Developing an Ontology Representing Fall Risk Management Domain Knowledge

Ontologies serve as comprehensive frameworks for organizing domain-specific knowledge, offering significant benefits for managing clinical data. This study presents the development of the Fall Risk Management Ontology (FRMO), designed to enhance clinical text mining, facilitate integration and interoperability between disparate data sources, and streamline clinical data analysis. By representing major entities within the fall risk management domain, the FRMO supports the unification of clinical language and decision-making processes, ultimately contributing to the prevention of falls among older adults. We used Ontology Web Language (OWL) to build the FRMO in Protégé. Of the seven steps of the Stanford approach, six steps were utilized in the development of the FRMO: (1) defining the domain and scope of the ontology, (2) reusing existing ontologies when possible, (3) enumerating ontology terms, (4) specifying the classes and their hierarchy, (5) defining the properties of the classes, and (6) defining the facets of the properties. We evaluated the FRMO using four main criteria: consistency, completeness, accuracy, and clarity. The developed ontology comprises 890 classes arranged in a hierarchical structure, including six top-level classes with a total of 43 object properties and 28 data properties. FRMO is the first comprehensively described semantic ontology for fall risk management. Healthcare providers can use the ontology as the basis of clinical decision technology for managing falls among older adults.

Online biomedical named entities recognition by data and knowledge-driven model

Named entity recognition (NER) is an important task for the natural language processing of biomedical text. Currently, most NER studies standardized biomedical text, but NER for unstandardized biomedical text draws less attention from researchers. Named entities in online biomedical text exist with errors and polymorphisms, which negatively impact NER models' performance and impede support from knowledge representation methods. In this paper, we propose a neural network method that can effectively recognize entities in unstandardized online medical/health text. We introduce a new pre-training scheme that uses large-scale online question-answering pairs to enhance transformers' model capacity on online biomedical text. Moreover, we supply models with knowledge representations from a knowledge base called multi-channel knowledge labels, and this method overcomes the restriction from languages, like Chinese, that require word segmentation tools to represent knowledge. Our model outperforms other baseline methods significantly in experiments on a dataset for Chinese online medical entity recognition and achieves state-of-the-art results.

Intelligent search system for resume and labor law

Labor and employment are important issues in social life. The demand for online job searching and searching for labor regulations in legal documents, particularly regarding the policy for unemployment benefits, is essential. Nowadays, each function has some programs for its working. However, there is no program that combines both functions. In practice, when users seek a job, they may be unemployed or want to transfer to another work. Thus, they are required to search for regulations about unemployment insurance policies and related information, as well as regulations about workers working smoothly and following labor law. Ontology is a useful technique for representing areas of practical knowledge. This article proposes an ontology-based method for solving labor and employment-related problems. First, we construct an ontology of job skills to match curriculum vitae (CV) and job descriptions (JD). In addition, an ontology for representing labor law documents is proposed to aid users in their search for legal labor law regulations. These ontologies are combined to construct the knowledge base of a job-searching and labor law-searching system. In addition, this integrated ontology is used to study several issues involving the matching of CVs and JDs and the search for labor law issues. A system for intelligent resume searching in information technology is developed using the proposed method. This system also incorporates queries pertaining to Vietnamese labor law policies regarding unemployment and healthcare benefits. The experimental results demonstrate that the method designed to assist job seekers and users searching for legal labor documents is effective.

Advancing Knowledge on Situation Comprehension in Dynamic Traffic Situations by Studying Eye Movements to Empty Spatial Locations

OBJECTIVE

This study used the looking-at-nothing phenomenon to explore situation awareness (SA) and the effects of working memory (WM) load in driving situations.

BACKGROUND

While driving, people develop a mental representation of the environment. Since errors in retrieving information from this representation can have fatal consequences, it is essential for road safety to investigate this process. During retrieval, people tend to fixate spatial positions of visually encoded information, even if it is no longer available at that location. Previous research has shown that this "looking-at-nothing" behavior can be used to trace retrieval processes.

METHOD

In a video-based laboratory experiment with 2 (WM) x 3 (SA level) within-subjects design, participants (N = 33) viewed a reduced screen and evaluated auditory statements relating to different SA levels on previously seen dynamic traffic scenarios while eye movements were recorded.

RESULTS

When retrieving information, subjects more frequently fixated emptied spatial locations associated with the information relevant for the probed SA level. The retrieval of anticipations (SA level 3) in contrast to the other SA level information resulted in more frequent gaze transitions that corresponded to the spatial dynamics of future driving behavior.

CONCLUSION

The results support the idea that people build a visual-spatial mental image of a driving situation. Different gaze patterns when retrieving level-specific information indicate divergent retrieval processes.

APPLICATION

Potential applications include developing new methodologies to assess the mental representation and SA of drivers objectively.

A precision medicine approach to personalized prescribing using genetic and nongenetic factors for clinical decision-making

Screening potential drug-drug interactions, drug-gene interactions, contraindications, and other factors is crucial in clinical practice. However, implementing these screening concepts in real-world settings poses challenges. This work proposes an approach towards precision medicine that combines genetic and nongenetic factors to facilitate clinical decision-making. The approach focuses on raising the performance of four potential interaction screenings in the prescribing process, including drug-drug interactions, drug-gene interactions, drug-herb interactions, drug-social lifestyle interactions, and two potential considerations for patients with liver or renal impairment. The work describes the design of a curated knowledge-based model called the knowledge model for potential interaction and consideration screening, the screening logic for both the detection module and inference module, and the personalized prescribing report. Three case studies have demonstrated the proof-of-concept and effectiveness of this approach. The proposed approach aims to reduce decision-making processes for healthcare professionals, reduce medication-related harm, and enhance treatment effectiveness. Additionally, the recommendation with a semantic network is suggested to assist in risk-benefit analysis when health professionals plan therapeutic interventions with new medicines that have insufficient evidence to establish explicit recommendations. This approach offers a promising solution to implementing precision medicine in clinical practice.

A framework for structured semantic representation capable of active sensing and interpretable inference: A cancer prognostic analysis case study

Precise semantic representation is important for allowing machines to truly comprehend the meaning of natural language text, especially biomedical literature. Although the semantic relations among words in a single sentence may be accurately represented with existing approaches, relations between two sentences cannot yet be accurately modeled, which leads to a lack of contextual information and difficulty in performing interpretable semantic inference. Additionally, it is challenging to merge semantic representations curated by different experts. These critical challenges are insufficiently addressed by existing methods. In this paper, we present a framework for structured semantic representation (FSSR) to address these issues. FSSR uses a double-layer structure Construct that combines Paradigm and Instance to represent the semantics of a word or a sentence. It uses six types of rules to represent the semantic relations between sentence Constructs and uses a Computational Model to represent an action. FSSR is a graph-based representation of semantics, in which a node represents a Construct or a Paradigm. Two nodes are connected by an edge (a rule). In addition, FSSR enables interpretable inference and active acquisition of new information, as illustrated in a case study. This case study models the semantics of a cancer prognostic analysis article and reproduces its text results and charts. We provide a website that visualizes the inference process (http://cragraph.synergylab.cn).

Extracting Complementary and Integrative Health Approaches in Electronic Health Records

Complementary and Integrative Health (CIH) has gained increasing popularity in the past decades. While the evidence bases to support them are growing, there is still a gap in understanding their effects and potential adverse events using real-world data. The overall goal of this study is to represent information pertinent to both psychological and physical CIH approaches (specifically, using examples of music therapy, chiropractic, and aquatic exercise in this study) in an electronic health record (EHR) system. We also aim to evaluate the ability of existing natural language processing (NLP) systems to identify CIH approaches. A total of 300 notes were randomly selected and manually annotated. Annotations were made for status, symptom, and frequency of each approach. This set of annotations was used as a gold standard to evaluate the performance of NLP systems used in this study (specifically BioMedICUS, MetaMap, and cTAKES) for extracting CIH concepts. Venn diagram was used to investigate the consistency of medical records searching by Current Procedural Terminology (CPT) codes and CIH approaches keywords in SQL. Since CPT codes usually do not have specific mentions of CIH approaches, the Venn diagram had less overlap with those found in clinical notes for all three CIH therapies. The three NLP systems achieved 0.41 in average lenient match F1-score in all three CIH approaches, respectively. BioMedICUS achieved the best performance in aquatic exercise with an F1-score of 0.66. This study contributes to the overall representation of CIH in clinical note and lays a foundation for using EHR for clinical research for CIH approaches.

Knowledge graph augmentation: consistency, immutability, reliability, and context

A knowledge graph is convenient for storing knowledge in artificial intelligence applications. On the other hand, it has some shortcomings that need to be improved. These shortcomings can be summarised as the inability to automatically update all the knowledge affecting a piece of knowledge when it changes, ambiguity, inability to sort the knowledge, inability to keep some knowledge immutable, and inability to make a quick comparison between knowledge. In our work, reliability, consistency, immutability, and context mechanisms are integrated into the knowledge graph to solve these deficiencies and improve the knowledge graph's performance. Hash technology is used in the design of these mechanisms. In addition, the mechanisms we have developed are kept separate from the knowledge graph to ensure that the functionality of the knowledge graph is not impaired. The mechanisms we developed within the scope of the study were tested by comparing them with the traditional knowledge graph. It was shown graphically and with t-test methods that our proposed structures have higher performance in terms of update and comparison. It is expected that the mechanisms we have developed will contribute to improving the performance of artificial intelligence software using knowledge graphs.

Creating an ignorance-base: Exploring known unknowns in the scientific literature

BACKGROUND

Scientific discovery progresses by exploring new and uncharted territory. More specifically, it advances by a process of transforming unknown unknowns first into known unknowns, and then into knowns. Over the last few decades, researchers have developed many knowledge bases to capture and connect the knowns, which has enabled topic exploration and contextualization of experimental results. But recognizing the unknowns is also critical for finding the most pertinent questions and their answers. Prior work on known unknowns has sought to understand them, annotate them, and automate their identification. However, no knowledge-bases yet exist to capture these unknowns, and little work has focused on how scientists might use them to trace a given topic or experimental result in search of open questions and new avenues for exploration. We show here that a knowledge base of unknowns can be connected to ontologically grounded biomedical knowledge to accelerate research in the field of prenatal nutrition.

RESULTS

We present the first ignorance-base, a knowledge-base created by combining classifiers to recognize ignorance statements (statements of missing or incomplete knowledge that imply a goal for knowledge) and biomedical concepts over the prenatal nutrition literature. This knowledge-base places biomedical concepts mentioned in the literature in context with the ignorance statements authors have made about them. Using our system, researchers interested in the topic of vitamin D and prenatal health were able to uncover three new avenues for exploration (immune system, respiratory system, and brain development) by searching for concepts enriched in ignorance statements. These were buried among the many standard enriched concepts. Additionally, we used the ignorance-base to enrich concepts connected to a gene list associated with vitamin D and spontaneous preterm birth and found an emerging topic of study (brain development) in an implied field (neuroscience). The researchers could look to the field of neuroscience for potential answers to the ignorance statements.

CONCLUSION

Our goal is to help students, researchers, funders, and publishers better understand the state of our collective scientific ignorance (known unknowns) in order to help accelerate research through the continued illumination of and focus on the known unknowns and their respective goals for scientific knowledge.

A novel gluten knowledge base of potential biomedical and health-related interactions extracted from the literature: using machine learning and graph analysis methodologies to reconstruct the bibliome

BACKGROUND

In return for their nutritional properties and broad availability, cereal crops have been associated with different alimentary disorders and symptoms, with the majority of the responsibility being attributed to gluten. Therefore, the research of gluten-related literature data continues to be produced at ever-growing rates, driven in part by the recent exploratory studies that link gluten to non-traditional diseases and the popularity of gluten-free diets, making it increasingly difficult to access and analyse practical and structured information. In this sense, the accelerated discovery of novel advances in diagnosis and treatment, as well as exploratory studies, produce a favourable scenario for disinformation and misinformation.

OBJECTIVES

Aligned with, the European Union strategy "Delivering on EU Food Safety and Nutrition in 2050" which emphasizes the inextricable links between imbalanced diets, the increased exposure to unreliable sources of information and misleading information, and the increased dependency on reliable sources of information; this paper presents GlutKNOIS, a public and interactive literature-based database that reconstructs and represents the experimental biomedical knowledge extracted from the gluten-related literature. The developed platform includes different external database knowledge, bibliometrics statistics and social media discussion to propose a novel and enhanced way to search, visualise and analyse potential biomedical and health-related interactions in relation to the gluten domain.

METHODS

For this purpose, the presented study applies a semi-supervised curation workflow that combines natural language processing techniques, machine learning algorithms, ontology-based normalization and integration approaches, named entity recognition methods, and graph knowledge reconstruction methodologies to process, classify, represent and analyse the experimental findings contained in the literature, which is also complemented by data from the social discussion.

RESULTS

and Conclusions: In this sense, 5,814 documents were manually annotated and 7,424 were fully automatically processed to reconstruct the first online gluten-related knowledge database of evidenced health-related interactions that produce health or metabolic changes based on the literature. In addition, the automatic processing of the literature combined with the knowledge representation methodologies proposed has the potential to assist in the revision and analysis of years of gluten research. The reconstructed knowledge base is public and accessible at https://sing-group.org/glutknois/.

How do automated reasoning features impact the usability of a clinical task management system? Development and usability testing of a prototype

BACKGROUND

Electronic clinical task management systems (ECTMSs) have been developed and adopted by care providers to improve care coordination. Some systems utilised automated reasoning (AR) to enable more intelligent task management functionalities, such as automated task allocation. Yet, the impact of such features on usability remains unclear. Poor usability of health information systems has been described to cause frustration and contribute to patient safety incidents.

AIM

To design AR features for an ECTMS and to evaluate their impact on usability.

METHODS

In this mixed methods study, four ECTMS feature prototypes were co-designed with two clinicians. For each prototype, one AR variant and one non-AR variant with equivalent functionalities were developed. A moderated usability testing was conducted with seven clinicians to obtain ease-of-use ratings of prototypes and measure task durations. Parameters related to demographics and attitudes of participants were obtained via a questionnaire. A framework analysis was performed to summarise qualitative feedback. To determine statistical relationships of study variables, Spearmańs rank coefficients were calculated and presented as a correlation matrix.

RESULTS

Three out of four prototypes received higher median ease-of-use ratings for AR variants and were associated with shorter average task durations. Multiple clinical use cases suitable for AR were identified. Preference for AR was found to moderately correlate with digital proficiency and prior experience with ECTMSs. Insufficient trust in automation, alert fatigue, and system customisation were identified as challenges in the adoption of AR features.

CONCLUSIONS

This study provides evidence for the potential of AR to enhance usability in ECTMSs. Consideration of psychological and organisational context of users in the feature design was found to be decisive for usability. Future research should explore implications for operational and clinical outcomes.

Investigating the network structure of domain-specific knowledge using the semantic fluency task

Cognitive scientists have a long-standing interest in quantifying the structure of semantic memory. Here, we investigate whether a commonly used paradigm to study the structure of semantic memory, the semantic fluency task, as well as computational methods from network science could be leveraged to explore the underlying knowledge structures of academic disciplines such as psychology or biology. To compare the knowledge representations of individuals with relatively different levels of expertise in academic subjects, undergraduate students (i.e., experts) and preuniversity high school students (i.e., novices) completed a semantic fluency task with cue words corresponding to general semantic categories (i.e., animals, fruits) and specific academic domains (e.g., psychology, biology). Network analyses of their fluency networks found that both domain-general and domain-specific semantic networks of undergraduates were more efficiently connected and less modular than the semantic networks of high school students. Our results provide an initial proof-of-concept that the semantic fluency task could be used by educators and cognitive scientists to study the representation of more specific domains of knowledge, potentially providing new ways of quantifying the nature of expert cognitive representations.

Developing a Knowledge Graph for Pharmacokinetic Natural Product-Drug Interactions

BACKGROUND

Pharmacokinetic natural product-drug interactions (NPDIs) occur when botanical or other natural products are co-consumed with pharmaceutical drugs. With the growing use of natural products, the risk for potential NPDIs and consequent adverse events has increased. Understanding mechanisms of NPDIs is key to preventing or minimizing adverse events. Although biomedical knowledge graphs (KGs) have been widely used for drug-drug interaction applications, computational investigation of NPDIs is novel. We constructed NP-KG as a first step toward computational discovery of plausible mechanistic explanations for pharmacokinetic NPDIs that can be used to guide scientific research.

METHODS

We developed a large-scale, heterogeneous KG with biomedical ontologies, linked data, and full texts of the scientific literature. To construct the KG, biomedical ontologies and drug databases were integrated with the Phenotype Knowledge Translator framework. The semantic relation extraction systems, SemRep and Integrated Network and Dynamic Reasoning Assembler, were used to extract semantic predications (subject-relation-object triples) from full texts of the scientific literature related to the exemplar natural products green tea and kratom. A literature-based graph constructed from the predications was integrated into the ontology-grounded KG to create NP-KG. NP-KG was evaluated with case studies of pharmacokinetic green tea- and kratom-drug interactions through KG path searches and meta-path discovery to determine congruent and contradictory information in NP-KG compared to ground truth data. We also conducted an error analysis to identify knowledge gaps and incorrect predications in the KG.

RESULTS

The fully integrated NP-KG consisted of 745,512 nodes and 7,249,576 edges. Evaluation of NP-KG resulted in congruent (38.98% for green tea, 50% for kratom), contradictory (15.25% for green tea, 21.43% for kratom), and both congruent and contradictory (15.25% for green tea, 21.43% for kratom) information compared to ground truth data. Potential pharmacokinetic mechanisms for several purported NPDIs, including the green tea-raloxifene, green tea-nadolol, kratom-midazolam, kratom-quetiapine, and kratom-venlafaxine interactions were congruent with the published literature.

CONCLUSION

NP-KG is the first KG to integrate biomedical ontologies with full texts of the scientific literature focused on natural products. We demonstrate the application of NP-KG to identify known pharmacokinetic interactions between natural products and pharmaceutical drugs mediated by drug metabolizing enzymes and transporters. Future work will incorporate context, contradiction analysis, and embedding-based methods to enrich NP-KG. NP-KG is publicly available at https://doi.org/10.5281/zenodo.6814507. The code for relation extraction, KG construction, and hypothesis generation is available at https://github.com/sanyabt/np-kg.

Sentiment analysis: A survey on design framework, applications and future scopes

Sentiment analysis is a solution that enables the extraction of a summarized opinion or minute sentimental details regarding any topic or context from a voluminous source of data. Even though several research papers address various sentiment analysis methods, implementations, and algorithms, a paper that includes a thorough analysis of the process for developing an efficient sentiment analysis model is highly desirable. Various factors such as extraction of relevant sentimental words, proper classification of sentiments, dataset, data cleansing, etc. heavily influence the performance of a sentiment analysis model. This survey presents a systematic and in-depth knowledge of different techniques, algorithms, and other factors associated with designing an effective sentiment analysis model. The paper performs a critical assessment of different modules of a sentiment analysis framework while discussing various shortcomings associated with the existing methods or systems. The paper proposes potential multidisciplinary application areas of sentiment analysis based on the contents of data and provides prospective research directions.

From eye movements to scanpath networks: A method for studying individual differences in expository text reading

Eye movements have been examined as an index of attention and comprehension during reading in the literature for over 30 years. Although eye-movement measurements are acknowledged as reliable indicators of readers' comprehension skill, few studies have analyzed eye-movement patterns using network science. In this study, we offer a new approach to analyze eye-movement data. Specifically, we recorded visual scanpaths when participants were reading expository science text, and used these to construct scanpath networks that reflect readers' processing of the text. Results showed that low ability and high ability readers' scanpath networks exhibited distinctive properties, which are reflected in different network metrics including density, centrality, small-worldness, transitivity, and global efficiency. Such patterns provide a new way to show how skilled readers, as compared with less skilled readers, process information more efficiently. Implications of our analyses are discussed in light of current theories of reading comprehension.

Modeling and integrating interactions involving the CYP450 enzyme system in a multi-terminology server: Contribution to information extraction from a clinical data warehouse

INTRODUCTION

The cytochrome P450 (CYP450) enzyme system is involved in the metabolism of certain drugs and is responsible for most drug interactions. These interactions result in either an enzymatic inhibition or an enzymatic induction mechanism that has an impact on the therapeutic management of patients. Detecting these drug interactions will allow for better predictability in therapeutic response. Therefore, computerized solutions can represent a valuable help for clinicians in their tasks of detection.

OBJECTIVE

The objective of this study is to provide a structured data-source of interactions involving the CYP450 enzyme system. These interactions are aimed to be integrated in the cross-lingual multi-terminology server HeTOP (Health Terminologies and Ontologies Portal), to support the query processing of the clinical data warehouse (CDW) EDSaN (Entrepôt de Données de Santé Normand).

MATERIAL AND METHODS

A selection and curation of drug components (DCs) that share a relationship with the CYP450 system was performed from several international data sources. The DCs were linked according to the type of relationship which can be substrate, inhibitor, or inducer. These relationships were then integrated into the HeTOP server. To validate the CYP450 relationships, a semantic query was performed on the CDW, whose search engine is founded on HeTOP data (concepts, terms, and relations).

RESULTS

A total of 776 DCs are associated by a new interaction relationship, integrated in HeTOP, by 14 enzymes. These are CYP450 1A2, 2A6, 2B6, 2C8, 2C9, 2C18, 2C19, 2D6, 2E1, 3A4, 3A7, 11B1,11B2 mitochondrial and P-glycoprotein, constituting a total of 2,088 relationships. A general modelling of cytochromic interactions was performed. From this model, 233,006 queries were processed in less than two hours, demonstrating the usefulness and performance of our CDW implementation. Moreover, they showed that in our university hospital, the concurrent prescription that could cause a cytochromic interaction is Bisoprolol with Amiodarone by enzymatic inhibition for 2,493 patients.

DISCUSSION

The queries submitted to the CDW EDSaN allowed to highlight the most prescribed molecules simultaneously and potentially responsible for cytochromic interactions. In a second step, it would be interesting to evaluate the real clinical impact by looking for possible adverse effects of these interactions in the patients' files. Other computational solutions for cytochromic interactions exist. The impact of CYP450 is particularly important for drugs with narrow therapeutic window (NTW) as they can lead to increased toxicity or therapeutic failure. It is also important to define which drug component is a pro-drug and to considerate the many genetic polymorphisms of patients.

CONCLUSION

The HeTOP server contains a non-negligible number of relationships between drug components and CYP450 from multiple reference sources. These data allow us to query our Clinical Data Warehouse to highlight these cytochromic interactions. It would be interesting in the future to assess the actual clinical impact in hospital reports.

A method for structuring complex clinical knowledge and its representational formalisms to support composite knowledge interoperability in healthcare

INTRODUCTION

The use and interoperability of clinical knowledge starts with the quality of the formalism utilized to express medical expertise. However, a crucial challenge is that existing formalisms are often suboptimal, lacking the fidelity to represent complex knowledge thoroughly and concisely. Often this leads to difficulties when seeking to unambiguously capture, share, and implement the knowledge for care improvement in clinical information systems used by providers and patients.

OBJECTIVES

To provide a systematic method to address some of the complexities of knowledge composition and interoperability related to standards-based representational formalisms of medical knowledge.

METHODS

Several cross-industry (Healthcare, Linguistics, System Engineering, Standards Development, and Knowledge Engineering) frameworks were synthesized into a proposed reference knowledge framework. The framework utilizes IEEE 42010, the MetaObject Facility, the Semantic Triangle, an Ontology Framework, and the Domain and Comprehensibility Appropriateness criteria. The steps taken were: 1) identify foundational cross-industry frameworks, 2) select architecture description method, 3) define life cycle viewpoints, 4) define representation and knowledge viewpoints, 5) define relationships between neighboring viewpoints, and 6) establish characteristic definitions of the relationships between components. System engineering principles applied included separation of concerns, cohesion, and loose coupling.

RESULTS

A "Multilayer Metamodel for Representation and Knowledge" (M*R/K) reference framework was defined. It provides a standard vocabulary for organizing and articulating medical knowledge curation perspectives, concepts, and relationships across the artifacts created during the life cycle of language creation, authoring medical knowledge, and knowledge implementation in clinical information systems such as electronic health records (EHR).

CONCLUSION

M*R/K provides a systematic means to address some of the complexities of knowledge composition and interoperability related to medical knowledge representations used in diverse standards. The framework may be used to guide the development, assessment, and coordinated use of knowledge representation formalisms. M*R/K could promote the alignment and aggregated use of distinct domain-specific languages in composite knowledge artifacts such as clinical practice guidelines (CPGs).

PToPI: A Comprehensive Review, Analysis, and Knowledge Representation of Binary Classification Performance Measures/Metrics

Although few performance evaluation instruments have been used conventionally in different machine learning-based classification problem domains, there are numerous ones defined in the literature. This study reviews and describes performance instruments via formally defined novel concepts and clarifies the terminology. The study first highlights the issues in performance evaluation via a survey of 78 mobile-malware classification studies and reviews terminology. Based on three research questions, it proposes novel concepts to identify characteristics, similarities, and differences of instruments that are categorized into 'performance measures' and 'performance metrics' in the classification context for the first time. The concepts reflecting the intrinsic properties of instruments such as canonical form, geometry, duality, complementation, dependency, and leveling, aim to reveal similarities and differences of numerous instruments, such as redundancy and ground-truth versus prediction focuses. As an application of knowledge representation, we introduced a new exploratory table called PToPI (Periodic Table of Performance Instruments) for 29 measures and 28 metrics (69 instruments including variant and parametric ones). Visualizing proposed concepts, PToPI provides a new relational structure for the instruments including graphical, probabilistic, and entropic ones to see their properties and dependencies all in one place. Applications of the exploratory table in six examples from different domains in the literature have shown that PToPI aids overall instrument analysis and selection of the proper performance metrics according to the specific requirements of a classification problem. We expect that the proposed concepts and PToPI will help researchers comprehend and use the instruments and follow a systematic approach to classification performance evaluation and publication.

Clinical decision support system for hypertension medication based on knowledge graph

BACKGROUND

High prevalence of hypertension and complicated medication knowledge have presented challenges to hypertension clinicians and general practitioners. Clinical decision support systems (CDSSs) are developed to aid clinicians in decision making. Current clinical knowledge is stored in fixed templates, which are not intuitive for clinicians and limit the knowledge reusability. Knowledge graphs (KGs) store knowledge in a way that is not only intuitive to humans but also processable by computers directly. However, existing medical KGs such as UMLS and CMeKG are general purpose and thus lack enough knowledge to enable hypertension medication.

METHODS

We first construct a KG specific to hypertension medication according to the Chinese hypertension guideline and then develop the corresponding CDSS to implement hypertension medication and knowledge management. Current advances in knowledge graph representation and modelling are researched and applied in the complex medical knowledge representation. Traditional knowledge representation and KG representation are innovatively combined in the storage of the KG to enable convenient knowledge management and easy application by the CDSS. Along a predefined reasoning path in the KG, the CDSS finally accomplishes the hypertension medication by applying knowledge stored in the KG. 124 health records of a hypertension Chief Physician from Beijing Anzhen Hospital, Capital Medical University, are collected to evaluate the system metrics on the single drug recommendation task.

RESULTS AND CONCLUSION

The proposed CDSS has functions of medication knowledge graph management and hypertension medication decision support. With elaborate design on knowledge representation, knowledge management is intuitive and convenient. By virtue of the KG, medication recommendations are highly visualized and explainable. Experiments on 124 health records with 90% guideline compliance collected from hospitals in single class recommendation task achieve 91%, 83% and 77% on recall, hit@3 and MRR metrics respectively, which demonstrates the quality of the KG and effectiveness of the system.

Legal document assembly system for introducing law students with legal drafting

In this paper, we present a method for introducing law students to the writing of legal documents. The method uses a machine-readable representation of the legal knowledge to support document assembly and to help the students to understand how the assembly is performed. The knowledge base consists of enacted legislation, document templates, and assembly instructions. We propose a system called LEDAS (LEgal Document Assembly System) for the interactive assembly of legal documents. It guides users through the assembly process and provides explanations of the interconnection between input data and claims stated in the document. The system acts as a platform for practicing drafting skills and has great potential as an education tool. It allows teachers to configure the system for the assembly of some particular type of legal document and then enables students to draft the documents by investigating which information is relevant for these documents and how the input data shape the final document. The generated legal document is complemented by a graphical representation of legal arguments expressed in the document. The system is based on existing legal standards to facilitate its introduction in the legal domain. Applicability of the system in the education of future lawyers is positively evaluated by the group of law students and their TA.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10506-022-09339-2.

Toward a standard formal semantic representation of the model card report

BACKGROUND

Model card reports aim to provide informative and transparent description of machine learning models to stakeholders. This report document is of interest to the National Institutes of Health's Bridge2AI initiative to address the FAIR challenges with artificial intelligence-based machine learning models for biomedical research. We present our early undertaking in developing an ontology for capturing the conceptual-level information embedded in model card reports.

RESULTS

Sourcing from existing ontologies and developing the core framework, we generated the Model Card Report Ontology. Our development efforts yielded an OWL2-based artifact that represents and formalizes model card report information. The current release of this ontology utilizes standard concepts and properties from OBO Foundry ontologies. Also, the software reasoner indicated no logical inconsistencies with the ontology. With sample model cards of machine learning models for bioinformatics research (HIV social networks and adverse outcome prediction for stent implantation), we showed the coverage and usefulness of our model in transforming static model card reports to a computable format for machine-based processing.

CONCLUSIONS

The benefit of our work is that it utilizes expansive and standard terminologies and scientific rigor promoted by biomedical ontologists, as well as, generating an avenue to make model cards machine-readable using semantic web technology. Our future goal is to assess the veracity of our model and later expand the model to include additional concepts to address terminological gaps. We discuss tools and software that will utilize our ontology for potential application services.

Representation and Normalization of Complex Interventions for Evidence Computing

Complex interventions are ubiquitous in healthcare. A lack of computational representations and information extraction solutions for complex interventions hinders accurate and efficient evidence synthesis. In this study, we manually annotated and analyzed 3,447 intervention snippets from 261 randomized clinical trial (RCT) abstracts and developed a compositional representation for complex interventions, which captures the spatial, temporal and Boolean relations between intervention components, along with an intervention normalization pipeline that automates three tasks: (i) treatment entity extraction; (ii) intervention component relation extraction; and (iii) attribute extraction and association. 361 intervention snippets from 29 unseen abstracts were included to report on the performance of the evaluation. The average F-measure was 0.74 for treatment entity extraction on an exact match and 0.82 for attribute extraction. The F-measure for relation extraction of multi-component complex interventions was 0.90. 93% of extracted attributes were correctly attributed to corresponding treatment entities.

Temporal Medical Knowledge Representation Using Ontologies

Representing temporal information is a recurrent problem for biomedical ontologies. We propose a foundational ontology that combines the so-called three-dimensional and four-dimensional approaches in order to be able to track changes in an individual and to trace his or her medical history. This requires, on the one hand, associating with any representation of an individual the representation of his or her life course and, on the other hand, distinguishing the properties that characterize this individual from those that characterize his or her life course.

Delta-modulated cortical alpha oscillations support new knowledge generation through memory integration

The ability to generate new knowledge depends on integration of separate information. For example, in one episode an individual may learn that apple seeds are called pips. In a separate episode, the individual may then learn that pips contain cyanide. Integration of the related facts in memory may then support derivation of the new knowledge that apple seeds contain cyanide. Past studies show that adults form relational memories that represent the commonalities among discrete events, and that such integrated representation supports the ability to infer new knowledge. Although these integrated representations are thought to result from linking separate memories to the same neuronal ensemble, the neural mechanisms that underlie formation of such linkages are not well understood. Here we examined whether self-derivation of new, integrated knowledge was supported by oscillatory coherence, a means of linking discrete neuronal ensembles. Cortical alpha coherence was greater when adults encoded new facts that could be integrated with existing knowledge, relative to encoding unrelated facts, particularly in participants who showed better performance on the subsequent test of knowledge generation via fact integration. In high performers, posterior alpha amplitude was also modulated by delta phase, a form of cross-frequency coupling previously implicated in coordinating information stored widely throughout the cortex. Examination of the timing and topography of these respective signatures suggested that these oscillatory dynamics work in concert to encode and represent new knowledge with respect to prior knowledge that is reactivated, thus revealing fundamental mechanisms through which related memories are linked into integrated knowledge structures.

Biomedical Ontologies to Guide AI Development in Radiology

The advent of deep learning has engendered renewed and rapidly growing interest in artificial intelligence (AI) in radiology to analyze images, manipulate textual reports, and plan interventions. Applications of deep learning and other AI approaches must be guided by sound medical knowledge to assure that they are developed successfully and that they address important problems in biomedical research or patient care. To date, AI has been applied to a limited number of real-world radiology applications. As AI systems become more pervasive and are applied more broadly, they will benefit from medical knowledge on a larger scale, such as that available through computer-based approaches. A key approach to represent computer-based knowledge in a particular domain is an ontology. As defined in informatics, an ontology defines a domain's terms through their relationships with other terms in the ontology. Those relationships, then, define the terms' semantics, or "meaning." Biomedical ontologies commonly define the relationships between terms and more general terms, and can express causal, part-whole, and anatomic relationships. Ontologies express knowledge in a form that is both human-readable and machine-computable. Some ontologies, such as RSNA's RadLex radiology lexicon, have been applied to applications in clinical practice and research, and may be familiar to many radiologists. This article describes how ontologies can support research and guide emerging applications of AI in radiology, including natural language processing, image-based machine learning, radiomics, and planning.

Implementation and evaluation of a multivariate abstraction-based, interval-based dynamic time-warping method as a similarity measure for longitudinal medical records

OBJECTIVES

A common prerequisite for tasks such as classification, prediction, clustering and retrieval of longitudinal medical records is a clinically meaningful similarity measure that considers both [multiple] variable (concept) values and their time. Currently, most similarity measures focus on raw, time-stamped data as these are stored in a medical record. However, clinicians think in terms of clinically meaningful temporal abstractions, such as "decreasing renal functions", enabling them to ignore minor time and value variations and focus on similarities among the clinical trajectories of different patients. Our objective was to define an abstraction- and interval-based methodology for matching longitudinal, multivariate medical records, and rigorously assess its value, versus the option of using just the raw, time-stamped data.

METHODS

We have developed a new methodology for determination of the relative distance between a pair of longitudinal records, by extending the known dynamic time warping (DTW) method into an interval-based dynamic time warping (iDTW) methodology. The iDTW methodology includes (A): A three-steps interval-based representation (iRep) method: [1] abstracting the raw, time-stamped data of the longitudinal records into clinically meaningful interval-based abstractions, using a domain-specific knowledge base, [2] scoping the period of comparison of the records, [3] creating from the intervals a symbolic time series, by partitioning them into a predetermined temporal granularity; (B) An interval-based matching (iMatch) method to match each relevant pair of multivariate longitudinal records, each represented as multiple series of short symbolic intervals in the determined temporal granularity, using a modified DTW version.

EVALUATION

Three classification or prediction tasks were defined: (1) classifying 161 records of oncology patients as having had autologous versus allogenic bone-marrow transplantation; (2) classifying the longitudinal records of 125 hepatitis patients as having B or C hepatitis; and (3) predicting micro- or macro-albuminuria in the second year, for 151 diabetes patients who were followed for five years. The raw, time-stamped, multivariate data within each medical record, for one, two, or three concepts out of four or five concepts judged as relevant in each medical domain, were abstracted into clinically meaningful intervals using the Knowledge-Based Temporal-Abstraction method, using previously acquired knowledge. We focused on two temporal-abstraction types: (1) State abstractions, which discretize a concept's raw value into a predetermined range (e.g., LOW or HIGH Hemoglobin); and (2) Gradient abstractions, which indicate the trend of the concept's value (e.g., INCREASING, DECREASING Hemoglobin value). We created all of the combinations of either uni-dimensional (State or Gradient) or multi-dimensional (State and Gradient) abstractions, of all of the concepts used. Classification of a record was determined by using a majority of the k-Nearest-Neighbors (KNN) of the given record, k ranging over the odd numbers (to break ties) from 1 to N, N being the size of the training set. We have experimented with all possible configurations of the parameters that our method uses. Overall, a total of 75,936 experiments were performed: 33,600 in the Oncology domain, 28,800 in the Hepatitis domain, and 13,536 in the Diabetes domain. Each experiment involved the performance of a 10-fold Cross Validation to compute the mean performance of a particular iDTW method-configuration set of settings, for a specific subset of one, two, or three concepts out of all of the domain-specific concepts relevant to the classification or prediction task on which the experiment focuses. We measured for each such experimental combination the Area Under the Curve (AUC) and the optimal Specificity/Sensitivity ratio using Youden's Index. We then aggregated the experiments by the types of unidimensional or multidimensional abstractions used in them (including the use of only raw concepts as a special case); for example, two state abstractions of different concepts, and one gradient abstraction of a third concept. We compared the mean AUC when using each such feature representation, or combination of abstractions, across all possible method-setting configurations, to the mean AUC when using as a feature representation, for the same task, only raw concepts, also across all possible method-setting configurations. Finally, we applied a paired t-test, to determine whether the mean difference between the accuracy of each temporal-abstraction representation, across all concept and configuration combinations, and the respective raw-concept combinations, across all concept subset and configuration combinations, is significant (P < 0.05).

RESULTS

The mean performance of the classification and prediction tasks when using, as a feature representation, the various temporal-abstraction combinations, was significantly higher than that performance when using only raw data. Furthermore, in each domain and task, there existed at least one representation using interval-based abstractions whose use led, on average (over all concept subset combinations and method configurations) to a significantly better performance than the use of only subsets of the raw time-stamped data. In seven of nine combinations of domain type (out of three) and number of concepts used (one, two, or three), the variance of the AUCs (for all representations and configurations) was considerably higher across all raw-concept subsets, compared to all abstract combinations. Increasing the number of features used by the matching task enhanced performance. Using multi-dimensional abstractions of the same concept further enhanced the performance. When using only raw data, increasing the number of neighbors monotonically increased the mean performance (over all concept combinations and method configurations) until reaching an optimal saddle-point aroundN; when using abstractions, however, optimal mean performance was often reached after matching only five nearest neighbors.

CONCLUSIONS

Using multivariate and multidimensional interval-based, abstraction-based similarity measures is feasible, and consistently and significantly improved the mean classification and prediction performance in time-oriented domains, using DTW-inspired methods, compared to the use of only raw, time-stamped data. It also made the KNN classification more effective. Nevertheless, although the mean performance for the abstract representations was higher than the mean performance when using only raw-data concepts, the actual optimal classification performance in each domain and task depends on the choice of the specific raw or abstract concepts used as features.

Formalization of gene regulation knowledge using ontologies and gene ontology causal activity models

Gene regulation computational research requires handling and integrating large amounts of heterogeneous data. The Gene Ontology has demonstrated that ontologies play a fundamental role in biological data interoperability and integration. Ontologies help to express data and knowledge in a machine processable way, which enables complex querying and advanced exploitation of distributed data. Contributing to improve data interoperability in gene regulation is a major objective of the GREEKC Consortium, which aims to develop a standardized gene regulation knowledge commons. GREEKC proposes the use of ontologies and semantic tools for developing interoperable gene regulation knowledge models, which should support data annotation. In this work, we study how such knowledge models can be generated from cartoons of gene regulation scenarios. The proposed method consists of generating descriptions in natural language of the cartoons; extracting the entities from the texts; finding those entities in existing ontologies to reuse as much content as possible, especially from well known and maintained ontologies such as the Gene Ontology, the Sequence Ontology, the Relations Ontology and ChEBI; and implementation of the knowledge models. The models have been implemented using Protégé, a general ontology editor, and Noctua, the tool developed by the Gene Ontology Consortium for the development of causal activity models to capture more comprehensive annotations of genes and link their activities in a causal framework for Gene Ontology Annotations. We applied the method to two gene regulation scenarios and illustrate how to apply the models generated to support the annotation of data from research articles.

Autonomous Systems and Artificial Intelligence - Hype or Prerequisite for P5 Medicine?

For meeting the challenge of aging, multi-diseased societies, cost containment, workforce development and consumerism by improved care quality and patient safety as well as more effective and efficient care processes, health and social care systems around the globe undergo an organizational, methodological and technological transformation towards personalized, preventive, predictive, participative precision medicine (P5 medicine). This paper addresses chances, challenges and risks of specific disruptive methodologies and technologies for the transformation of health and social care systems, especially focusing on the deployment of intelligent and autonomous systems.

OntoRepliCov: an Ontology-Based Approach for Modeling the SARS-CoV-2 Replication Process

Understanding the replication machinery of viruses contributes to suggest and try effective antiviral strategies. Exhaustive knowledge about the proteins structure, their function, or their interaction is one of the preconditions for successfully modeling it. In this context, modeling methods based on a formal representation with a high semantic expressiveness would be relevant to extract proteins and their nucleotide or amino acid sequences as an element from the replication process. Consequently, our approach relies on the use of semantic technologies to design the SARS-CoV-2 replication machinery. This provides the ability to infer new knowledge related to each step of the virus replication. More specifically, we developed an ontology-based approach enriched with reasoning process of a complete replication machinery process for SARS-CoV-2. We present in this paper a partial overview of our ontology OntoRepliCov to describe one step of this process, namely, the continuous translation or protein synthesis, through classes, properties, axioms, and SWRL (Semantic Web Rule Language) rules.

Low back pain expert systems: Clinical resolution through probabilistic considerations and poset

OBJECTIVE

Proper diagnosis of Low Back Pain (LBP) is quite challenging in especially the developing countries like India. Though some developed countries prepared guidelines for evaluation of LBP with tests to detect psychological overlay, implementation of the recommendations becomes quite difficult in regular clinical practice, and different specialties of medicine offer different modes of management. Aiming at offering an expert-level diagnosis for the patients having LBP, this paper uses Artificial Intelligence (AI) to derive a clinically justified and highly sensitive LBP resolution technique.

MATERIALS AND METHODS

The paper considers exhaustive knowledge for different LBP disorders (classified based on different pain generators), which have been represented using lattice structures to ensure completeness, non-redundancy, and optimality in the design of knowledge base. Further the representational enhancement of the knowledge has been done through construction of a hierarchical network, called RuleNet, using the concept of partially-ordered set (poset) with respect to the subset equality (⊆) relation. With implicit incorporation of probability within the knowledge, the RuleNet is used to derive reliable resolution logic along with effective resolution of uncertainties during clinical decision making.

RESULTS

The proposed methodology has been validated with clinical records of seventy seven LBP patients accessed from the database of ESI Hospital Sealdah, India over a period of one year from 2018 to 2019. Achieving 83% sensitivity of the proposed technique, the pain experts at the hospital find the design clinically satisfactory. The inferred outcomes have also been found to be homogeneous with the actual or original diagnosis.

DISCUSSIONS

The proposed approach achieves the clinical and computational efficiency by limiting the shortcomings of the existing methodologies for AI-based LBP diagnosis. While computational efficiency (with respect to both time and space complexity) is ensured by inferring clinical decisions through optimal processing of the knowledge items using poset, the clinical acceptability has been ascertained reaching to the most-likely diagnostic outcomes through probabilistic resolution of clinical uncertainties.

CONCLUSION

The derived resolution technique, when embedded in LBP medical expert systems, would provide a fast, reliable, and affordable healthcare solution for this ailment to a wider range of general population suffering from LBP. The proposed scheme would significantly reduce the controversies and confusion in LBP treatment, and cut down the cost of unnecessary or inappropriate treatment and referral.

An ontology network for Diabetes Mellitus in Mexico

Background

Medical experts in the domain of Diabetes Mellitus (DM) acquire specific knowledge from diabetic patients through monitoring and interaction. This allows them to know the disease and information about other conditions or comorbidities, treatments, and typical consequences of the Mexican population. This indicates that an expert in a domain knows technical information about the domain and contextual factors that interact with it in the real world, contributing to new knowledge generation. For capturing and managing information about the DM, it is necessary to design and implement techniques and methods that allow: determining the most relevant conceptual dimensions and their correct organization, the integration of existing medical and clinical information from different resources, and the generation of structures that represent the deduction process of the doctor. An Ontology Network is a collection of ontologies of diverse knowledge domains which can be interconnected by meta-relations. This article describes an Ontology Network for representing DM in Mexico, designed by a proposed methodology. The information used for Ontology Network building include the ontological resource reuse and non-ontological resource transformation for ontology design and ontology extending by natural language processing techniques. These are medical information extracted from vocabularies, taxonomies, medical dictionaries, ontologies, among others. Additionally, a set of semantic rules has been defined within the Ontology Network to derive new knowledge.

Results

An Ontology Network for DM in Mexico has been built from six well-defined domains, resulting in new classes, using ontological and non-ontological resources to offer a semantic structure for assisting in the medical diagnosis process. The network comprises 1367 classes, 20 object properties, 63 data properties, and 4268 individuals from seven different ontologies. Ontology Network evaluation was carried out by verifying the purpose for its design and some quality criteria.

Conclusions

The composition of the Ontology Network offers a set of well-defined ontological modules facilitating the reuse of one or more of them. The inclusion of international vocabularies as SNOMED CT or ICD-10 reinforces the representation by international standards. It increases the semantic interoperability of the network, providing the opportunity to integrate other ontologies with the same vocabularies. The ontology network design methodology offers a guide for ontology developers about how to use ontological and non-ontological resources in order to exploit the maximum of information and knowledge from a set of domains that share or not information.

Online learning environments to stimulate in students the processes of mutual interaction between digital and analog artefacts to enhance student learning

In the recent years, numerous papers have discussed the use of concept maps in education. In this paper, we use the Dynamic Concept Maps (DCMs) in online learning environments as tools able to stimulate in students the processes of mutual interaction and hybridization between digital artefacts (DCMs) and analog artefacts (books) so as to encourage the development of significant learning. This method, called “DynaMap Remediation Approach” (DMRA), encourages and stimulates learners to study topics in greater detail, and supports the development of their own learning. The advantages of this method are listed below:•

DMRA is significantly effective in terms of reducing study time and improvement of learning outcomes.

•

DMRA valorises the active role of the learners during their process of knowledge construction and may have significant implications for educators who would like to use innovative and engaging online learning environments to enhance student learning.

•

DMRA is a simple and highly reproducible method.

PINIR: a comprehensive information resource for Pin-II type protease inhibitors

BACKGROUND

Serine protease inhibitors belonging to the Potato type-II Inhibitor family Protease Inhibitors (Pin-II type PIs) are essential plant defense molecules. They are characterized by multiple inhibitory repeat domains, conserved disulfide bond pattern, and a tripeptide reactive center loop. These features of Pin-II type PIs make them potential molecules for protein engineering and designing inhibitors for agricultural and therapeutic applications. However, the diversity in these PIs remains unexplored due to the lack of annotated protein sequences and their functional attributes in the available databases.

RESULTS

We have developed a database, PINIR (Pin-II type PIs Information Resource), by systematic collection and manual annotation of 415 Pin-II type PI protein sequences. For each PI, the number and position for signature sequences are specified: 695 domains, 75 linkers, 63 reactive center loops, and 10 disulfide bond patterns are identified and mapped. Database analysis revealed novel subcategories of PIs, species-correlated occurrence of inhibitory domains, reactive center loops, and disulfide bond patterns. By analyzing linker regions, we predict that alternative processing at linker regions could generate PI variants in the Solanaceae family.

CONCLUSION

PINIR ( https://pinir.ncl.res.in ) provides a web interface for browsing and analyzing the protein sequences of Pin-II type PIs. Information about signature sequences, spatio-temporal expression, biochemical properties, gene sequences, and literature references are provided. Analysis of PINIR depicts conserved species-specific features of Pin-II type PI protein sequences. Diversity in the sequence of inhibitory domains and reactive loops directs potential applications to engineer Pin-II type PIs. The PINIR database will serve as a comprehensive information resource for further research into Pin-II type PIs.

Judgment errors in naturalistic numerical estimation

People estimate numerical quantities (such as the calories of foods) on a day-to-day basis. Although these estimates influence behavior and determine wellbeing, they are prone to two important types of errors. Scaling errors occur when people make mistakes reporting their beliefs about a particular numerical quantity (e.g. by inflating small numbers). Belief errors occur when people make mistakes using their knowledge of the judgment target to form their beliefs about the numerical quantity (e.g. by overweighting certain cues). In this paper, we quantitatively model numerical estimates, and in turn, scaling and belief errors, in everyday judgment tasks. Our approach is unique in using insights from semantic memory research to specify knowledge for naturalistic judgment targets, allowing our models to formally describe nuanced errors in belief not considered in prior research. In Studies 1 and 2, we find that belief error models predict participant estimates and errors with very high out-of-sample accuracy rates, significantly outperforming the predictions of scaling error models. In fact, the best-fitting belief error models can closely mimic the inverse-S shaped patterns captured by scaling error models, suggesting that the types of responses previously attributed to scaling errors can be seen as errors of belief. In Studies 3 to 8, we find that belief error models are also able to predict people's responses in semantic judgment, free association, and verbal protocol tasks related to numerical judgment, and thus provide a good account of the cognitive underpinnings of judgment.

STO: Stroke Ontology for Accelerating Translational Stroke Research

Introduction

Ontology-based annotation of evidence, using disease-specific ontologies, can accelerate analysis and interpretation of the knowledge domain of diseases. Although many domain-specific disease ontologies have been developed so far, in the area of cardiovascular diseases, there is a lack of ontological representation of the disease knowledge domain of stroke.

Methods

The stroke ontology (STO) was created on the basis of the ontology development life cycle and was built using Protégé ontology editor in the ontology web language format. The ontology was evaluated in terms of structural and functional features, expert evaluation, and competency questions.

Results

The stroke ontology covers a broad range of major biomedical and risk factor concepts. The majority of concepts are enriched by synonyms, definitions, and references. The ontology attempts to incorporate different users’ views on the stroke domain such as neuroscientists, molecular biologists, and clinicians. Evaluation of the ontology based on natural language processing showed a high precision (0.94), recall (0.80), and F-score (0.78) values, indicating that STO has an acceptable coverage of the stroke knowledge domain. Performance evaluation using competency questions designed by a clinician showed that the ontology can be used to answer expert questions in light of published evidence.

Conclusions

The stroke ontology is the first, multiple-view ontology in the domain of brain stroke that can be used as a tool for representation, formalization, and standardization of the heterogeneous data related to the stroke domain. Since this is a draft version of the ontology, the contribution of the stroke scientific community can help to improve the usability of the current version.

How do non-human primates represent others' awareness of where objects are hidden?

Although non-human primates (NHPs) generally appear to predict how knowledgeable agents use knowledge to guide their behavior, the cognitive mechanisms that enable this remain poorly understood. We assessed the conditions under which NHPs' representations of an agent's awareness break down. Free-ranging rhesus macaques (Macaca mulatta) watched as an agent observed a target object being hidden in one of two boxes. While the agent could no longer see the boxes, the box containing the object flipped open and the object either changed in size/shape (Experiment 1) or color (Experiment 2). Monkeys looked longer when the agent searched for the object incorrectly rather than correctly following the color change (a non-geometric manipulation), but not the size/shape change (a geometric manipulation). Even though the agent maintained knowledge of the object's location in both cases, monkeys no longer expected the agent to search correctly after it had been geometrically (but not non-geometrically) manipulated. Experiment 3 confirmed that monkeys were sensitive to the color manipulation used in Experiment 2, making it unlikely that a failure to perceive the color manipulation accounted for our findings. Our results show that NHPs do not always expect that knowledgeable agents will act on their knowledge to obtain their goals, consistent with heuristic-based accounts of how NHPs represent others' mental states. These findings also suggest that geometric changes that occur outside the agent's perceptual access may disrupt attribution of awareness more so than non-geometric changes.

Survey on graph embeddings and their applications to machine learning problems on graphs

Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs and their components, such as nodes, edges and subgraphs under preserving inner graph properties. Using the constructed feature spaces, many machine learning problems on graphs can be solved via standard frameworks suitable for vectorized feature representation. Our survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description. First, we start with the methodological approach and extract three types of graph embedding models based on matrix factorization, random-walks and deep learning approaches. Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding. Going further, we perform a thorough evaluation of graph embedding applications to machine learning problems on graphs, among which are node classification, link prediction, clustering, visualization, compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems. Finally, we overview the existing applications of graph embeddings to computer science domains, formulate open problems and provide experiment results, explaining how different networks properties result in graph embeddings quality in the four classic machine learning problems on graphs, such as node classification, link prediction, clustering and graph visualization. As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.

Knowledge representation and learning of operator clinical workflow from full-length routine fetal ultrasound scan videos

Ultrasound is a widely used imaging modality, yet it is well-known that scanning can be highly operator-dependent and difficult to perform, which limits its wider use in clinical practice. The literature on understanding what makes clinical sonography hard to learn and how sonography varies in the field is sparse, restricted to small-scale studies on the effectiveness of ultrasound training schemes, the role of ultrasound simulation in training, and the effect of introducing scanning guidelines and standards on diagnostic image quality. The Big Data era, and the recent and rapid emergence of machine learning as a more mainstream large-scale data analysis technique, presents a fresh opportunity to study sonography in the field at scale for the first time. Large-scale analysis of video recordings of full-length routine fetal ultrasound scans offers the potential to characterise differences between the scanning proficiency of experts and trainees that would be tedious and time-consuming to do manually due to the vast amounts of data. Such research would be informative to better understand operator clinical workflow when conducting ultrasound scans to support skills training, optimise scan times, and inform building better user-machine interfaces. This paper is to our knowledge the first to address sonography data science, which we consider in the context of second-trimester fetal sonography screening. Specifically, we present a fully-automatic framework to analyse operator clinical workflow solely from full-length routine second-trimester fetal ultrasound scan videos. An ultrasound video dataset containing more than 200 hours of scan recordings was generated for this study. We developed an original deep learning method to temporally segment the ultrasound video into semantically meaningful segments (the video description). The resulting semantic annotation was then used to depict operator clinical workflow (the knowledge representation). Machine learning was applied to the knowledge representation to characterise operator skills and assess operator variability. For video description, our best-performing deep spatio-temporal network shows favourable results in cross-validation (accuracy: 91.7%), statistical analysis (correlation: 0.98, p < 0.05) and retrospective manual validation (accuracy: 76.4%). For knowledge representation of operator clinical workflow, a three-level abstraction scheme consisting of a Subject-specific Timeline Model (STM), Summary of Timeline Features (STF), and an Operator Graph Model (OGM), was introduced that led to a significant decrease in dimensionality and computational complexity compared to raw video data. The workflow representations were learnt to discriminate between operator skills, where a proposed convolutional neural network-based model showed most promising performance (cross-validation accuracy: 98.5%, accuracy on unseen operators: 76.9%). These were further used to derive operator-specific scanning signatures and operator variability in terms of type, order and time distribution of constituent tasks.

Naive geography: geoconceptology and topology of geomental maps

The article presents the study of the geospace mental representations and their variability depending on the regional point of view. The research material comprises about 500 naive maps of Russia, created by informants of seven Russian regions: Moscow, St. Petersburg (capitals), Siberia (Barnaul, Biysk), Southern, Mid- and Northern Ural (Orenburg, Ufa, Perm) and Kaliningrad. A geoconcept, as a set of collective ideas about a geographic object, synthesizes images of a geographic location (topos), its name (toponym), ideas about it and its spatial parameters (length, coordinates, location relative to other geolocations). The paper raises the problem of the topology of the mental space, and describes the method and results of constructing computable metric models of geomental spaces. The use of modern means of processing and analyzing naive maps allowed to detect spatial dependencies between geoconcepts, their probable localization zones, and position relative to each other on the geomental map space. Modeling of geoconcepts was carried out on the example of the analysis of the collective regional representations associated with the capital (Moscow). Noticeable differences were found in the regional geoconcepts of Moscow, which makes it relevant to conduct research on the regional variability of the geoconcept systems of the country's common space.

Creating Synthetic Patients to Address Interoperability Issues: A Case Study with the Management of Breast Cancer Patients

Interoperability issues are common in biomedical informatics. Reusing data generated from a system in another system, or integrating an existing clinical decision support system (CDSS) in a new organization is a complex task due to recurrent problems of concept mapping and alignment. The GL-DSS of the DESIREE project is a guideline-based CDSS to support the management of breast cancer patients. The knowledge base is formalized as an ontology and decision rules. OncoDoc is another CDSS applied to breast cancer management. The knowledge base is structured as a decision tree. OncoDoc has been routinely used by the multidisciplinary tumor board physicians of the Tenon Hospital (Paris, France) for three years leading to the resolution of 1,861 exploitable decisions. Because we were lacking patient data to assess the DESIREE GL-DSS, we investigated the option of reusing OncoDoc patient data. Taking into account that we have two CDSSs with two formalisms to represent clinical practice guidelines and two knowledge representation models, we had to face semantic and structural interoperability issues. This paper reports how we created 10,681 synthetic patients to solve these issues and make OncoDoc data re-usable by the GL-DSS of DESIREE.

Learning and generalization of within-category representations in a rule-based category structure

The task requirements during the course of category learning are critical for promoting within-category representations (e.g., correlational structure of the categories). Recent data suggest that for unidimensional rule-based structures, only inference training promotes the learning of within-category representations, and generalization across tasks is limited. It is unclear if this is a general feature of rule-based structures, or a limitation of unidimensional rule-based structures. The present work reports the results of three experiments further investigating this issue using an exclusive-or rule-based structure where successful performance depends upon attending to two stimulus dimensions. Participants were trained using classification or inference and were tested using inference. For both the classification and inference training conditions, within-category representations were learned and could be generalized at test (i.e., from classification to inference) and this result was dependent upon a congruence between local and global regions of the stimulus space. These data further support the idea that the task requirements during learning (i.e., a need to attend to multiple stimulus dimensions) are critical determinants of the category representations that are learned and the utility of these representations for supporting generalization in novel situations.

Animating inter-organisational resilience communication: A participatory social network analysis of water governance in the UK

Resilience as a concept and resilience assessment as a practice are being explored across a range of social, ecological and technical systems. In this paper, we propose a new method and visualisation approach for interrogating the communication of resilience within organisational networks, using participatory social network analysis and message passing. Through an examination of the UK water sector organisational network, represented by multiple co-produced network graphs, we identify organisations having a key role in the communication of resilience regulatory and evidence messages, as well as highlighting the potential role of complexity tools in strategy formulation. Animations are presented showing the dynamics of resilience communication, which is discussed. Reflections on the use of participatory social network analysis are explored, as the method opens new doors to potentially examine how network changes could alter communication. Key insights highlight that perceived responsibilities for resilience in the UK water sector rest with a small core of organisations; water customers play a limited role in the two-way communication of resilience and water sector organisations do not communicate widely on resilience with other sectors (such as energy). Additionally, who an organisations' neighbours are and what catalyses a message to be passed are important in determining how quickly messages spread. Results lead to a recommendation that high level governmental and policy organisations should engage to a greater extent with new resilience knowledge and consider the use of complexity tools in policy making. Policy in relation to resilience is not keeping pace with such knowledge, limiting the communication and learning of organisations who ardently follow policy and regulation. For inter-organisational cooperation to make a difference to water governance, such organisations need to be encouraged to communicate and embed the latest approaches in relation to resilience and complexity thinking and practice.

The Role and Promise of Artificial Intelligence in Medical Toxicology

Artificial intelligence (AI) refers to machines or software that process information and interact with the world as understanding beings. Examples of AI in medicine include the automated reading of chest X-rays and the detection of heart dysrhythmias from wearables. A key promise of AI is its potential to apply logical reasoning at the scale of data too vast for the human mind to comprehend. This scaling up of logical reasoning may allow clinicians to bring the entire breadth of current medical knowledge to bear on each patient in real time. It may also unearth otherwise unreachable knowledge in the attempt to integrate knowledge and research across disciplines. In this review, we discuss two complementary aspects of artificial intelligence: deep learning and knowledge representation. Deep learning recognizes and predicts patterns. Knowledge representation structures and interprets those patterns or predictions. We frame this review around how deep learning and knowledge representation might expand the reach of Poison Control Centers and enhance syndromic surveillance from social media.

Systematic analysis of the scientific literature on population surveillance

Introduction

Population surveillance provides data on the health status of the population through continuous scrutiny of different indicators. Identifying risk factors is essential for the quickly detecting and controlling of epidemic outbreaks and reducing the incidence of cross-infections and non-communicable diseases. The objective of the present study is to analyze research on population surveillance, identifying the main topics of interest for investigators in the area.

Methodology

We included documents indexed in the Web of Science Core Collection in the period from 2000 to 2019 and assigned with the generic Medical Subject Heading (MeSH) “population surveillance” or its related terms (“public health surveillance,” “sentinel surveillance” or “biosurveillance”). A co-occurrence analysis was undertaken to identify the document clusters comprising the main research topics. Scientific production, collaboration, and citation patterns in each of the clusters were characterized bibliometrically. We also analyzed research on coronaviruses, relating the results obtained to the management of the COVID-19 pandemic.

Results

We included 39,184 documents, which reflected a steady growth in scientific output driven by papers on “Public, Environmental & Occupational Health” (21.62% of the documents) and “Infectious Diseases” (10.49%). Research activity was concentrated in North America (36.41%) and Europe (32.09%). The USA led research in the area (40.14% of documents). Ten topic clusters were identified, including “Disease Outbreaks,” which is closely related to two other clusters (“Genetics” and “Influenza”). Other clusters of note were “Cross Infections” as well as one that brought together general public health concepts and topics related to non-communicable diseases (cardiovascular and coronary diseases, mental diseases, diabetes, wound and injuries, stroke, and asthma). The rest of the clusters addressed “Neoplasms,” “HIV,” “Pregnancy,” “Substance Abuse/Obesity,” and “Tuberculosis.” Although research on coronavirus has focused on population surveillance only occasionally, some papers have analyzed and collated guidelines whose relevance to the dissemination and management of the COVID-19 pandemic has become obvious. Topics include tracing the spread of the virus, limiting mass gatherings that would facilitate its propagation, and the imposition of quarantines. There were important differences in the scientific production and citation of different clusters: the documents on mental illnesses, stroke, substance abuse/obesity, and cross-infections had much higher citations than the clusters on disease outbreaks, tuberculosis, and especially coronavirus, where these values are substantially lower.

Conclusions

The role of population surveillance should be strengthened, promoting research and the development of public health surveillance systems in countries whose contribution to the area is limited.

A scoping review of co-production between researchers and journalists in research communication

Co-production is rapidly gaining purchase as an approach to making research matter more to diverse audiences. There exists a wealth of information about co-production in areas such as public administration and sustainability science, but comparatively little within the specific area of research communication. In particular, little is known about the harnessing the potential of researchers and journalists engaging in co-production to generate evidence-based knowledge, foster an informed public, and achieve societal impacts. This review aimed to address that gap in the knowledge base by systematically mapping the theoretical and empirical literature related to co-production between researchers and journalists in research communication. Given the paucity of study in this area, we advanced this aim by synthesizing the extant literature that has explored the more general concept of interactions between researchers and journalists. Following a scoping review methodology, a total of 60 articles were selected for inclusion in this review. We analyzed the included articles following a systematic method of using a data extraction framework to synthesize and interpret contextual (country of the study or author [s], publication type, sector, and methods) and thematic (objectives, theoretical framework, findings) information. Three cross-cutting themes were identified that help to elucidate important considerations for researchers and journalists engaged in or considering engaging in co-production in research communication: (a) the roles of researchers and journalists; (b) the pitfalls and promises of co-production; and (c) the barriers and facilitators of co-production. Following an in-depth examination of these themes, we conclude with a synopsis of the literature along with identifying two major topics for progressing current knowledge and practice.

Medical expert system for low back pain management: design issues and conflict resolution with Bayesian network

The paper focuses on the development of a reliable medical expert system for diagnosis of low back pain (LBP) by proposing an efficient frame-based knowledge representation scheme and a suitable resolution logic with conflicts in outcomes being resolved using Bayesian network. Considering that LBP is classified into many diseases based on different pain generators, the proposed methodology infers non-conflicting LBP diseases sorted according to their chances of occurrence. A satisfactory clinical efficacy (average relative error - 0.09, recall 74.44%, precision 76.67%, accuracy 71.11%, and F1-score 73.88%) of the proposed methodology has been found after validating the design with empirically selected thirty LBP patient cases. Constraining that an inferred disease having chance of occurrence, prior to pathological investigations, below 0.75 (as set by four pain specialists) is not accepted clinically; the design can correctly identify, on average, 74.44% of actual diagnosis; and 76.67% of inferred diagnosis is included in actual diagnosis. With the predicted chance of occurrence being lower than 0.75 by a fraction of 0.09 on average, the proposed design performs well for 73.88% cases detecting 71.11% inferred outcomes as accurate. The design offers homogeneity to the actual outcomes, with the chi-squared static being calculated as 11.08 having 12 as degree of freedom. Graphical abstract.

Framing the Intractable: Comprehensive Success Factor Analysis for Grand Challenges

Complex socio-technical challenges, often referred to as grand challenges or wicked problems, lack a robust method for their holistic framing. Current approaches to framing fall into two primary categories. On one hand, models grounded in reductionist perspectives tend to oversimplify the problems and thus fall short of capturing the true complexity that must be understood to make tangible progress. On the other, notable attempts to achieve holism are more effective at incorporating contextual nuance, but still lack systematicity to identify and drive effective inclusion of critical issues, and also tend to suffer from the inherent bias of select expert input. In this article, we report on an extension of holistic problem framing techniques called comprehensive success factor analysis (CSFA) that makes-sense of web-mined information reflective of both expert and general population perspectives as well as pattern-informed ontological knowledge organization structure, to yield 'richer pictures' of grand challenges. This method has been developed and refined over a seven-year period by application to a variety of distinct socio-technical challenges, and emphasizes that framing complex problems requires one to embrace multiple levels of abstraction, a plurality of perspectives, careful contextualization, and an overarching system view. The CSFA method results in 'success factor trees' that are more comprehensive than seen otherwise and present a holistic view of the essential factors that need to be considered when engaging in large scale socio-technical problems. The success factor trees provide common grounds for meaningful collaboration and discourse on grand challenges, facilitate more informed resource allocation decisions, and provide guidance for designing solutions through careful consideration of system factors that are not always apparent. The paper illustrates CSFA applied to the challenge of 'food security for a nation in a low- to middle-income country context' to ascertain the value of the approach and finds that it results in a robust view of the challenge that greatly exceeds perspectives arrived at in the literature using current framing methods, on dimensions of scope, levels of abstraction, plurality, and context detail.

Re-written narrative: transformation of the image of Ivan-chaj in Eastern Europe

The aim of this study was to understand the role of viral narratives and the involvement of social media into the invention of tradition. We took as an example the recently highly promoted Ivan-chaj, a tea made from the fermented leaves of willowherb, a plant little known and used in Europe until a few years ago. Relying on a wide variety of sources circulating on the Internet (videos, various texts and visuals) and robust empirical field research results, we used mixed methods to analyze this specific case in order to understand if people adopt new teachings and if their acceptance leads to practical output. The results showed that the new teachings spread quickly, supported by narratives based on a wide variety of interaction points that viralized the message, also causing an economic impact. It is clear that the change of status and the economic success that Ivan-chaj now enjoys is due to the virality of the narrative, which has reshaped the image of Ivan-chaj from an "outcast" imitation and tea substitute into the national healthy drink. Having appeared in Russia, mostly as a Russian cultural marker, the narrative went viral and spread beyond its borders where neighbors have tried in turn to embrace Ivan-chaj as their own cultural marker by proclaiming it a local tradition. Indeed, narratives regarding Ivan-chaj spread easily in countries sharing some linguistic, historical and/or cultural elements with Russia (via the nexus of the Soviet Union).

Evidence-based policy making: determining what is evidence

In the era of evidence-based policy, framing and assessing the core evidence is fundamental to our ability to use research in support of public policy. In a world of almost exponentially expanding scholarly publication, it is becoming harder to define what is known. This article reviews the basic theories of knowledge, the context for sorting through and summarizing that knowledge and a number of options available, and used, to assemble the knowledge base for research and policy work. The authors undertook a summative process in the domain of biotechnology, agriculture and development and offer insights into the comparative methods and their impacts on the outcome. A population sample of 421 articles was gathered. Four methods-expert Delphi, citation analysis, social network analysis and peer evaluation-were used to select the 51 pieces for inclusion and analysis in the core literature. That analysis shows that each process delivered a different set of evidence. The potential for bias in knowledge assessment can challenge policy makers in their process of reviewing evidence that rationalizes policy.

Children's epistemic forecasting: The case of knowledge loss

Do children understand the cognitive changes that happen with development? Two experiments examined whether 4- and 6-year-olds understand that, as time passes, children forget some of the things they currently know. In Experiment 1, children were taught the names of a new person and a new object and then were informed that contact with these items will discontinue. Children were asked whether they would know the names tomorrow and as grown-ups. Both age groups demonstrated awareness that forgetting might occur. In Experiment 2, children showed a similar pattern of judgments about a peer's knowledge. The findings suggest that knowledge loss is integral to children's future thinking and is part of their understanding of the mind as a dynamically changing system.