investigates the relationship between variables through a correlation method and then through structural equations. The statistical population was selected based on the Cochran formula including 120 professors and postgraduate students in architecture and Islamic architecture of Tehran Universities. The research tool was a web-based questionnaire and its link was made available to the statistical community online. The structural equation method was used in SPSS and Amos software to test the regression and fitting test model. Pearson correlation test was also used to determine the relationship between research variables. The results show that the model of the influence of "religion" factors in enhancing "environmental peace" through the mediating variable of "spirituality" explains these relationships; in other words, in this indirect causal relation, enhancement of semantic factors mediated by "spirituality" factors enhances environmental peace in architecture.

PMID: 31965465 [PubMed - as supplied by publisher]

Effect of cochlear implantation on language development and assessment of the quality of studies in this field: A systematic review.

Med J Islam Repub Iran. 2019;33:107

Authors: Khoramian S, Soleymani Z, Keramati N, Motasaddi Zarandy M

Abstract
Background: Cochlear implantation (CI) is an achievement that facilitates the acquisition of language skills in deaf children throughout the world. The use of this technology has a positive effect on all components of language acquisition (syntax, semantic, pragmatic, etc.). However, this positive impact is influenced by various factors. Understanding the strengths and weaknesses of studies on the development of language abilities can help improve these studies. Consequently, in the future, it will lead to the improvement of language rehabilitation in these children. Limited studies on children with CI in have been done so far. This article summarized the outcomes of scientific articles on the clinical efficacy of CI on Persian speaking children. This study also provided a clear picture of these studies by examining the quality of their methodologies and tools. Methods: Articles indexed in Google Scholar, Web of Science, Medline, Scopus and Iranian databases (Danesh Gostar, Magiran, and SID) were searched using keywords "language," "Cochlear implant", "Persian/ Farsi" in English and Persian languages with "and/or". Original articles investigated on children younger than 13 years old with hearing impairment and CI were included. Results: Five hundred and twenty-three articles were found based on the keywords. Among all of these, 485 were excluded due to the title and the abstract; we selected 38, of which 24 were repeated. Finally, 14 articles remained. We reviewed the articles based on the preferred reporting items for systematic review and meta-analysis (PRISMA) and checklist and Grading of Recommendations, Assessment, Development, and Evaluations (GRADE). Conclusion: Similar to international studies, Persian speaking children with CI have slower language development than their peers with normal hearing, but they are better than their peers who use hearing aids. The results of reviewing on quality of the articles showed that the studies could not meet reasonable quality because of the lack of a standard test in different aspects of Persian language and the absence of patients' databanks. These results also can be used by other nationalities that recently have started surveys on children with CIs.

PMID: 31934567 [PubMed]

Comprenhensive analysis of rule formalisms to represent clinical guidelines: Selection criteria and case study on antibiotic clinical guidelines.

Artif Intell Med. 2020 Jan 09;:101741

Authors: Iglesias N, Juarez JM, Campos M

Abstract
BACKGROUND: The over-use of antibiotics in clinical domains is causing an alarming increase in bacterial resistance, thus endangering their effectiveness as regards the treatment of highly recurring severe infectious diseases. Whilst Clinical Guidelines (CGs) focus on the correct prescription of antibiotics in a narrative form, Clinical Decision Support Systems (CDSS) operationalize the knowledge contained in CGs in the form of rules at the point of care. Despite the efforts made to computerize CGs, there is still a gap between CGs and the myriad of rule technologies (based on different logic formalisms) that are available to implement CDSSs in real clinical settings.
OBJECTIVE: To helpCDSS designers to determine the most suitable rule-based technology (medical-oriented rules, production rules and semantic web rules) with which to model knowledge from CGs for the prescription of antibiotics. We propose a framework of criteria for this purpose that is extensible to more generic CGs.
MATERIALS AND METHODS: Our proposal is based on the identification of core technical requirements extracted from both literature and the analysis of CGs for antibiotics, establishing three dimensions for analysis: language expressivity, interoperability and industrial aspects. We present a case study regarding the John Hopkins Hospital (JHH) Antibiotic Guidelines for Urinary Tract Infection (UTI), a highly recurring hospital acquired infection. We have adopted our framework of criteria in order to analyse and implement these CGs using various rule technologies: HL7 Arden Syntax, general-purpose Production Rules System (Drools), HL7 standard Rule Interchange Format (RIF), Semantic Web Rule Language (SWRL) and SParql Inference Notation (SPIN) rule extensions (implementing our own ontology for UTI).
RESULTS: We have identified the main criteria required to attain a maintainable and cost-affordable computable knowledge representation for CGs. We have represented the JHH UTI CGs knowledge in a total of 12 Arden Syntax MLMs, 81 Drools rules and 154 ontology classes, properties and individuals. Our experiments confirm the relevance of the proposed set of criteria and show the level of compliance of the different rule technologies with the JHH UTI CGs knowledge representation.
CONCLUSIONS: The proposed framework of criteria may help clinical institutions to select the most suitable rule technology for the representation of CGs in general, and for the antibiotic prescription domain in particular, depicting the main aspects that lead to Computer Interpretable Guidelines (CIGs), such as Logic expressivity (Open/Closed World Assumption, Negation-As-Failure), Temporal Reasoning and Interoperability with existing HIS and clinical workflow. Future work will focus on providing clinicians with suggestions regarding new potential steps for CGs, considering process mining approaches and CGs Process Workflows, the use of HL7 FHIR for HIS interoperability and the representation of Knowledge-as- a-Service (KaaS).

PMID: 31928849 [PubMed - as supplied by publisher]

STAT: A Web-based Semantic Text Annotation Tool to Assist Building Mental Health Knowledge Base.

IEEE Int Conf Healthc Inform. 2019 Jun;2019:

Authors: He X, Zhang H, Yang X, Guo Y, Bian J

Abstract
Mental health problems are serious among American adults and many of them are turning to the Internet for help. However, online mental health information is not well-organized and in low quality. We are building a mental health knowledge base (MHKB) with evidence-based information extracted from scientific literature manually, but lacking efficiency. We envision to leverage collective wisdoms through crowdsourcing to speed up the curation of MHKB. In order to integrate with crowdsourcing platforms, we designed and prototyped a web-based annotation tool, STAT (Semantic Text Annotation Tool), with real-time annotation recommendation and annotation quality analysis, to facilitate management of laypeople annotators recruited through crowdsourcing to complete the necessary annotation tasks.

PMID: 31903451 [PubMed]

A literature review of current technologies on health data integration for patient-centered health management.

Health Informatics J. 2019 Dec 30;:1460458219892387

Authors: Peng C, Goswami P, Bai G

Abstract
Health data integration enables a collaborative utilization of data across different systems. It not only provides a comprehensive view of a patient's health but can also potentially cope with challenges faced by the current healthcare system. In this literature review, we investigated the existing work on heterogeneous health data integration as well as the methods of utilizing the integrated health data. Our search was narrowed down to 32 articles for analysis. The integration approaches in the reviewed articles were classified into three classifications, and the utilization approaches were classified into five classifications. The topic of health data integration is still under debate and problems are far from being resolved. This review suggests the need for a more efficient way to invoke the various services for aggregating health data, as well as a more effective way to integrate the aggregated health data for supporting collaborative utilization. We have found that the combination of Web Application Programming Interface and Semantic Web technologies has the potential to cope with the challenges based on our analysis of the review result.

PMID: 31884843 [PubMed - as supplied by publisher]

Spelling performance on the web and in the lab.

PLoS One. 2019;14(12):e0226647

Authors: Rey A, Manguin JL, Olivier C, Pacton S, Courrieu P

Abstract
Several dictionary websites are available on the web to access semantic, synonymous, or spelling information about a given word. During nine years, we systematically recorded all the entered letter sequences from a French web dictionary. A total of 200 million orthographic forms were obtained allowing us to create a large-scale database of spelling errors that could inform psychological theories about spelling processes. To check the reliability of this big data methodology, we selected from this database a sample of 100 frequently misspelled words. A group of 100 French university students had to perform a spelling-to-dictation test on this list of words. The results showed a strong correlation between the two data sets on the frequencies of produced spellings (r = 0.82). Although the distributions of spelling errors were relatively consistent across the two databases, the proportion of correct responses revealed significant differences. Regression analyses allowed us to generate possible explanations for these differences in terms of task-dependent factors. We argue that comparing the results of these large-scale databases with those of standard and controlled experimental paradigms is certainly a good way to determine the conditions under which this big data methodology can be adequately used for informing psychological theories.

PMID: 31856230 [PubMed - in process]

The Lancaster Sensorimotor Norms: multidimensional measures of perceptual and action strength for 40,000 English words.

Behav Res Methods. 2019 Dec 12;:

Authors: Lynott D, Connell L, Brysbaert M, Brand J, Carney J

Abstract
Sensorimotor information plays a fundamental role in cognition. However, the existing materials that measure the sensorimotor basis of word meanings and concepts have been restricted in terms of their sample size and breadth of sensorimotor experience. Here we present norms of sensorimotor strength for 39,707 concepts across six perceptual modalities (touch, hearing, smell, taste, vision, and interoception) and five action effectors (mouth/throat, hand/arm, foot/leg, head excluding mouth/throat, and torso), gathered from a total of 3,500 individual participants using Amazon's Mechanical Turk platform. The Lancaster Sensorimotor Norms are unique and innovative in a number of respects: They represent the largest-ever set of semantic norms for English, at 40,000 words × 11 dimensions (plus several informative cross-dimensional variables), they extend perceptual strength norming to the new modality of interoception, and they include the first norming of action strength across separate bodily effectors. In the first study, we describe the data collection procedures, provide summary descriptives of the dataset, and interpret the relations observed between sensorimotor dimensions. We then report two further studies, in which we (1) extracted an optimal single-variable composite of the 11-dimension sensorimotor profile (Minkowski 3 strength) and (2) demonstrated the utility of both perceptual and action strength in facilitating lexical decision times and accuracy in two separate datasets. These norms provide a valuable resource to researchers in diverse areas, including psycholinguistics, grounded cognition, cognitive semantics, knowledge representation, machine learning, and big-data approaches to the analysis of language and conceptual representations. The data are accessible via the Open Science Framework (http://osf.io/7emr6/) and an interactive web application (https://www.lancaster.ac.uk/psychology/lsnorms/).

PMID: 31832879 [PubMed - as supplied by publisher]

Analysing the Scientific Publications of Peter Reichertz: Reflections from the Perspective of Medical Informatics Knowledge Today.

J Med Syst. 2019 Dec 11;44(1):23

Authors: Haux R

Abstract
Professor Peter L. Reichertz is one of the most significant pioneers in the field of medical informatics worldwide. In 1969, 50 years ago, he became Professor at the Hannover Medical School. On the occasion of this anniversary an attempt was made to report on the scientific work of Peter Reichertz and to reflect on this work in the light of medical informatics knowledge today. The aim of this study was to search publications listings in the Peter L. Reichertz Archive, in Pubmed/Medline, and in the Web of Science. As well as to analyse contents and communication approaches to help in classifying Peter Reichertz's scientific publications. Three comprehensive publication lists were identified: the Print Bibliography (384 publications), the Disc Bibliography (285 publications) and the Selected Publications Bibliography (111 publications). Based on the last bibliography, a classification was built along the semantic dimensions of (1) major topics, (2) fields of publication, and (3) publication languages. Major contents of Peter Reichertz's research in informatics were medical informatics as a field (including education), informatics applications in medicine and health care, and health information systems. Clear shifts over time were observed. To his research on informatics applications, in the 1970s health information systems was added as topic, which then became a major part of his research. While in the 1960s and earlier German was a major publication language, from the 1970s onwards this shifted to English as the major language. Peter Reichertz very early identified the potential of computers in medicine and health care. He did not just use information and communication technology and information processing methodology as if they were other technology, such as microscopes or ultrasonic devices, for improving diagnosis and therapy. He was visionary enough to very early see the revolutionary potential of informatics for biomedicine and health care, with consequential impact on research and education.

PMID: 31828547 [PubMed - in process]

Detecting Lifestyle Risk Factors for Chronic Kidney Disease With Comorbidities: Association Rule Mining Analysis of Web-Based Survey Data.

J Med Internet Res. 2019 Dec 10;21(12):e14204

Authors: Peng S, Shen F, Wen A, Wang L, Fan Y, Liu X, Liu H

Abstract
BACKGROUND: The rise in the number of patients with chronic kidney disease (CKD) and consequent end-stage renal disease necessitating renal replacement therapy has placed a significant strain on health care. The rate of progression of CKD is influenced by both modifiable and unmodifiable risk factors. Identification of modifiable risk factors, such as lifestyle choices, is vital in informing strategies toward renoprotection. Modification of unhealthy lifestyle choices lessens the risk of CKD progression and associated comorbidities, although the lifestyle risk factors and modification strategies may vary with different comorbidities (eg, diabetes, hypertension). However, there are limited studies on suitable lifestyle interventions for CKD patients with comorbidities.
OBJECTIVE: The objectives of our study are to (1) identify the lifestyle risk factors for CKD with common comorbid chronic conditions using a US nationwide survey in combination with literature mining, and (2) demonstrate the potential effectiveness of association rule mining (ARM) analysis for the aforementioned task, which can be generalized for similar tasks associated with noncommunicable diseases (NCDs).
METHODS: We applied ARM to identify lifestyle risk factors for CKD progression with comorbidities (cardiovascular disease, chronic pulmonary disease, rheumatoid arthritis, diabetes, and cancer) using questionnaire data for 450,000 participants collected from the Behavioral Risk Factor Surveillance System (BRFSS) 2017. The BRFSS is a Web-based resource, which includes demographic information, chronic health conditions, fruit and vegetable consumption, and sugar- or salt-related behavior. To enrich the BRFSS questionnaire, the Semantic MEDLINE Database was also mined to identify lifestyle risk factors.
RESULTS: The results suggest that lifestyle modification for CKD varies among different comorbidities. For example, the lifestyle modification of CKD with cardiovascular disease needs to focus on increasing aerobic capacity by improving muscle strength or functional ability. For CKD patients with chronic pulmonary disease or rheumatoid arthritis, lifestyle modification should be high dietary fiber intake and participation in moderate-intensity exercise. Meanwhile, the management of CKD patients with diabetes focuses on exercise and weight loss predominantly.
CONCLUSIONS: We have demonstrated the use of ARM to identify lifestyle risk factors for CKD with common comorbid chronic conditions using data from BRFSS 2017. Our methods can be generalized to advance chronic disease management with more focused and optimized lifestyle modification of NCDs.

PMID: 31821152 [PubMed - in process]