BEERE: a web server for biomedical entity expansion, ranking and explorations.

Nucleic Acids Res. 2019 May 22;:

Authors: Yue Z, Willey CD, Hjelmeland AB, Chen JY

Abstract
BEERE (Biomedical Entity Expansion, Ranking and Explorations) is a new web-based data analysis tool to help biomedical researchers characterize any input list of genes/proteins, biomedical terms or their combinations, i.e. 'biomedical entities', in the context of existing literature. Specifically, BEERE first aims to help users examine the credibility of known entity-to-entity associative or semantic relationships supported by database or literature references from the user input of a gene/term list. Then, it will help users uncover the relative importance of each entity-a gene or a term-within the user input by computing the ranking scores of all entities. At last, it will help users hypothesize new gene functions or genotype-phenotype associations by an interactive visual interface of constructed global entity relationship network. The output from BEERE includes: a list of the original entities matched with known relationships in databases; any expanded entities that may be generated from the analysis; the ranks and ranking scores reported with statistical significance for each entity; and an interactive graphical display of the gene or term network within data provenance annotations that link to external data sources. The web server is free and open to all users with no login requirement and can be accessed at http://discovery.informatics.uab.edu/beere/.

PMID: 31114876 [PubMed - as supplied by publisher]

SBOL-OWL: An ontological approach for formal and semantic representation of synthetic biology information.

ACS Synth Biol. 2019 May 06;:

Authors: Misirli G, Taylor R, Goñi-Moreno A, Mclaughlin JA, Myers CJ, Gennari J, Lord P, Wipat A

Abstract
Standard representation of data is key for the reproducibility of designs in synthetic biology. The Synthetic Biology Open Language (SBOL) has already emerged as a data standard to represent information about genetic circuits, and it is based on capturing data using graphs. The language provides the syntax using a free text document that is accessible to humans only. This paper describes SBOL-OWL, an ontology for a machine understandable definition of SBOL. This ontology acts as a semantic layer for genetic circuit designs. As a result, computational tools can understand the meaning of design entities in addition to parsing structured SBOL data. SBOL-OWL not only describes how genetic circuits can be constructed computationally, it also facilitates the use of several existing Semantic Web tools for synthetic biology. This paper demonstrates some of these features, for example, to validate designs and check for inconsistencies. Through the use of SBOL-OWL, queries can be simplified and become more intuitive. Moreover, existing reasoners can be used to infer information about genetic circuit designs that cannot be directly retrieved using existing querying mechanisms. This ontological representation of the SBOL standard provides a new perspective to the verification, representation, and querying of information about genetic circuits and is important to incorporate complex design information via the integration of biological ontologies.

PMID: 31059645 [PubMed - as supplied by publisher]

Feature engineering for sentiment analysis in e-health forums.

PLoS One. 2018;13(11):e0207996

Authors: Carrillo-de-Albornoz J, Rodríguez Vidal J, Plaza L

Abstract
INTRODUCTION: Exploiting information in health-related social media services is of great interest for patients, researchers and medical companies. The challenge is, however, to provide easy, quick and relevant access to the vast amount of information that is available. One step towards facilitating information access to online health data is opinion mining. Even though the classification of patient opinions into positive and negative has been previously tackled, most works make use of machine learning methods and bags of words. Our first contribution is an extensive evaluation of different features, including lexical, syntactic, semantic, network-based, sentiment-based and word embeddings features to represent patient-authored texts for polarity classification. The second contribution of this work is the study of polar facts (i.e. objective information with polar connotations). Traditionally, the presence of polar facts has been neglected and research in polarity classification has been bounded to opinionated texts. We demonstrate the existence and importance of polar facts for the polarity classification of health information.
MATERIAL AND METHODS: We annotate a set of more than 3500 posts to online health forums of breast cancer, crohn and different allergies, respectively. Each sentence in a post is manually labeled as "experience", "fact" or "opinion", and as "positive", "negative" and "neutral". Using this data, we train different machine learning algorithms and compare traditional bags of words representations with word embeddings in combination with lexical, syntactic, semantic, network-based and emotional properties of texts to automatically classify patient-authored contents into positive, negative and neutral. Beside, we experiment with a combination of textual and semantic representations by generating concept embeddings using the UMLS Metathesaurus.
RESULTS: We reach two main results: first, we find that it is possible to predict polarity of patient-authored contents with a very high accuracy (≈ 70 percent) using word embeddings, and that this considerably outperforms more traditional representations like bags of words; and second, when dealing with medical information, negative and positive facts (i.e. objective information) are nearly as frequent as negative and positive opinions and experiences (i.e. subjective information), and their importance for polarity classification is crucial.

PMID: 30496232 [PubMed - indexed for MEDLINE]

An open access medical knowledge base for community driven diagnostic decision support system development.

BMC Med Inform Decis Mak. 2019 Apr 27;19(1):93

Authors: Müller L, Gangadharaiah R, Klein SC, Perry J, Bernstein G, Nurkse D, Wailes D, Graham R, El-Kareh R, Mehta S, Vinterbo SA, Aronoff-Spencer E

Abstract
INTRODUCTION: While early diagnostic decision support systems were built around knowledge bases, more recent systems employ machine learning to consume large amounts of health data. We argue curated knowledge bases will remain an important component of future diagnostic decision support systems by providing ground truth and facilitating explainable human-computer interaction, but that prototype development is hampered by the lack of freely available computable knowledge bases.
METHODS: We constructed an open access knowledge base and evaluated its potential in the context of a prototype decision support system. We developed a modified set-covering algorithm to benchmark the performance of our knowledge base compared to existing platforms. Testing was based on case reports from selected literature and medical student preparatory material.
RESULTS: The knowledge base contains over 2000 ICD-10 coded diseases and 450 RX-Norm coded medications, with over 8000 unique observations encoded as SNOMED or LOINC semantic terms. Using 117 medical cases, we found the accuracy of the knowledge base and test algorithm to be comparable to established diagnostic tools such as Isabel and DXplain. Our prototype, as well as DXplain, showed the correct answer as "best suggestion" in 33% of the cases. While we identified shortcomings during development and evaluation, we found the knowledge base to be a promising platform for decision support systems.
CONCLUSION: We built and successfully evaluated an open access knowledge base to facilitate the development of new medical diagnostic assistants. This knowledge base can be expanded and curated by users and serve as a starting point to facilitate new technology development and system improvement in many contexts.

PMID: 31029130 [PubMed - in process]

Meaningful Integration of Data from Heterogeneous Health Services and Home Environment Based on Ontology.

Sensors (Basel). 2019 Apr 12;19(8):

Authors: Peng C, Goswami P

Abstract
The development of electronic health records, wearable devices, health applications and Internet of Things (IoT)-empowered smart homes is promoting various applications. It also makes health self-management much more feasible, which can partially mitigate one of the challenges that the current healthcare system is facing. Effective and convenient self-management of health requires the collaborative use of health data and home environment data from different services, devices, and even open data on the Web. Although health data interoperability standards including HL7 Fast Healthcare Interoperability Resources (FHIR) and IoT ontology including Semantic Sensor Network (SSN) have been developed and promoted, it is impossible for all the different categories of services to adopt the same standard in the near future. This study presents a method that applies Semantic Web technologies to integrate the health data and home environment data from heterogeneously built services and devices. We propose a Web Ontology Language (OWL)-based integration ontology that models health data from HL7 FHIR standard implemented services, normal Web services and Web of Things (WoT) services and Linked Data together with home environment data from formal ontology-described WoT services. It works on the resource integration layer of the layered integration architecture. An example use case with a prototype implementation shows that the proposed method successfully integrates the health data and home environment data into a resource graph. The integrated data are annotated with semantics and ontological links, which make them machine-understandable and cross-system reusable.

PMID: 31013678 [PubMed - in process]

PGxO and PGxLOD: a reconciliation of pharmacogenomic knowledge of various provenances, enabling further comparison.

BMC Bioinformatics. 2019 Apr 18;20(Suppl 4):139

Authors: Monnin P, Legrand J, Husson G, Ringot P, Tchechmedjiev A, Jonquet C, Napoli A, Coulet A

Abstract
BACKGROUND: Pharmacogenomics (PGx) studies how genomic variations impact variations in drug response phenotypes. Knowledge in pharmacogenomics is typically composed of units that have the form of ternary relationships gene variant - drug - adverse event. Such a relationship states that an adverse event may occur for patients having the specified gene variant and being exposed to the specified drug. State-of-the-art knowledge in PGx is mainly available in reference databases such as PharmGKB and reported in scientific biomedical literature. But, PGx knowledge can also be discovered from clinical data, such as Electronic Health Records (EHRs), and in this case, may either correspond to new knowledge or confirm state-of-the-art knowledge that lacks "clinical counterpart" or validation. For this reason, there is a need for automatic comparison of knowledge units from distinct sources.
RESULTS: In this article, we propose an approach, based on Semantic Web technologies, to represent and compare PGx knowledge units. To this end, we developed PGxO, a simple ontology that represents PGx knowledge units and their components. Combined with PROV-O, an ontology developed by the W3C to represent provenance information, PGxO enables encoding and associating provenance information to PGx relationships. Additionally, we introduce a set of rules to reconcile PGx knowledge, i.e. to identify when two relationships, potentially expressed using different vocabularies and levels of granularity, refer to the same, or to different knowledge units. We evaluated our ontology and rules by populating PGxO with knowledge units extracted from PharmGKB (2701), the literature (65,720) and from discoveries reported in EHR analysis studies (only 10, manually extracted); and by testing their similarity. We called PGxLOD (PGx Linked Open Data) the resulting knowledge base that represents and reconciles knowledge units of those various origins.
CONCLUSIONS: The proposed ontology and reconciliation rules constitute a first step toward a more complete framework for knowledge comparison in PGx. In this direction, the experimental instantiation of PGxO, named PGxLOD, illustrates the ability and difficulties of reconciling various existing knowledge sources.

PMID: 30999867 [PubMed - in process]

Adolescents' Developing Sensitivity to Orthographic and Semantic Cues During Visual Search for Words.

Front Psychol. 2019;10:642

Authors: Vibert N, Braasch JLG, Darles D, Potocki A, Ros C, Jaafari N, Rouet JF

Abstract
Two eye-tracking experiments were conducted to assess the influence of words either looking like the target word (orthographic distractors) or semantically related to the target word (semantic distractors) on visual search for words within lists by adolescents of 11, 13, and 15 years of age. In Experiment 1 (literal search task), participants saw the target word before the search (e.g., "raven"), whereas in Experiment 2 (categorical task) the target word was only defined by its semantic category (e.g., "bird"). In both experiments, participants' search times decreased from fifth to ninth grade, both because older adolescents gazed less often at non-target words during the search and because they could reject non-target words more quickly once they were fixated. Progress in visual search efficiency was associated with a large increase in word identification skills, which were a strong determinant of average gaze durations and search times for the categorical task, but much less for the literal task. In the literal task, the presence of orthographic or semantic distractors in the list increased search times for all age groups. In the categorical task, the impact of semantic distractor words was stronger than in the literal task because participants needed to gaze at the semantic distractors longer than at the other words before rejecting them. Altogether, the data support the assumption that the progressive automation of word decoding up until the age of 12 and the better quality of older adolescents' lexical representations facilitate a flexible use of both the perceptual and semantic features of words for top-down guidance within the displays. In particular, older adolescents were better prepared to aim at or reject words without gazing at them directly. Finally, the overall similar progression of the maturation of single word visual search processes and that of more real-life information search within complex verbal documents suggests that the young adolescents' difficulties in searching the Web effectively could be due to their insufficiently developed lexical representations and word decoding abilities.

PMID: 30971984 [PubMed]

The role of medical registries, potential applications and limitations.

Med Pharm Rep. 2019 Jan;92(1):7-14

Authors: Pop B, Fetica B, Blaga ML, Trifa AP, Achimas-Cadariu P, Vlad CI, Achimas-Cadariu A

Abstract
Medical registries provide highly reliable data, challenged hierarchically only by randomized controlled trials. Although registries have been used in several fields of medicine for more than a century and a half, their key role is frequently overlooked and poorly recognized. Medical registries have evolved from calculating basic epidemiological data (incidence, prevalence, mortality) to diverse applications in disease prevention, early diagnosis and screening programs, treatment response, health care planning, decision making and disease control programs. Implementing, maintaining and running a medical registry requires substantial effort. Developing the registry represents a complex task and is one of the major barriers in widespread use of registries. Medical registries have potential to evolve to a next generation by taking benefit from recent semantic web technology developments. This paper is aimed at providing a summary of the basic information available on medical registries and to highlight the progress and potential applications in this field.

PMID: 30957080 [PubMed]

StudyPortal - A Novel Method to Visualize Study Research Networks.

Stud Health Technol Inform. 2019;258:163

Authors: Varghese J, Fujarski M, Dugas M

Abstract
International trial databases as ClinicalTrials.gov or the EU Clinical Trials Register lack geographic visualization of clinical trials. Utilizing key requirements from patient support groups and clinical researchers, an interactive online platform called StudyPortal was designed. It enables patients, health providers and clinical researchers to find and localize suitable studies or whole research networks for selected diseases in a geographic proximity. A semantic layer enables multilingual disease input and autosuggestion. Trial information is pulled and processed from ClinicalTrials.gov. In addition, author affiliations of disease-related PubMed articles are retrievable in order to boost sensitivity of visualized research networks. The integration of a geodatabase and maps enables access to geospatial study search and visualization. A preliminary implementation of the platform is already accessible on the web: https://studyportal.uni-muenster.de. It showed that over 70% of trials and over 90% of scientific articles are visualized correctly by applying expert review and using Web of Science and the WHO trial database as external sources. Publication and trial-registration bias are significant issues that limit completeness of visualization. ClinicalTrials.gov, MEDLINE and geomaps are well-maintained but disconnected sources. StudyPortal integrates these sources to render a novel geospatial view of regional or global clinical research landscapes of US and European trials in real-time. Future work will focus on extensive search filters for recruitment status and intervention characteristics.

PMID: 30942737 [PubMed - in process]

Interoperability Improvement of Mobile Patient Survey (MoPat) Implementing Fast Health Interoperability Resources (FHIR).

Stud Health Technol Inform. 2019;258:141-145

Authors: Storck M, Hollenberg L, Dugas M, Soto-Rey I

Abstract
Despite the advances in health information technology and the increasing usage of electronic systems, syntactic and semantic interoperability between different health information systems remains challenging. An emerging standard to tackle interoperability issues is HL7 FHIR, which uses modern web technologies for communication like Representational State Transfer. The electronic patient reported outcome system Mobile Patient Survey (MoPat) was adapted to support metadata import and clinical data export using HL7 FHIR. Thereby, the data models of HL7 FHIR and MoPat were compared and the existing import and export functions of MoPat were extended to support HL7 FHIR. A test protocol including eight test datasets to proof functioning of the new features was successfully conducted. In the near future, a real time searching toolbar of FHIR metadata resources will be integrated within MoPat. MoPat FHIR import and export functions are ready to be used in a clinical setting in combination with a FHIR compliant clinical data server.

PMID: 30942732 [PubMed - in process]

Drivers for the development of an Animal Health Surveillance Ontology (AHSO).

Prev Vet Med. 2019 May 01;166:39-48

Authors: Dórea FC, Vial F, Hammar K, Lindberg A, Lambrix P, Blomqvist E, Revie CW

Abstract
Comprehensive reviews of syndromic surveillance in animal health have highlighted the hindrances to integration and interoperability among systems when data emerge from different sources. Discussions with syndromic surveillance experts in the fields of animal and public health, as well as computer scientists from the field of information management, have led to the conclusion that a major component of any solution will involve the adoption of ontologies. Here we describe the advantages of such an approach, and the steps taken to set up the Animal Health Surveillance Ontological (AHSO) framework. The AHSO framework is modelled in OWL, the W3C standard Semantic Web language for representing rich and complex knowledge. We illustrate how the framework can incorporate knowledge directly from domain experts or from data-driven sources, as well as by integrating existing mature ontological components from related disciplines. The development and extent of AHSO will be community driven and the final products in the framework will be open-access.

PMID: 30935504 [PubMed - in process]

Talk2Me: Automated linguistic data collection for personal assessment.

PLoS One. 2019;14(3):e0212342

Authors: Komeili M, Pou-Prom C, Liaqat D, Fraser KC, Yancheva M, Rudzicz F

Abstract
Language is one the earliest capacities affected by cognitive change. To monitor that change longitudinally, we have developed a web portal for remote linguistic data acquisition, called Talk2Me, consisting of a variety of tasks. In order to facilitate research in different aspects of language, we provide baselines including the relations between different scoring functions within and across tasks. These data can be used to augment studies that require a normative model; for example, we provide baseline classification results in identifying dementia. These data are released publicly along with a comprehensive open-source package for extracting approximately two thousand lexico-syntactic, acoustic, and semantic features. This package can be applied arbitrarily to studies that include linguistic data. To our knowledge, this is the most comprehensive publicly available software for extracting linguistic features. The software includes scoring functions for different tasks.

PMID: 30917120 [PubMed - in process]

Cognitive training for people with mild to moderate dementia.

Cochrane Database Syst Rev. 2019 Mar 25;3:CD013069

Authors: Bahar-Fuchs A, Martyr A, Goh AM, Sabates J, Clare L

Abstract
BACKGROUND: Cognitive impairment, a defining feature of dementia, plays an important role in the compromised functional independence that characterises the condition. Cognitive training (CT) is an approach that uses guided practice on structured tasks with the direct aim of improving or maintaining cognitive abilities.
OBJECTIVES: • To assess effects of CT on cognitive and non-cognitive outcomes for people with mild to moderate dementia and their caregivers.• To compare effects of CT with those of other non-pharmacological interventions, including cognitive stimulation or rehabilitation, for people with mild to moderate dementia and their caregivers.• To identify and explore factors related to intervention and trial design that may be associated with the efficacy of CT for people with mild to moderate dementia and their caregivers.
SEARCH METHODS: We searched ALOIS, the Cochrane Dementia and Cognitive Improvement Group Specialised Register, on 5 July 2018. ALOIS contains records of clinical trials identified through monthly searches of several major healthcare databases and numerous trial registries and grey literature sources. In addition to this, we searched MEDLINE, Embase, PsycINFO, CINAHL, LILACS, Web of Science Core Collection, ClinicalTrials.gov, and the World Health Organization's trials portal, ICTRP, to ensure that searches were comprehensive and up-to-date.
SELECTION CRITERIA: We included randomised controlled trials (RCTs) that described interventions for people with mild to moderate dementia and compared CT versus a control or alternative intervention.
DATA COLLECTION AND ANALYSIS: We extracted relevant data from published manuscripts and through contact with trial authors if required. We assessed risk of bias using the Cochrane 'Risk of bias' tool. We divided comparison conditions into active or passive control conditions and alternative treatments. We used a large number of measures and data to evaluate 19 outcomes at end of treatment, as well as 16 outcomes at follow-up in the medium term; we pooled this information in meta-analyses. We calculated pooled estimates of treatment effect using a random-effects model, and we estimated statistical heterogeneity using a standard Chi² statistic. We graded the evidence using GradePro.
MAIN RESULTS: The 33 included trials were published between 1988 and 2018 and were conducted in 12 countries; most were unregistered, parallel-group, single-site RCTs, with samples ranging from 12 to 653 participants. Interventions were between two and 104 weeks long. We classified most experimental interventions as 'straight CT', but we classified some as 'augmented CT', and about two-thirds as multi-domain interventions. Researchers investigated 18 passive and 13 active control conditions, along with 15 alternative treatment conditions, including occupational therapy, mindfulness, reminiscence therapy, and others.The methodological quality of studies varied, but we rated nearly all studies as having high or unclear risk of selection bias due to lack of allocation concealment, and high or unclear risk of performance bias due to lack of blinding of participants and personnel.We used data from 32 studies in the meta-analysis of at least one outcome. Relative to a control condition, we found moderate-quality evidence showing a small to moderate effect of CT on our first primary outcome, composite measure of global cognition at end of treatment (standardised mean difference (SMD) 0.42, 95% confidence interval (CI) 0.23 to 0.62), and high-quality evidence showing a moderate effect on the secondary outcome of verbal semantic fluency (SMD 0.52, 95% CI 0.23 to 0.81) at end of treatment, with these gains retained in the medium term (3 to 12 months post treatment). In relation to many other outcomes, including our second primary outcome of clinical disease severity in the medium term, the quality of evidence was very low, so we were unable to determine whether CT was associated with any meaningful gains.When compared with an alternative treatment, we found that CT may have little to no effect on our first primary outcome of global cognition at end of treatment (SMD 0.21, 95% CI -0.23 to 0.64), but the quality of evidence was low. No evidence was available to assess our second primary outcome of clinical disease severity in the medium term. We found moderate-quality evidence showing that CT was associated with improved mood of the caregiver at end of treatment, but this was based on a single trial. The quality of evidence in relation to many other outcomes at end of treatment and in the medium term was too low for us to determine whether CT was associated with any gains, but we are moderately confident that CT did not lead to any gains in mood, behavioural and psychological symptoms, or capacity to perform activities of daily living.
AUTHORS' CONCLUSIONS: Relative to a control intervention, but not to a variety of alternative treatments, CT is probably associated with small to moderate positive effects on global cognition and verbal semantic fluency at end of treatment, and these benefits appear to be maintained in the medium term. Our certainty in relation to many of these findings is low or very low. Future studies should take stronger measures to mitigate well-established risks of bias, and should provide long-term follow-up to improve our understanding of the extent to which observed gains are retained. Future trials should also focus on direct comparison of CT versus alternative treatments rather than passive or active control conditions.

PMID: 30909318 [PubMed - as supplied by publisher]

Too many tags spoil the metadata: investigating the knowledge management of scientific research with semantic web technologies.

J Cheminform. 2019 Mar 21;11(1):23

Authors: Kanza S, Gibbins N, Frey JG

Abstract
Scientific research is increasingly characterised by the volume of documents and data that it produces, from experimental plans and raw data to reports and papers. Researchers frequently struggle to manage and curate these materials, both individually and collectively. Previous studies of Electronic Lab Notebooks (ELNs) in academia and industry have identified semantic web technologies as a means for organising scientific documents to improve current workflows and knowledge management practices. In this paper, we present a qualitative, user-centred study of researcher requirements and practices, based on a series of discipline-specific focus groups. We developed a prototype semantic ELN to serve as a discussion aid for these focus groups, and to help us explore the technical readiness of a range of semantic web technologies. While these technologies showed potential, existing tools for semantic annotation were not well-received by our focus groups, and need to be refined before they can be used to enhance current researcher practices. In addition, the seemingly simple notion of "tagging and searching" documents appears anything but; the researchers in our focus groups had extremely personal requirements for how they organise their work, so the successful incorporation of semantic web technologies into their practices must permit a significant degree of customisation and personalisation.

PMID: 30900066 [PubMed]

A new wave of innovation in Semantic web tools for drug discovery.

Expert Opin Drug Discov. 2019 Mar 19;:1-12

Authors: Kanza S, Frey JG

Abstract
INTRODUCTION: The use of semantic web technologies to aid drug discovery has gained momentum over recent years. Researchers in this domain have realized that semantic web technologies are key to dealing with the high levels of data for drug discovery. These technologies enable us to represent the data in a formal, structured, interoperable and comparable way, and to tease out undiscovered links between drug data (be it identifying new drug-targets or relevant compounds, or links between specific drugs and diseases). Areas covered: This review focuses on explaining how semantic web technologies are being used to aid advances in drug discovery. The main types of semantic web technologies are explained, outlining how they work and how they can be used in the drug discovery process, with a consideration of how the use of these technologies has progressed from their initial usage. Expert opinion: The increased availability of shared semantic resources (tools, data and importantly the communities) have enabled the application of semantic web technologies to facilitate semantic (context dependent) search across multiple data sources, which can be used by machine learning to produce better predictions by exploiting the semantic links in knowledge graphs and linked datasets.

PMID: 30884989 [PubMed - as supplied by publisher]

Ontology-Defined Middleware for Internet of Things Architectures.

Sensors (Basel). 2019 Mar 07;19(5):

Authors: Caballero V, Valbuena S, Vernet D, Zaballos A

Abstract
The Internet of Things scenario is composed of an amalgamation of physical devices. Those physical devices are heterogeneous in their nature both in terms of communication protocols and in data exchange formats. The Web of Things emerged as a homogenization layer that uses well-established web technologies and semantic web technologies to exchange data. Therefore, the Web of Things enables such physical devices to the web, they become Web Things. Given such a massive number of services and processes that the Internet of Things/Web of Things enables, it has become almost mandatory to describe their properties and characteristics. Several web ontologies and description frameworks are devoted to that purpose. Ontologies such as SOSA/SSN or OWL-S describe the Web Things and their procedures to sense or actuate. For example, OWL-S complements SOSA/SSN in describing the procedures used for sensing/actuating. It is, however, not its scope to be specific enough to enable a computer program to interpret and execute the defined flow of control. In this work, it is our goal to investigate how we can model those procedures using web ontologies in a manner that allows us to directly deploy the procedure implementation. A prototype implementation of the results of our research is implemented along with an analysis of several use cases to show the generality of our proposal.

PMID: 30866533 [PubMed - in process]

"Similar query was answered earlier": processing of patient authored text for retrieving relevant contents from health discussion forum.

Health Inf Sci Syst. 2019 Dec;7(1):4

Authors: Saha SK, Prakash A, Majumder M

Abstract
Online remedy finders and health-related discussion forums have become increasingly popular in recent years. Common web users write their health problems there and request suggestion from experts or other users. As a result, these forums became a huge repository of information and discussions on various health issues. An intelligent information retrieval system can help to utilize this repository in various applications. In this paper, we propose a system for the automatic identification of existing similar forum posts given a new post. The system is based on computing similarity between two patient authored texts. For computing the similarity between the current post and existing posts, the system uses a hybrid strategy based on template information, topic modelling, and latent semantic indexing. The system is tested using a set of real questions collected from a homeopathy forum namely abchomeopathy.com. The relevance of the posts retrieved by the system is evaluated by human experts. The evaluation results demonstrate that the precision of the system is 88.87%.

PMID: 30863540 [PubMed]

How to Develop a Drug Target Ontology: KNowledge Acquisition and Representation Methodology (KNARM).

Methods Mol Biol. 2019;1939:49-69

Authors: Küçük McGinty H, Visser U, Schürer S

Abstract
Technological advancements in many fields have led to huge increases in data production, including data volume, diversity, and the speed at which new data is becoming available. In accordance with this, there is a lack of conformity in the ways data is interpreted. This era of "big data" provides unprecedented opportunities for data-driven research and "big picture" models. However, in-depth analyses-making use of various data types and data sources and extracting knowledge-have become a more daunting task. This is especially the case in life sciences where simplification and flattening of diverse data types often lead to incorrect predictions. Effective applications of big data approaches in life sciences require better, knowledge-based, semantic models that are suitable as a framework for big data integration, while avoiding oversimplifications, such as reducing various biological data types to the gene level. A huge hurdle in developing such semantic knowledge models, or ontologies, is the knowledge acquisition bottleneck. Automated methods are still very limited, and significant human expertise is required. In this chapter, we describe a methodology to systematize this knowledge acquisition and representation challenge, termed KNowledge Acquisition and Representation Methodology (KNARM). We then describe application of the methodology while implementing the Drug Target Ontology (DTO). We aimed to create an approach, involving domain experts and knowledge engineers, to build useful, comprehensive, consistent ontologies that will enable big data approaches in the domain of drug discovery, without the currently common simplifications.

PMID: 30848456 [PubMed - in process]

Databases for evaluating interferences between affective content and image quality.

Data Brief. 2019 Apr;23:103700

Authors: Gasparini F, Ciocca G, Corchs S

Abstract
The two databases here described were generated to evaluate the role of affective content while assessing image quality (Corchs et al., 2018) [1]. The databases are composed of images JPEG-compressed together with the subjective quality scores collected during psychophysical experiments. To reduce interferences in quality perception due to image semantic, we have restricted the semantic content, choosing only close-ups of face images, and we have considered only two emotion categories (happy and sad). We have selected 23 images with happy faces and 23 images with sad faces of high quality. For what concerns image quality we have considered JPEG-distortion with 4 levels of compression, corresponding to q-factors 10, 15, 20, 30. The first image database, hereafter called MMSP-FaceA, is thus composed of 230 images (23+23) × 5 quality levels (including the original high quality pristine images). To better consider only interferences in quality perception due to affective content, we have generated a second image database where the background of images belonging to MMSP-FaceA has been cut off. This second image database is labelled as MMSP-FaceB. Psychophysical experiments were conducted, on a controlled web-based interface, where participants rated the image quality of the two databases in a five point scale. The two final databases MMSP-FaceA and MMSP-FaceB are thus composed of 230 images each, together with the raw quality scores assigned by the observers, and are available at our laboratory web site: www.mmsp.unimib.it/download.

PMID: 30828597 [PubMed]

Towards the semantic enrichment of Computer Interpretable Guidelines: a method for the identification of relevant ontological terms.

AMIA Annu Symp Proc. 2018;2018:922-931

Authors: Quesada-Martínez M, Marcos M, Abad-Navarro F, Martínez-Salvador B, Fernández-Breis JT

Abstract
Clinical Practice Guidelines (CPGs) contain recommendations intended to optimize patient care, produced based on a systematic review of evidence. In turn, Computer-Interpretable Guidelines (CIGs) are formalized versions of CPGs for use as decision-support systems. We consider the enrichment of the CIG by means of an OWL ontology that describes the clinical domain of the CIG, which could be exploited e.g. for the interoperability with the Electronic Health Record (EHR). As a first step, in this paper we describe a method to support the development of such an ontology starting from a CIG. The method uses an alignment algorithm for the automated identification of ontological terms relevant to the clinical domain of the CIG, as well as a web platform to manually review the alignments and select the appropriate ones. Finally, we present the results of the application of the method to a small corpus of CIGs.

PMID: 30815135 [PubMed - in process]