Association of Patient Treatment Preference With Dropout and Clinical Outcomes in Adult Psychosocial Mental Health Interventions: A Systematic Review and Meta-analysis.

JAMA Psychiatry. 2019 Dec 04;:

Authors: Windle E, Tee H, Sabitova A, Jovanovic N, Priebe S, Carr C

Abstract
Importance: Receiving a preferred treatment has previously been associated with lower dropout rates and better clinical outcomes, but this scenario has not been investigated specifically for psychosocial interventions for patients with a mental health diagnosis.
Objective: To assess the association of patient treatment preference with dropout and clinical outcomes in adult psychosocial mental health interventions via a systematic review and meta-analysis.
Data Sources: The Cochrane Library, Embase, PubMed, PsychINFO, Scopus, Web of Science, Nice HDAS (Healthcare Databases Advanced Search), Google Scholar, BASE (Bielefeld Academic Search Engine), Semantic Scholar, and OpenGrey were searched from inception to July 20, 2018, and updated on June 10, 2019.
Study Selection: Studies were eligible if they (1) were a randomized clinical trial; (2) involved participants older than 18 years; (3) involved participants with mental health diagnoses; (4) reported data from a group of participants who received their preferred treatment and a group who received their nonpreferred treatment or who were not given a choice; and (5) offered at least 1 psychosocial intervention.
Data Extraction and Synthesis: Two researchers extracted study data for attendance, dropout, and clinical outcomes independently. Both assessed the risk of bias according to the Cochrane tool. Data were pooled using random-effects meta-analyses.
Main Outcomes and Measures: The following 7 outcomes were examined: attendance, dropout, therapeutic alliance, depression and anxiety outcomes, global outcomes, treatment satisfaction, and remission.
Results: A total of 7341 articles were identified, with 34 eligible for inclusion. Twenty-nine articles were included in the meta-analyses comprising 5294 participants. Receiving a preferred psychosocial mental health treatment had a medium positive association with dropout rates (relative risk, 0.62; 0.48-0.80; P < .001; I2 = 44.6%) and therapeutic alliance (Cohen d = 0.48; 0.15-0.82; P = .01; I2 = 20.4%). There was no evidence of a significant association with other outcomes.
Conclusions and Relevance: This is the first review, to our knowledge, examining the association of receiving a preferred psychosocial mental health treatment with both engagement and outcomes for patients with a mental health diagnosis. Patients with mental health diagnoses who received their preferred treatment demonstrated a lower dropout rate from treatment and higher therapeutic alliance scores. These findings underline the need to accommodate patient preference in mental health services to maximize treatment uptake and reduce financial costs of premature dropout and disengagement.

PMID: 31799994 [PubMed - as supplied by publisher]

The Alliance of Genome Resources: Building a Modern Data Ecosystem for Model Organism Databases.

Genetics. 2019 Dec;213(4):1189-1196

Authors: Alliance of Genome Resources Consortium

Abstract
Model organisms are essential experimental platforms for discovering gene functions, defining protein and genetic networks, uncovering functional consequences of human genome variation, and for modeling human disease. For decades, researchers who use model organisms have relied on Model Organism Databases (MODs) and the Gene Ontology Consortium (GOC) for expertly curated annotations, and for access to integrated genomic and biological information obtained from the scientific literature and public data archives. Through the development and enforcement of data and semantic standards, these genome resources provide rapid access to the collected knowledge of model organisms in human readable and computation-ready formats that would otherwise require countless hours for individual researchers to assemble on their own. Since their inception, the MODs for the predominant biomedical model organisms [Mus sp (laboratory mouse), Saccharomyces cerevisiae, Drosophila melanogaster, Caenorhabditis elegans, Danio rerio, and Rattus norvegicus] along with the GOC have operated as a network of independent, highly collaborative genome resources. In 2016, these six MODs and the GOC joined forces as the Alliance of Genome Resources (the Alliance). By implementing shared programmatic access methods and data-specific web pages with a unified "look and feel," the Alliance is tackling barriers that have limited the ability of researchers to easily compare common data types and annotations across model organisms. To adapt to the rapidly changing landscape for evaluating and funding core data resources, the Alliance is building a modern, extensible, and operationally efficient "knowledge commons" for model organisms using shared, modular infrastructure.

PMID: 31796553 [PubMed - in process]

UMLS to DBPedia link discovery through circular resolution.

J Am Med Inform Assoc. 2018 07 01;25(7):819-826

Authors: Cuzzola J, Bagheri E, Jovanovic J

Abstract
Objective: The goal of this work is to map Unified Medical Language System (UMLS) concepts to DBpedia resources using widely accepted ontology relations from the Simple Knowledge Organization System (skos:exactMatch, skos:closeMatch) and from the Resource Description Framework Schema (rdfs:seeAlso), as a result of which a complete mapping from UMLS (UMLS 2016AA) to DBpedia (DBpedia 2015-10) is made publicly available that includes 221 690 skos:exactMatch, 26 276 skos:closeMatch, and 6 784 322 rdfs:seeAlso mappings.
Methods: We propose a method called circular resolution that utilizes a combination of semantic annotators to map UMLS concepts to DBpedia resources. A set of annotators annotate definitions of UMLS concepts returning DBpedia resources while another set performs annotation on DBpedia resource abstracts returning UMLS concepts. Our pipeline aligns these 2 sets of annotations to determine appropriate mappings from UMLS to DBpedia.
Results: We evaluate our proposed method using structured data from the Wikidata knowledge base as the ground truth, which consists of 4899 already existing UMLS to DBpedia mappings. Our results show an 83% recall with 77% precision-at-one (P@1) in mapping UMLS concepts to DBpedia resources on this testing set.
Conclusions: The proposed circular resolution method is a simple yet effective technique for linking UMLS concepts to DBpedia resources. Experiments using Wikidata-based ground truth reveal a high mapping accuracy. In addition to the complete UMLS mapping downloadable in n-triple format, we provide an online browser and a RESTful service to explore the mappings.

PMID: 29648604 [PubMed - indexed for MEDLINE]

Exploring website gist through rapid serial visual presentation.

Cogn Res Princ Implic. 2019 Nov 20;4(1):44

Authors: Owens JW, Chaparro BS, Palmer EM

Abstract
BACKGROUND: Users can make judgments about web pages in a glance. Little research has explored what semantic information can be extracted from a web page within a single fixation or what mental representations users have of web pages, but the scene perception literature provides a framework for understanding how viewers can extract and represent diverse semantic information from scenes in a glance. The purpose of this research was (1) to explore whether semantic information about a web page could be extracted within a single fixation and (2) to explore the effects of size and resolution on extracting this information. Using a rapid serial visual presentation (RSVP) paradigm, Experiment 1 explored whether certain semantic categories of websites (i.e., news, search, shopping, and social networks/blogs) could be detected within a RSVP stream of web page stimuli. Natural scenes, which have been shown to be detectable within a single fixation in the literature, served as a baseline for comparison. Experiment 2 examined the effects of stimulus size and resolution on observers' ability to detect the presence of website categories using similar methods.
RESULTS: Findings from this research demonstrate that users have conceptual models of websites that allow detection of web pages from a fixation's worth of stimulus exposure, when provided additional time for processing. For website categories other than search, detection performance decreased significantly when web elements were no longer discernible due to decreases in size and/or resolution. The implications of this research are that website conceptual models rely more on page elements and less on the spatial relationship between these elements.
CONCLUSIONS: Participants can detect websites accurately when they were displayed for less than a fixation and when the participants were allowed additional processing time. Subjective comments and stimulus onset asynchrony data suggested that participants likely relied on local features for the detection of website targets for several website categories. This notion was supported when the size and/or resolution of stimuli were decreased to the extent that web elements were indistinguishable. This demonstrates that schemas or conceptualizations of websites provided information sufficient to detect websites from approximately 140 ms of stimulus exposure.

PMID: 31748970 [PubMed]

The ethnopharmacological literature: An analysis of the scientific landscape.

J Ethnopharmacol. 2019 Nov 18;:112414

Authors: Kan Yeung AW, Heinrich M, Kijjoa A, Tzvetkov NT, Atanasov AG

Abstract
ETHNOPHARMACOLOGICAL RELEVANCE: The research into bioactive natural products originating from medicinal plants, fungi and other organisms has a long history, accumulating abundant and diverse publications. However no quantitative literature analysis has been conducted.
AIM OF THE STUDY: Here we analyze the bibliometric data of ethnopharmacology literature and relate the semantic content to the publication and citation data so that the major research themes, contributors, and journals of different time periods could be identified and evaluated.
MATERIALS AND METHODS: Web of Science (WoS) was searched to identify relevant publications. The Analyze function of WoS and bibliometric software (VOSviewer) were utilized to perform the analyses.
RESULTS: Until the end of November 2018, 59,576 publications -linked to 'ethnopharmacology' indexed by WoS, published since 1958 in more than 5,600 journals, and contributed by over 20,600 institutions located in more than 200 countries/regions, were identified. The papers were published under four dominating WoS categories, namely pharmacology/pharmacy (34.4%), plant sciences (28.6%), medicinal chemistry (25.3%), and integrative complementary medicine (20.6%). India (14.6%) and China (13.2%) were dominating the publication space. The United States and Brazil also had more than 8.0% contribution each. The rest of the top ten countries/regions were mainly from Asia. There were around ten-fold more original articles (84.6%) than reviews (8.4%).
CONCLUSIONS: Ethnopharmacological research has a consistent focus on food and plant sciences, (bio)chemistry, complementary medicine and pharmacology, with a more limited scientific acceptance in the socio-cultural sciences. Dynamic global contributions have been shifting from developed countries to economically and scientifically emerging countries in Asia, South America and the Middle East. Research on recording medicinal plant species used by traditional medicine continues, but the evaluation of specific properties or treatment effects of extracts and compounds has increased enormously. Moreover increasing attention is paid to some widely distributed natural products, such as curcumin, quercetin, and rutin.

PMID: 31751650 [PubMed - as supplied by publisher]

Cross-lingual Semantic Annotation of Biomedical Literature: Experiments in Spanish and English.

Bioinformatics. 2019 Nov 15;:

Authors: Perez N, Accuosto P, Bravo À, Cuadros M, Martínez-García E, Saggion H, Rigau G

Abstract
MOTIVATION: Biomedical literature is one of the most relevant sources of information for knowledge mining in the field of Bioinformatics. In spite of English being the most widely addressed language in the field, in recent years there has been a growing interest from the natural language processing community in dealing with languages other than English. However, the availability of language resources and tools for appropriate treatment of non-English texts is lacking behind. Our research is concerned with the semantic annotation of biomedical texts in the Spanish language, which can be considered an under-resourced language where biomedical text processing is concerned.
RESULTS: We have carried out experiments to assess the effectiveness of several methods for the automatic annotation of biomedical texts in Spanish. One approach is based on the linguistic analysis of Spanish texts and their annotation using an information retrieval and concept disambiguation approach. A second method takes advantage of a Spanish-English machine translation process to annotate English documents and transfer annotations back to Spanish. A third method takes advantage of the combination of both procedures. Our evaluation shows that a combined system has competitive advantages over the two individual procedures.
AVAILABILITY: UMLSmapper (https://snlt.vicomtech.org/umlsmapper) and the annotation transfer tool (http://scientmin.taln.upf.edu/anntransfer) are freely available for research purposes as web services and/or demos.
SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID: 31730202 [PubMed - as supplied by publisher]

Exploring semantic deep learning for building reliable and reusable one health knowledge from PubMed systematic reviews and veterinary clinical notes.

J Biomed Semantics. 2019 Nov 12;10(Suppl 1):22

Authors: Arguello-Casteleiro M, Stevens R, Des-Diz J, Wroe C, Fernandez-Prieto MJ, Maroto N, Maseda-Fernandez D, Demetriou G, Peters S, Noble PM, Jones PH, Dukes-McEwan J, Radford AD, Keane J, Nenadic G

Abstract
BACKGROUND: Deep Learning opens up opportunities for routinely scanning large bodies of biomedical literature and clinical narratives to represent the meaning of biomedical and clinical terms. However, the validation and integration of this knowledge on a scale requires cross checking with ground truths (i.e. evidence-based resources) that are unavailable in an actionable or computable form. In this paper we explore how to turn information about diagnoses, prognoses, therapies and other clinical concepts into computable knowledge using free-text data about human and animal health. We used a Semantic Deep Learning approach that combines the Semantic Web technologies and Deep Learning to acquire and validate knowledge about 11 well-known medical conditions mined from two sets of unstructured free-text data: 300 K PubMed Systematic Review articles (the PMSB dataset) and 2.5 M veterinary clinical notes (the VetCN dataset). For each target condition we obtained 20 related clinical concepts using two deep learning methods applied separately on the two datasets, resulting in 880 term pairs (target term, candidate term). Each concept, represented by an n-gram, is mapped to UMLS using MetaMap; we also developed a bespoke method for mapping short forms (e.g. abbreviations and acronyms). Existing ontologies were used to formally represent associations. We also create ontological modules and illustrate how the extracted knowledge can be queried. The evaluation was performed using the content within BMJ Best Practice.
RESULTS: MetaMap achieves an F measure of 88% (precision 85%, recall 91%) when applied directly to the total of 613 unique candidate terms for the 880 term pairs. When the processing of short forms is included, MetaMap achieves an F measure of 94% (precision 92%, recall 96%). Validation of the term pairs with BMJ Best Practice yields precision between 98 and 99%.
CONCLUSIONS: The Semantic Deep Learning approach can transform neural embeddings built from unstructured free-text data into reliable and reusable One Health knowledge using ontologies and content from BMJ Best Practice.

PMID: 31711540 [PubMed - in process]

Development of a Free Online Interactive Naming Therapy for Bilingual Aphasia.

Am J Speech Lang Pathol. 2019 Nov 05;:1-10

Authors: Sandberg C, Gray T, Kiran S

Abstract
Purpose The purpose of this ongoing project was to provide speech-language pathologists who serve culturally and linguistically diverse populations with a freely available online tool for naming therapy in a variety of languages. The purpose of this clinical focus article was to report on this resource in an effort to make known its existence, its instructions for use, and the evidence-based practices from which it was developed. Method The website, bilingualnamingtherapy.com, was created by the research team in collaboration with a web programmer using Amazon Web Services. The treatment protocol for the website was adapted from an evidence-based naming intervention in which clients select and verify appropriate semantic features for the target words. This protocol comes from the work of Kiran and colleagues (Edmonds & Kiran, 2006; Kiran & Iakupova, 2011; Kiran & Lo, 2013; Kiran & Roberts, 2010; Kiran, Sandberg, Gray, Ascenso, & Kester, 2013; Krishnan, Tiwari, Kiran, & Chengappa, 2014), who showed positive benefits of this therapy within and across languages in bilingual persons with aphasia. The stimuli for the online therapy were developed in a variety of languages. First, words and semantic features were translated from English to 10 different languages. Next, surveys were created using Qualtrics software and posted on Amazon Mechanical Turk to verify picture labels and semantic features for each word in each language. The results of these surveys guided the stimuli used for each language on the website. An interactive website was developed to allow clinicians to select a set of words and progress through a series of steps. A step-by-step tutorial on how to use this website is also included in this article. Conclusions The interactive online naming therapy described in this article is currently available in English and Spanish, with Chinese under construction. Several more languages are in various stages of preparation for use on the website, and suggestions for additional languages are being actively sought. Bilingualnamingtherapy.com promises to be a useful tool for speech-language pathologists who work with culturally and linguistically diverse clients. This website provides naming therapy materials, adapted from an evidence-based protocol, in a variety of languages, that have been developed based on feedback from speakers of each language to maximize cultural and linguistic appropriateness.

PMID: 31689369 [PubMed - as supplied by publisher]

Forma mentis networks quantify crucial differences in STEM perception between students and experts.

PLoS One. 2019;14(10):e0222870

Authors: Stella M, de Nigris S, Aloric A, Siew CSQ

Abstract
In order to investigate how high school students and researchers perceive science-related (STEM) subjects, we introduce forma mentis networks. This framework models how people conceptually structure their stance, mindset or forma mentis toward a given topic. In this study, we build forma mentis networks revolving around STEM and based on psycholinguistic data, namely free associations of STEM concepts (i.e., which words are elicited first and associated by students/researchers reading "science"?) and their valence ratings concepts (i.e., is "science" perceived as positive, negative or neutral by students/researchers?). We construct separate networks for (Ns = 159) Italian high school students and (Nr = 59) interdisciplinary professionals and researchers in order to investigate how these groups differ in their conceptual knowledge and emotional perception of STEM. Our analysis of forma mentis networks at various scales indicate that, like researchers, students perceived "science" as a strongly positive entity. However, differently from researchers, students identified STEM subjects like "physics" and "mathematics" as negative and associated them with other negative STEM-related concepts. We call this surrounding of negative associations a negative emotional aura. Cross-validation with external datasets indicated that the negative emotional auras of physics, maths and statistics in the students' forma mentis network related to science anxiety. Furthermore, considering the semantic associates of "mathematics" and "physics" revealed that negative auras may originate from a bleak, dry perception of the technical methodology and mnemonic tools taught in these subjects (e.g., calculus rules). Overall, our results underline the crucial importance of emphasizing nontechnical and applied aspects of STEM disciplines, beyond purely methodological teaching. The quantitative insights achieved through forma mentis networks highlight the necessity of establishing novel pedagogic and interdisciplinary links between science, its real-world complexity, and creativity in science learning in order to enhance the impact of STEM education, learning and outreach activities.

PMID: 31622351 [PubMed - in process]

THINGS: A database of 1,854 object concepts and more than 26,000 naturalistic object images.

PLoS One. 2019;14(10):e0223792

Authors: Hebart MN, Dickter AH, Kidder A, Kwok WY, Corriveau A, Van Wicklin C, Baker CI

Abstract
In recent years, the use of a large number of object concepts and naturalistic object images has been growing strongly in cognitive neuroscience research. Classical databases of object concepts are based mostly on a manually curated set of concepts. Further, databases of naturalistic object images typically consist of single images of objects cropped from their background, or a large number of naturalistic images of varying quality, requiring elaborate manual image curation. Here we provide a set of 1,854 diverse object concepts sampled systematically from concrete picturable and nameable nouns in the American English language. Using these object concepts, we conducted a large-scale web image search to compile a database of 26,107 high-quality naturalistic images of those objects, with 12 or more object images per concept and all images cropped to square size. Using crowdsourcing, we provide higher-level category membership for the 27 most common categories and validate them by relating them to representations in a semantic embedding derived from large text corpora. Finally, by feeding images through a deep convolutional neural network, we demonstrate that they exhibit high selectivity for different object concepts, while at the same time preserving variability of different object images within each concept. Together, the THINGS database provides a rich resource of object concepts and object images and offers a tool for both systematic and large-scale naturalistic research in the fields of psychology, neuroscience, and computer science.

PMID: 31613926 [PubMed - in process]

Ten years of knowledge representation for health care (2009-2018): Topics, trends, and challenges.

Artif Intell Med. 2019 Sep;100:101713

Authors: Riaño D, Peleg M, Ten Teije A

Abstract
BACKGROUND: In the last ten years, the international workshop on knowledge representation for health care (KR4HC) has hosted outstanding contributions of the artificial intelligence in medicine community pertaining to the formalization and representation of medical knowledge for supporting clinical care. Contributions regarding modeling languages, technologies and methodologies to produce these models, their incorporation into medical decision support systems, and practical applications in concrete medical settings have been the main contributions and the basis to define the evolution of this field across Europe and worldwide.
OBJECTIVES: Carry out a review of the papers accepted in KR4HC in the 2009-2018 decade, analyze and characterize the topics and trends within this field, and identify challenges for the evolution of the area in the near future.
METHODS: We reviewed the title, the abstract, and the keywords of the 112 papers that were accepted to the workshop, identified the medical and technological topics involved in these works, provided a classification of these papers in medical and technological perspectives and obtained the timeline of these topics in order to determine interest growths and declines. The experience of the authors in the field and the evidences after the review were the basis to propose a list of challenges of knowledge representation in health care for the future.
RESULTS: The most generic knowledge representation methods are ontologies (31%), semantic web related formalisms (26%), decision tables and rules (19%), logic (14%), and probabilistic models (10%). From a medical informatics perspective, knowledge is mainly represented as computer interpretable clinical guidelines (43%), medical domain ontologies (26%), and electronic health care records (22%). Within the knowledge lifecycle, contributions are found in knowledge generation (38%), knowledge specification (24%), exception detection and management (12%), knowledge enactment (8%), temporal knowledge and reasoning (7%), and knowledge sharing and maintenance (7%). The clinical emphasis of knowledge is mainly related to clinical treatments (27%), diagnosis (13%), clinical quality indicators (13%), and guideline integration for multimorbid patients (12%). According to the level of development of the works presented, we distinguished four maturity levels: formal (22%), implementation (52%), testing (13%), and deployment (2%) levels. Some papers described technologies for specific clinical issues or diseases, mainly cancer (22%) and diseases of the circulatory system (20%). Chronicity and comorbidity were present in 10% and 8% of the papers, respectively.
CONCLUSIONS: KR4HC is a stable community, still active after ten years. A persistent focus has been knowledge representation, with an emphasis on semantic-web ontologies and on clinical-guideline based decision-support. Among others, two topics receive growing attention: integration of computer-interpretable guideline knowledge for the management of multimorbidity patients, and patient empowerment and patient-centric care.

PMID: 31607346 [PubMed - in process]

EAGLE-A Scalable Query Processing Engine for Linked Sensor Data.

Sensors (Basel). 2019 Oct 09;19(20):

Authors: Nguyen Mau Quoc H, Serrano M, Mau Nguyen H, G Breslin J, Le-Phuoc D

Abstract
Recently, many approaches have been proposed to manage sensor data using semantic web technologies for effective heterogeneous data integration. However, our empirical observations revealed that these solutions primarily focused on semantic relationships and unfortunately paid less attention to spatio-temporal correlations. Most semantic approaches do not have spatio-temporal support. Some of them have attempted to provide full spatio-temporal support, but have poor performance for complex spatio-temporal aggregate queries. In addition, while the volume of sensor data is rapidly growing, the challenge of querying and managing the massive volumes of data generated by sensing devices still remains unsolved. In this article, we introduce EAGLE, a spatio-temporal query engine for querying sensor data based on the linked data model. The ultimate goal of EAGLE is to provide an elastic and scalable system which allows fast searching and analysis with respect to the relationships of space, time and semantics in sensor data. We also extend SPARQL with a set of new query operators in order to support spatio-temporal computing in the linked sensor data context.

PMID: 31600957 [PubMed - in process]

SEAweb: the small RNA Expression Atlas web application.

Nucleic Acids Res. 2019 Oct 10;:

Authors: Rahman RU, Liebhoff AM, Bansal V, Fiosins M, Rajput A, Sattar A, Magruder DS, Madan S, Sun T, Gautam A, Heins S, Liwinski T, Bethune J, Trenkwalder C, Fluck J, Mollenhauer B, Bonn S

Abstract
We present the Small RNA Expression Atlas (SEAweb), a web application that allows for the interactive querying, visualization and analysis of known and novel small RNAs across 10 organisms. It contains sRNA and pathogen expression information for over 4200 published samples with standardized search terms and ontologies. In addition, SEAweb allows for the interactive visualization and re-analysis of 879 differential expression and 514 classification comparisons. SEAweb's user model enables sRNA researchers to compare and re-analyze user-specific and published datasets, highlighting common and distinct sRNA expression patterns. We provide evidence for SEAweb's fidelity by (i) generating a set of 591 tissue specific miRNAs across 29 tissues, (ii) finding known and novel bacterial and viral infections across diseases and (iii) determining a Parkinson's disease-specific blood biomarker signature using novel data. We believe that SEAweb's simple semantic search interface, the flexible interactive reports and the user model with rich analysis capabilities will enable researchers to better understand the potential function and diagnostic value of sRNAs or pathogens across tissues, diseases and organisms.

PMID: 31598718 [PubMed - as supplied by publisher]

Fine Subdivisions of the Semantic Network Supporting Social and Sensory-Motor Semantic Processing.

Cereb Cortex. 2018 08 01;28(8):2699-2710

Authors: Lin N, Wang X, Xu Y, Wang X, Hua H, Zhao Y, Li X

Abstract
Neuroimaging studies have consistently indicated that semantic processing involves a brain network consisting of multimodal cortical regions distributed in the frontal, parietal, and temporal lobes. However, little is known about how semantic information is organized and processed within the network. Some recent studies have indicated that sensory-motor semantic information modulates the activation of this network. Other studies have indicated that this network responds more to social semantic information than to other information. Using fMRI, we collectively investigated the brain activations evoked by social and sensory-motor semantic information by manipulating the sociality and imageability of verbs in a word comprehension task. We detected 2 subgroups of brain regions within the network showing sociality and imageability effects, respectively. The 2 subgroups of regions are distinct but overlap in bilateral angular gyri and adjacent middle temporal gyri. A follow-up analysis of resting-state functional connectivity showed that dissociation of the 2 subgroups of regions is partially associated with their intrinsic functional connectivity differences. Additionally, an interaction effect of sociality and imageability was observed in the left anterior temporal lobe. Our findings indicate that the multimodal cortical semantic network has fine subdivisions that process and integrate social and sensory-motor semantic information.

PMID: 28633369 [PubMed - indexed for MEDLINE]

A Pervasive Healthcare System for COPD Patients.

Diagnostics (Basel). 2019 Oct 01;9(4):

Authors: Ajami H, Mcheick H, Mustapha K

Abstract
Chronic obstructive pulmonary disease (COPD) is one of the most severe public health problems worldwide. Pervasive computing technology creates a new opportunity to redesign the traditional pattern of medical system. While many pervasive healthcare systems are currently found in the literature, there is little published research on the effectiveness of these paradigms in the medical context. This paper designs and validates a rule-based ontology framework for COPD patients. Unlike conventional systems, this work presents a new vision of telemedicine and remote care solutions that will promote individual self-management and autonomy for COPD patients through an advanced decision-making technique. Rules accuracy estimates were 89% for monitoring vital signs, and environmental factors, and 87% for nutrition facts, and physical activities.

PMID: 31581453 [PubMed]

Technical Note: Ontology-guided Radiomics Analysis Workflow (O-RAW).

Med Phys. 2019 Oct 03;:

Authors: Shi Z, Traverso A, van Soest J, Dekker A, Wee L

Abstract
PURPOSE: Radiomics is the process to automate tumour feature extraction from medical images. This has shown potential for quantifying the tumour phenotype and predicting treatment response. The three major challenges of radiomics research and clinical adoption are: (i) lack of standardized methodology for radiomics analyses, (ii) lack of a universal lexicon to denote features that are semantically equivalent, and (iii) lists of feature values alone do not sufficiently capture the details of feature extraction that might nonetheless strongly affect feature values (e.g. image normalization or interpolation parameters). These barriers hamper multi-centre validation studies applying subtly different imaging protocols, pre-processing steps and radiomics software. We propose an open-source Ontology-guided Radiomics Analysis Workflow (O-RAW) to address the above challenges in the following manner: (i) distributing a free and open-source software package for radiomics analysis, (ii) deploying a standard lexicon to uniquely describe features in common usage and (iii) provide methods to publish radiomic features as a semantically-interoperable data graph object complying to FAIR (Findable Accessible Interoperable Reusable) data principles.
METHODS: O-RAW was developed in Python, and has three major modules using open-source component libraries (PyRadiomics Extension and PyRadiomics). First, PyRadiomics Extension takes standard DICOM-RT (Radiotherapy) input objects (i.e. a DICOM series and an RTSTRUCT file) and parses them as arrays of voxel intensities and a binary mask corresponding to a volume of interest (VOI). Next, these arrays are passed into PyRadiomics, which performs the feature extraction procedure and returns a Python dictionary object. Lastly, PyRadiomics Extension parses this dictionary as a W3C-compliant Semantic Web "triple store" (i.e., list of subject-predicate-object statements) with relevant semantic meta-labels drawn from the Radiation Oncology Ontology and Radiomics Ontology. The output can be published on an SPARQL endpoint, and can be remotely examined via SPARQL queries or to a comma separated file for further analysis.
RESULTS: We showed that O-RAW executed efficiently on three datasets with differing modalities, MMD (CT), CROSS (PET) and THUNDER (MR). The test was performed on an HP laptop running Windows 7 operating system and 8GB RAM on which we noted execution time including DICOM images and associated RTSTRUCT matching, binary mask conversion of a single VOI, batch-processing of feature extraction (105 basic features in PyRadiomics), and the conversion to an RDF object. The results were (RIDER) 407.3, (MMD) 123.5, (CROSS) 513.2 and (THUNDER) 128.9 seconds for a single VOI. In addition, we demonstrated a use case, taking images from a public repository and publishing the radiomics results as FAIR data in this study on www.radiomics.org. Finally, we provided a practical instance to show how a user could query radiomic features and track the calculation details based on the RDF graph object created by O-RAW via a simple SPARQL query.
CONCLUSIONS: We implemented O-RAW for FAIR radiomics analysis, and successfully published radiomic features from DICOM-RT objects as semantic web triples. Its practicability and flexibility can greatly increase the development of radiomics research and ease transfer to clinical practice.

PMID: 31580484 [PubMed - as supplied by publisher]

Beyond opinion classification: Extracting facts, opinions and experiences from health forums.

PLoS One. 2019;14(1):e0209961

Authors: Carrillo-de-Albornoz J, Aker A, Kurtic E, Plaza L

Abstract
INTRODUCTION: Surveys indicate that patients, particularly those suffering from chronic conditions, strongly benefit from the information found in social networks and online forums. One challenge in accessing online health information is to differentiate between factual and more subjective information. In this work, we evaluate the feasibility of exploiting lexical, syntactic, semantic, network-based and emotional properties of texts to automatically classify patient-generated contents into three types: "experiences", "facts" and "opinions", using machine learning algorithms. In this context, our goal is to develop automatic methods that will make online health information more easily accessible and useful for patients, professionals and researchers.
MATERIAL AND METHODS: We work with a set of 3000 posts to online health forums in breast cancer, morbus crohn and different allergies. Each sentence in a post is manually labeled as "experience", "fact" or "opinion". Using this data, we train a support vector machine algorithm to perform classification. The results are evaluated in a 10-fold cross validation procedure.
RESULTS: Overall, we find that it is possible to predict the type of information contained in a forum post with a very high accuracy (over 80 percent) using simple text representations such as word embeddings and bags of words. We also analyze more complex features such as those based on the network properties, the polarity of words and the verbal tense of the sentences and show that, when combined with the previous ones, they can boost the results.

PMID: 30625206 [PubMed - indexed for MEDLINE]

Clinical Concept Value Sets and Interoperability in Health Data Analytics.

AMIA Annu Symp Proc. 2018;2018:480-489

Authors: Gold S, Batch A, McClure R, Jiang G, Kharrazi H, Saripalle R, Huser V, Weng C, Roderer N, Szarfman A, Elmqvist N, Gotz D

Abstract
This paper focuses on value sets as an essential component in the health analytics ecosystem. We discuss shared repositories of reusable value sets and offer recommendations for their further development and adoption. In order to motivate these contributions, we explain how value sets fit into specific analytic tasks and the health analytics landscape more broadly; their growing importance and ubiquity with the advent of Common Data Models, Distributed Research Networks, and the availability of higher order, reusable analytic resources like electronic phenotypes and electronic clinical quality measures; the formidable barriers to value set reuse; and our introduction of a concept-agnostic orientation to vocabulary collections. The costs of ad hoc value set management and the benefits of value set reuse are described or implied throughout. Our standards, infrastructure, and design recommendations are not systematic or comprehensive but invite further work to support value set reuse for health analytics. The views represented in the paper do not necessarily represent the views of the institutions or of all the co-authors.

PMID: 30815088 [PubMed - indexed for MEDLINE]

Enabling Web-scale data integration in biomedicine through Linked Open Data.

NPJ Digit Med. 2019;2:90

Authors: Kamdar MR, Fernández JD, Polleres A, Tudorache T, Musen MA

Abstract
The biomedical data landscape is fragmented with several isolated, heterogeneous data and knowledge sources, which use varying formats, syntaxes, schemas, and entity notations, existing on the Web. Biomedical researchers face severe logistical and technical challenges to query, integrate, analyze, and visualize data from multiple diverse sources in the context of available biomedical knowledge. Semantic Web technologies and Linked Data principles may aid toward Web-scale semantic processing and data integration in biomedicine. The biomedical research community has been one of the earliest adopters of these technologies and principles to publish data and knowledge on the Web as linked graphs and ontologies, hence creating the Life Sciences Linked Open Data (LSLOD) cloud. In this paper, we provide our perspective on some opportunities proffered by the use of LSLOD to integrate biomedical data and knowledge in three domains: (1) pharmacology, (2) cancer research, and (3) infectious diseases. We will discuss some of the major challenges that hinder the wide-spread use and consumption of LSLOD by the biomedical research community. Finally, we provide a few technical solutions and insights that can address these challenges. Eventually, LSLOD can enable the development of scalable, intelligent infrastructures that support artificial intelligence methods for augmenting human intelligence to achieve better clinical outcomes for patients, to enhance the quality of biomedical research, and to improve our understanding of living systems.

PMID: 31531395 [PubMed]

Model annotation and discovery with the Physiome Model Repository.

BMC Bioinformatics. 2019 Sep 06;20(1):457

Authors: Sarwar DM, Kalbasi R, Gennari JH, Carlson BE, Neal ML, Bono B, Atalag K, Hunter PJ, Nickerson DP

Abstract
BACKGROUND: Mathematics and Phy sics-based simulation models have the potential to help interpret and encapsulate biological phenomena in a computable and reproducible form. Similarly, comprehensive descriptions of such models help to ensure that such models are accessible, discoverable, and reusable. To this end, researchers have developed tools and standards to encode mathematical models of biological systems enabling reproducibility and reuse, tools and guidelines to facilitate semantic description of mathematical models, and repositories in which to archive, share, and discover models. Scientists can leverage these resources to investigate specific questions and hypotheses in a more efficient manner.
RESULTS: We have comprehensively annotated a cohort of models with biological semantics. These annotated models are freely available in the Physiome Model Repository (PMR). To demonstrate the benefits of this approach, we have developed a web-based tool which enables users to discover models relevant to their work, with a particular focus on epithelial transport. Based on a semantic query, this tool will help users discover relevant models, suggesting similar or alternative models that the user may wish to explore or use.
CONCLUSION: The semantic annotation and the web tool we have developed is a new contribution enabling scientists to discover relevant models in the PMR as candidates for reuse in their own scientific endeavours. This approach demonstrates how semantic web technologies and methodologies can contribute to biomedical and clinical research. The source code and links to the web tool are available at https://github.com/dewancse/model-discovery-tool.

PMID: 31492098 [PubMed - in process]