eNeuro. 2022 Sep 21;9(5):ENEURO.0116-22.2022. doi: 10.1523/ENEURO.0116-22.2022. Print 2022 Sep-Oct.

ABSTRACT

To understand a dialogue, we need to know the topics that are being discussed. This enables us to integrate our knowledge of what was said previously to interpret the current dialogue. This study involved a large-scale behavioral experiment conducted online and a separate fMRI experiment, both testing human participants. In both, we selectively manipulated knowledge about the narrative content of dialogues presented in short videos. The clips were scenes from situation comedies that were split into two parts. The speech in the part 1 clips could either be presented normally or spectrally rotated to render it unintelligible. The part 2 clips that concluded the scenes were always presented normally. The behavioral experiment showed that knowledge of the preceding narrative boosted memory for the part 2 clips as well as increased the intersubject semantic similarity of recalled descriptions of the dialogues. The fMRI experiment replicated the finding that prior knowledge improved memory for the conclusions of the dialogues. Furthermore, prior knowledge strengthened temporal intersubject correlations in brain regions including the left angular gyrus and inferior frontal gyrus. Together, these findings show that (1) prior knowledge constrains the interpretation of a dialogue to be more similar across individuals; and (2), consistent with this, the activation of brain regions involved in semantic control processing is also more similar between individuals who share the same prior knowledge. Processing in these regions likely supports the activation and integration of prior knowledge, which helps people to better understand and remember dialogues as they unfold.

PMID:36096648 | PMC:PMC9491346 | DOI:10.1523/ENEURO.0116-22.2022

J Biomed Inform. 2022 Sep 8:104201. doi: 10.1016/j.jbi.2022.104201. Online ahead of print.

ABSTRACT

BACKGROUND: Knowledge graphs (KGs) play a key role to enable explainable artificial intelligence (AI) applications in healthcare. Constructing clinical knowledge graphs (CKGs) against heterogeneous electronic health records (EHRs) has been desired by the research and healthcare AI communities. From the standardization perspective, community-based standards such as the Fast Healthcare Interoperability Resources (FHIR) and the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) are increasingly used to represent and standardize EHR data for clinical data analytics, however, the potential of such a standard on building CKG has not been well investigated.

OBJECTIVE: To develop and evaluate methods and tools that expose the OMOP CDM-based clinical data repositories into virtual clinical KGs that are compliant with FHIR Resource Description Framework (RDF) specification.

METHODS: We developed a system called FHIR-Ontop-OMOP to generate virtual clinical KGs from the OMOP relational databases. We leveraged an OMOP CDM-based Medical Information Mart for Intensive Care (MIMIC-III) data repository to evaluate the FHIR-Ontop-OMOP system in terms of the faithfulness of data transformation and the conformance of the generated CKGs to the FHIR RDF specification.

RESULTS: A beta version of the system has been released. A total of more than 100 data element mappings from 11 OMOP CDM clinical data, health system and vocabulary tables were implemented in the system, covering 11 FHIR resources. The generated virtual CKG from MIMIC-III contains 46,520 instances of FHIR Patient, 716,595 instances of Condition, 1,063,525 instances of Procedure, 24,934,751 instances of MedicationStatement, 365,181,104 instances of Observations, and 4,779,672 instances of CodeableConcept. Patient counts identified by five pairs of SQL (over the MIMIC database) and SPARQL (over the virtual CKG) queries were identical, ensuring the faithfulness of the data transformation. Generated CKG in RDF triples for 100 patients were fully conformant with the FHIR RDF specification.

CONCLUSION: The FHIR-Ontop-OMOP system can expose OMOP database as a FHIR-compliant RDF graph. It provides a meaningful use case demonstrating the potentials that can be enabled by the interoperability between FHIR and OMOP CDM. Generated clinical KGs in FHIR RDF provide a semantic foundation to enable explainable AI applications in healthcare.

PMID:36089199 | DOI:10.1016/j.jbi.2022.104201

Q J Exp Psychol (Hove). 2022 Sep 3:17470218221125425. doi: 10.1177/17470218221125425. Online ahead of print.

ABSTRACT

The role of meaning facets based on sensorimotor experiences is well-investigated in comprehension but has received little attention in language production research. In two experiments, we investigated whether experiential traces of space influenced lexical choices when participants completed visually-presented sentence fragments (e.g., 'You are at the sea and you see a ...') with spoken nouns (e.g., 'dolphin', 'palm tree'). The words were presented consecutively in an ascending or descending direction, starting from the center of the screen. These physical spatial cues did not influence lexical choices. However, the produced nouns met the spatial characteristics of the broader sentence contexts such that the typical spatial locations of the produced noun referents were predicted by the location of the situations described by the sentence fragments (i.e., upper or lower sphere). By including distributional semantic similarity measures derived from computing cosine values between sentence nouns and produced nouns using a web-based text corpus, we show that the meaning dimension of 'location in space' guides lexical selection during speaking. We discuss the relation of this spatial meaning dimension to accounts of experientially grounded and usage-based theories of language processing and their combination in hybrid approaches. In doing so, we contribute to a more comprehensive understanding of the many facets of meaning processing during language production and their impact on the words we select to express verbal messages.

PMID:36062350 | DOI:10.1177/17470218221125425

Front Genet. 2022 Aug 19;13:985500. doi: 10.3389/fgene.2022.985500. eCollection 2022.

ABSTRACT

New technologies, such as next-generation sequencing, have advanced the ability to diagnose diseases and improve prognosis but require the identification of thousands of variants in each report based on several databases scattered across places. Curating an integrated interpretation database is time-consuming, costly, and needs regular update. On the other hand, the automatic curation of knowledge sources always results in overloaded information. In this study, an automated pipeline was proposed to create an integrated visual single-nucleotide polymorphism (SNP) interpretation tool called SNPMap. SNPMap pipelines periodically obtained SNP-related information from LitVar, PubTator, and GWAS Catalog API tools and presented it to the user after extraction, integration, and visualization. Keywords and their semantic relations to each SNP are rendered into two graphs, with their significance represented by the size/width of circles/lines. Moreover, the most related SNPs for each keyword that appeared in SNPMap were calculated and sorted. SNPMap retains the advantage of an automatic process while assisting users in accessing more lucid and detailed information through visualization and integration with other materials.

PMID:36061173 | PMC:PMC9437274 | DOI:10.3389/fgene.2022.985500

World Wide Web. 2022 Aug 27:1-18. doi: 10.1007/s11280-022-01013-6. Online ahead of print.

ABSTRACT

Medical reports have significant clinical value to radiologists and specialists, especially during a pandemic like COVID. However, beyond the common difficulties faced in the natural image captioning, medical report generation specifically requires the model to describe a medical image with a fine-grained and semantic-coherence paragraph that should satisfy both medical commonsense and logic. Previous works generally extract the global image features and attempt to generate a paragraph that is similar to referenced reports; however, this approach has two limitations. Firstly, the regions of primary interest to radiologists are usually located in a small area of the global image, meaning that the remainder parts of the image could be considered as irrelevant noise in the training procedure. Secondly, there are many similar sentences used in each medical report to describe the normal regions of the image, which causes serious data bias. This deviation is likely to teach models to generate these inessential sentences on a regular basis. To address these problems, we propose an Auxiliary Signal-Guided Knowledge Encoder-Decoder (ASGK) to mimic radiologists' working patterns. Specifically, the auxiliary patches are explored to expand the widely used visual patch features before fed to the Transformer encoder, while the external linguistic signals help the decoder better master prior knowledge during the pre-training process. Our approach performs well on common benchmarks, including CX-CHR, IU X-Ray, and COVID-19 CT Report dataset (COV-CTR), demonstrating combining auxiliary signals with transformer architecture can bring a significant improvement in terms of medical report generation. The experimental results confirm that auxiliary signals driven Transformer-based models are with solid capabilities to outperform previous approaches on both medical terminology classification and paragraph generation metrics.

PMID:36060430 | PMC:PMC9417931 | DOI:10.1007/s11280-022-01013-6

Front Big Data. 2022 Aug 17;5:965715. doi: 10.3389/fdata.2022.965715. eCollection 2022.

ABSTRACT

Epilepsy affects ~2-3 million individuals in the United States, a third of whom have uncontrolled seizures. Sudden unexpected death in epilepsy (SUDEP) is a catastrophic and fatal complication of poorly controlled epilepsy and is the primary cause of mortality in such patients. Despite its huge public health impact, with a ~1/1,000 incidence rate in persons with epilepsy, it is an uncommon enough phenomenon to require multi-center efforts for well-powered studies. We developed the Multimodal SUDEP Data Resource (MSDR), a comprehensive system for sharing multimodal epilepsy data in the NIH funded Center for SUDEP Research. The MSDR aims at accelerating research to address critical questions about personalized risk assessment of SUDEP. We used a metadata-guided approach, with a set of common epilepsy-specific terms enforcing uniform semantic interpretation of data elements across three main components: (1) multi-site annotated datasets; (2) user interfaces for capturing, managing, and accessing data; and (3) computational approaches for the analysis of multimodal clinical data. We incorporated the process for managing dataset-specific data use agreements, evidence of Institutional Review Board review, and the corresponding access control in the MSDR web portal. The metadata-guided approach facilitates structural and semantic interoperability, ultimately leading to enhanced data reusability and scientific rigor. MSDR prospectively integrated and curated epilepsy patient data from seven institutions, and it currently contains data on 2,739 subjects and 10,685 multimodal clinical data files with different data formats. In total, 55 users registered in the current MSDR data repository, and 6 projects have been funded to apply MSDR in epilepsy research, including three R01 projects and three R21 projects.

PMID:36059922 | PMC:PMC9428292 | DOI:10.3389/fdata.2022.965715

Plant Phenomics. 2022 May 18;2022:9893639. doi: 10.34133/2022/9893639. eCollection 2022.

ABSTRACT

The abilities of plant biologists and breeders to characterize the genetic basis of physiological traits are limited by their abilities to obtain quantitative data representing precise details of trait variation, and particularly to collect this data at a high-throughput scale with low cost. Although deep learning methods have demonstrated unprecedented potential to automate plant phenotyping, these methods commonly rely on large training sets that can be time-consuming to generate. Intelligent algorithms have therefore been proposed to enhance the productivity of these annotations and reduce human efforts. We propose a high-throughput phenotyping system which features a Graphical User Interface (GUI) and a novel interactive segmentation algorithm: Semantic-Guided Interactive Object Segmentation (SGIOS). By providing a user-friendly interface and intelligent assistance with annotation, this system offers potential to streamline and accelerate the generation of training sets, reducing the effort required by the user. Our evaluation shows that our proposed SGIOS model requires fewer user inputs compared to the state-of-art models for interactive segmentation. As a case study of the use of the GUI applied for genetic discovery in plants, we present an example of results from a preliminary genome-wide association study (GWAS) of in planta regeneration in Populus trichocarpa (poplar). We further demonstrate that the inclusion of a semantic prior map with SGIOS can accelerate the training process for future GWAS, using a sample of a dataset extracted from a poplar GWAS of in vitro regeneration. The capabilities of our phenotyping system surpass those of unassisted humans to rapidly and precisely phenotype our traits of interest. The scalability of this system enables large-scale phenomic screens that would otherwise be time-prohibitive, thereby providing increased power for GWAS, mutant screens, and other studies relying on large sample sizes to characterize the genetic basis of trait variation. Our user-friendly system can be used by researchers lacking a computational background, thus helping to democratize the use of deep segmentation as a tool for plant phenotyping.

PMID:36059601 | PMC:PMC9394117 | DOI:10.34133/2022/9893639

Comput Intell Neurosci. 2022 Aug 17;2022:5764148. doi: 10.1155/2022/5764148. eCollection 2022.

ABSTRACT

This work intends to classify and integrate music genres and emotions to improve the quality of music education. This work proposes a web image education resource retrieval method based on semantic network and interactive image filtering for a music education environment. It makes a judgment on these music source data and then uses these extracted feature sequences as the emotions expressed in the model of the combination of Long Short-Term Memory (LSTM) and Attention Mechanism (AM), thus judging the emotion category of music. The emotion recognition accuracy has increased after improving LSTM-AM into the BiGR-AM model. The greater the difference between emotion genres is, the easier it is to analyze the feature sequence containing emotion features, and the higher the recognition accuracy is. The classification accuracy of the excited, relieved, relaxed, and sad emotions can reach 76.5%, 71.3%, 80.8%, and 73.4%, respectively. The proposed interactive filtering method based on a Convolutional Recurrent Neural Network can effectively classify and integrate music resources to improve the quality of music education.

PMID:36035856 | PMC:PMC9402344 | DOI:10.1155/2022/5764148

Front Plant Sci. 2022 Aug 11;13:972286. doi: 10.3389/fpls.2022.972286. eCollection 2022.

ABSTRACT

Accurate and timely surveys of rice diseases and pests are important to control them and prevent the reduction of rice yields. The current manual survey method of rice diseases and pests is time-consuming, laborious, highly subjective and difficult to trace historical data. To address these issues, we developed an intelligent monitoring system for detecting and identifying the disease and pest lesions on the rice canopy. The system mainly includes a network camera, an intelligent detection model of diseases and pests on rice canopy, a web client and a server. Each camera of the system can collect rice images in about 310 m2 of paddy fields. An improved model YOLO-Diseases and Pests Detection (YOLO-DPD) was proposed to detect three lesions of Cnaphalocrocis medinalis, Chilo suppressalis, and Ustilaginoidea virens on rice canopy. The residual feature augmentation method was used to narrow the semantic gap between different scale features of rice disease and pest images. The convolution block attention module was added into the backbone network to enhance the regional disease and pest features for suppressing the background noises. Our experiments demonstrated that the improved model YOLO-DPD could detect three species of disease and pest lesions on rice canopy at different image scales with an average precision of 92.24, 87.35 and 90.74%, respectively, and a mean average precision of 90.11%. Compared to RetinaNet, Faster R-CNN and Yolov4 models, the mean average precision of YOLO-DPD increased by 18.20, 6.98, 6.10%, respectively. The average detection time of each image is 47 ms. Our system has the advantages of unattended operation, high detection precision, objective results, and data traceability.

PMID:36035691 | PMC:PMC9403268 | DOI:10.3389/fpls.2022.972286

Comput Math Methods Med. 2022 Aug 17;2022:9093262. doi: 10.1155/2022/9093262. eCollection 2022.

ABSTRACT

As more drugs are developed and the incidence of polypharmacy increases, it is becoming critically important to anticipate potential DDIs before they occur in the clinic, along with those for which effects might go unobserved. However, traditional methods for DDI identification are unable to coalesce interaction mechanisms out of vast lists of potential or known DDIs, much less study them accurately. Computational methods have great promise but have realized only limited clinical utility. This work develops a rule-based inference framework to predict DDI mechanisms and support determination of their clinical relevance. Given a drug pair, our framework interrogates and describes DDI mechanisms based on a knowledge graph that integrates extensive available biomedical resources through semantic web technologies and backward chaining inference, effectively identifying facts within the graph that prove and explain the mechanisms of the drugs' interaction. The framework was evaluated through a case study combining a chemotherapy agent, irinotecan, and a widely used antibiotic, levofloxacin. The mutual interactions identified indicate that our framework can effectively explore and explain the mechanisms of potential DDIs. This approach has the potential to improve drug discovery and design and to support rapid and cost-effective identification of DDIs along with their putative mechanisms, a key step in determining clinical relevance and supporting clinical decision-making.

PMID:36035294 | PMC:PMC9402322 | DOI:10.1155/2022/9093262

Math Biosci Eng. 2022 Jul 25;19(10):10445-10473. doi: 10.3934/mbe.2022489.

ABSTRACT

In clinical decision support, argumentation plays a key role while alternative reasons may be available to explain a given set of signs and symptoms, or alternative plans to treat a diagnosed disease. In literature, this key notion usually has closed boundary across approaches and lacks of openness and interoperability in Clinical Decision Support Systems (CDSSs) been built. In this paper, we propose a systematic approach for the representation of argumentation, their interpretation towards recommendation, and finally explanation in clinical decision support. A generic argumentation and recommendation scheme lays the foundation of the approach. On the basis of this, argumentation rules are represented using Resource Description Framework (RDF) for clinical guidelines, a rule engine developed for their interpretation, and recommendation rules represented using Semantic Web Rule Language (SWRL). A pair of proof knowledge graphs are made available in an integrated clinical decision environment to explain the argumentation and recommendation rationale, so that decision makers are informed of not just what are recommended but also why. A case study of triple assessment, a common procedure in the National Health Service of UK for women suspected of breast cancer, is used to demonstrate the feasibility of the approach. In conducting hypothesis testing, we evaluate the metrics of accuracy, variation, adherence, time, satisfaction, confidence, learning, and integration of the prototype CDSS developed for the case study in comparison with a conventional CDSS and also human clinicians without CDSS. The results are presented and discussed.

PMID:36032002 | DOI:10.3934/mbe.2022489

Int J Environ Res Public Health. 2022 Aug 4;19(15):9611. doi: 10.3390/ijerph19159611.

ABSTRACT

Exposure to green spaces contributes to residents' physical and mental health and well-being. The equitable allocation of green space has also become an increasingly important issue for society and the government. This study takes 3281 communities in Shenzhen as the analysis units. Using web crawlers, semantic segmentation based on deep learning, web map path planning and entropy weighting methods, four types of residents' daily green exposure indicators are calculated, including community green space ratio, green view index (GVI), park accessibility, and the weighted composite green exposure index. The results reveal inequalities in the level of green exposure in Shenzhen's communities across economic classes, mainly in GVI and comprehensive green exposure. We also found that the level of composite green exposure is relatively stable; however, green space ratio attainment levels for newer communities are increasing and GVI and park accessibility attainment levels are decreasing. Finally, among the newly built communities: compared to the low-income level communities, the high-income level communities have a significant advantage in green space, but the mid-income level communities do not have such an advantage. The main findings of this study can provide policy implications for urban green space planning, including the need to prioritize the addition of public green space near older communities with poor levels of green exposure, the addition of street greenery near communities with poor levels of composite green exposure, and ensuring that parks have entrances in all four directions as far as possible.

PMID:35954967 | DOI:10.3390/ijerph19159611

Brain Lang. 2022 Oct;233:105164. doi: 10.1016/j.bandl.2022.105164. Epub 2022 Aug 4.

ABSTRACT

People with aphasia often show partial impairments on a given task. This trial-to-trial variability offers a potential window into understanding how damaged language networks function. We test the hypothesis that successful word reading in participants with phonological system damage reflects semantic system recruitment. Residual semantic and phonological networks were defined with fMRI in 21 stroke participants with phonological damage using semantic- and rhyme-matching tasks. Participants performed an oral word reading task, and activation was compared between correct and incorrect trials within the semantic and phonological networks. The results showed a significant interaction between hemisphere, network activation, and reading success. Activation in the left hemisphere semantic network was higher when participants successfully read words. Residual phonological regions showed no difference in activation between correct and incorrect trials on the word reading task. The results provide evidence that semantic processing supports successful phonological retrieval in participants with phonological impairment.

PMID:35933744 | DOI:10.1016/j.bandl.2022.105164

J Med Internet Res. 2022 Aug 5;24(8):e39888. doi: 10.2196/39888.

ABSTRACT

BACKGROUND: Understanding how individuals think about a topic, known as the mental model, can significantly improve communication, especially in the medical domain where emotions and implications are high. Neurodevelopmental disorders (NDDs) represent a group of diagnoses, affecting up to 18% of the global population, involving differences in the development of cognitive or social functions. In this study, we focus on 2 NDDs, attention deficit hyperactivity disorder (ADHD) and autism spectrum disorder (ASD), which involve multiple symptoms and interventions requiring interactions between 2 important stakeholders: parents and health professionals. There is a gap in our understanding of differences between mental models for each stakeholder, making communication between stakeholders more difficult than it could be.

OBJECTIVE: We aim to build knowledge graphs (KGs) from web-based information relevant to each stakeholder as proxies of mental models. These KGs will accelerate the identification of shared and divergent concerns between stakeholders. The developed KGs can help improve knowledge mobilization, communication, and care for individuals with ADHD and ASD.

METHODS: We created 2 data sets by collecting the posts from web-based forums and PubMed abstracts related to ADHD and ASD. We utilized the Unified Medical Language System (UMLS) to detect biomedical concepts and applied Positive Pointwise Mutual Information followed by truncated Singular Value Decomposition to obtain corpus-based concept embeddings for each data set. Each data set is represented as a KG using a property graph model. Semantic relatedness between concepts is calculated to rank the relation strength of concepts and stored in the KG as relation weights. UMLS disorder-relevant semantic types are used to provide additional categorical information about each concept's domain.

RESULTS: The developed KGs contain concepts from both data sets, with node sizes representing the co-occurrence frequency of concepts and edge sizes representing relevance between concepts. ADHD- and ASD-related concepts from different semantic types shows diverse areas of concerns and complex needs of the conditions. KG identifies converging and diverging concepts between health professionals literature (PubMed) and parental concerns (web-based forums), which may correspond to the differences between mental models for each stakeholder.

CONCLUSIONS: We show for the first time that generating KGs from web-based data can capture the complex needs of families dealing with ADHD or ASD. Moreover, we showed points of convergence between families and health professionals' KGs. Natural language processing-based KG provides access to a large sample size, which is often a limiting factor for traditional in-person mental model mapping. Our work offers a high throughput access to mental model maps, which could be used for further in-person validation, knowledge mobilization projects, and basis for communication about potential blind spots from stakeholders in interactions about NDDs. Future research will be needed to identify how concepts could interact together differently for each stakeholder.

PMID:35930346 | DOI:10.2196/39888

Obstet Gynecol. 2022 Sep 1;140(3):450-452. doi: 10.1097/AOG.0000000000004902. Epub 2022 Aug 3.

ABSTRACT

Most studies of severe maternal morbidity (SMM) include only cases that occur during birth hospitalizations. We examined the increase in cases when including SMM during antenatal and postpartum (within 42 days of discharge) hospitalizations, using longitudinally linked data from 1,010,250 births in California from September 1, 2016, to December 31, 2018. For total SMM, expanding the definition resulted in 22.8% more cases; for nontransfusion SMM, 45.1% more cases were added. Sepsis accounted for 55.5% of the additional cases. The increase varied for specific indicators, for example, less than 2% for amniotic fluid embolism, 7.0% for transfusion, 112.9% for sepsis, and 155.6% for acute myocardial infarction. These findings reiterate the importance of considering SMM beyond just the birth hospitalization and facilitating access to longitudinally linked data to facilitate a more complete understanding of SMM.

PMID:35926198 | DOI:10.1097/AOG.0000000000004902

Brain Struct Funct. 2022 Sep;227(7):2513-2527. doi: 10.1007/s00429-022-02544-4. Epub 2022 Aug 4.

ABSTRACT

Language function in the brain, once thought to be highly localized, is now appreciated as relying on a connected but distributed network. The semantic system is of particular interest in the language domain because of its hypothesized integration of information across multiple cortical regions. Previous work in healthy individuals has focused on group-level functional connectivity (FC) analyses of the semantic system, which may obscure interindividual differences driving variance in performance. These studies also overlook the contributions of white matter networks to semantic function. Here, we identified semantic network nodes at the individual level with a semantic decision fMRI task in 53 typically aging adults, characterized network organization using structural connectivity (SC), and quantified the segregation and integration of the network using FC. Hub regions were identified in left inferior frontal gyrus. The individualized semantic network was composed of three interacting modules: (1) default-mode module characterized by bilateral medial prefrontal and posterior cingulate regions and also including right-hemisphere homotopes of language regions; (2) left frontal module extending dorsally from inferior frontal gyrus to pre-motor area; and (3) left temporoparietal module extending from temporal pole to inferior parietal lobule. FC within Module3 and integration of the entire network related to a semantic verbal fluency task, but not a matched phonological task. These results support and extend the tri-network semantic model (Xu in Front Psychol 8: 1538 1538, 2017) and the controlled semantic cognition model (Chiou in Cortex 103: 100 116, 2018) of semantic function.

PMID:35925418 | DOI:10.1007/s00429-022-02544-4

J Intell Inf Syst. 2022 Jul 29:1-26. doi: 10.1007/s10844-022-00731-7. Online ahead of print.

ABSTRACT

Complex system development and maintenance face the challenge of dealing with different types of models due to language affordances, preferences, sizes, and so forth that involve interaction between users with different levels of proficiency. Current conceptual data modelling tools do not fully support these modes of working. It requires that the interaction between multiple models in multiple languages is clearly specified to ensure they keep their intended semantics, which is lacking in extant tools. The key objective is to devise a mechanism to support semantic interoperability in hybrid tools for multi-modal modelling in a plurality of paradigms, all within one system. We propose FaCIL, a framework for such hybrid modelling tools. We design and realise the framework FaCIL, which maps UML, ER and ORM2 into a common metamodel with rules that provide the central point for management among the models and that links to the formalisation and logic-based automated reasoning. FaCIL supports the ability to represent models in different formats while preserving their semantics, and several editing workflows are supported within the framework. It has a clear separation of concerns for typical conceptual modelling activities in an interoperable and extensible way. FaCIL structures and facilitates the interaction between visual and textual conceptual models, their formal specifications, and abstractions as well as tracking and propagating updates across all the representations. FaCIL is compared against the requirements, implemented in crowd 2.0, and assessed with a use case. The proof-of-concept implementation in the web-based modelling tool crowd 2.0 demonstrates its viability. The framework also meets the requirements and fully supports the use case.

PMID:35919102 | PMC:PMC9334976 | DOI:10.1007/s10844-022-00731-7

Zh Nevrol Psikhiatr Im S S Korsakova. 2022;122(7. Vyp. 2):78-83. doi: 10.17116/jnevro202212207278.

ABSTRACT

OBJECTIVE: To study the needs of patients suffering from multiple sclerosis (MS) in Russia.

MATERIAL AND METHODS: The technologies of Big Data analysis and intelligent processing of unstructured information (semantic analysis of natural language texts), developed by Semantic Hub were used. Semantic Hub platform scans digital environment to connect to the sources of interest and to collect data of potential interest (i.e. texts generated by patients and their caregivers, in anonymized form). As the next step, each text is analyzed using natural language understanding technologies to build the knowledge base with aggregated data.

RESULTS: The semantic analysis of natural language texts made it possible to describe virtual population of Russian patients with MS and their caregivers on the Web: age, gender, regions of residence, movements, key Web resources for getting information and communicating with each other, insights about medical care and the quality of life of patients with MS.

CONCLUSIONS: In addition to doctors' recommendations, today the patient can get information from various sources, including other patients with MS. This trend requires attention of medical community: it is necessary to help patients get reliable information about the disease, and methods of therapy. Doctor-to-patient communication on the Web should be widely discussed to develop effective and ethical approaches.

PMID:35912561 | DOI:10.17116/jnevro202212207278

Australas Emerg Care. 2023 Mar;26(1):13-23. doi: 10.1016/j.auec.2022.07.002. Epub 2022 Jul 29.

ABSTRACT

INTRODUCTION: Acute appendicitis is the most common cause of acute abdominal pain presentations to the ED and common air ambulance transfer.

AIMS: describe how linked data can be used to explore patients' journeys, referral pathways and request-to-activation responsiveness of patients' appendectomy outcomes (minor vs major complexity).

METHODS: Data sources were linked: aeromedical, hospital and death. Request-to-activation intervals showed strong right-tailed skewness. Quantile regression examined whether the longest request-to-activation intervals were associated with appendicitis complexity in patients who underwent an appendectomy.

RESULTS: There were 684 patients in three referral pathways based on hospital capability levels. In total, 5.6 % patients were discharged from ED. 83.3 % of all rural origins entered via the ED. 3.8 % of appendicitis patients were triaged to tertiary hospitals. Appendectomy patients with major complexity outcomes were less likely to have longer request-to-activation wait times & had longer lengths of stay than patients with minor complexity outcomes.

CONCLUSIONS: Linked data highlighted four aspects of a functioning referral system: appendectomy outcomes of major complexity were less likely to have longer request-to-activation intervals compared to minor (sicker patients were identified); few were discharged from EDs (validated transfer); few were triaged to tertiary hospitals (appropriate level for need), and no deaths relating to appendectomy.

PMID:35909043 | DOI:10.1016/j.auec.2022.07.002

Sensors (Basel). 2022 Jul 23;22(15):5509. doi: 10.3390/s22155509.

ABSTRACT

Humor is a special human expression style, an important "lubricant" for daily communication for people; people can convey emotional messages that are not easily expressed through humor. At present, artificial intelligence is one of the popular research domains; "discourse understanding" is also an important research direction, and how to make computers recognize and understand humorous expressions similar to humans has become one of the popular research domains for natural language processing researchers. In this paper, a humor recognition model (MLSN) based on current humor theory and popular deep learning techniques is proposed for the humor recognition task. The model automatically identifies whether a sentence contains humor expression by capturing the inconsistency, phonetic features, and ambiguity of a joke as semantic features. The model was experimented on three publicly available wisecrack datasets and compared with state-of-the-art language models, and the results demonstrate that the proposed model has better humor recognition accuracy and can contribute to the research on discourse understanding.

PMID:35898012 | DOI:10.3390/s22155509