Developing a clinical decision support system software prototype that assists in the management of patients with self-harm in the emergency department: protocol of the PERMANENS project.

BACKGROUND: Self-harm presents a significant public health challenge. Emergency departments (EDs) are crucial healthcare settings in managing self-harm, but clinician uncertainty in risk assessment may contribute to ineffective care. Clinical Decision Support Systems (CDSSs) show promise in enhancing care processes, but their effective implementation in self-harm management remains unexplored. METHODS: PERMANENS comprises a combination of methodologies and study designs aimed at developing a CDSS prototype that assists clinicians in the personalized assessment and management of ED patients presenting with self-harm. Ensemble prediction models will be constructed by applying machine learning techniques on electronic registry data from four sites, i.e., Catalonia (Spain), Ireland, Norway, and Sweden. These models will predict key adverse outcomes including self-harm repetition, suicide, premature death, and lack of post-discharge care. Available registry data include routinely collected electronic health record data, mortality data, and administrative data, and will be harmonized using the OMOP Common Data Model, ensuring consistency in terminologies, vocabularies and coding schemes. A clinical knowledge base of effective suicide prevention interventions will be developed rooted in a systematic review of clinical practice guidelines, including quality assessment of guidelines using the AGREE II tool. The CDSS software prototype will include a backend that integrates the prediction models and the clinical knowledge base to enable accurate patient risk stratification and subsequent intervention allocation. The CDSS frontend will enable personalized risk assessment and will provide tailored treatment plans, following a tiered evidence-based approach. Implementation research will ensure the CDSS' practical functionality and feasibility, and will include periodic meetings with user-advisory groups, mixed-methods research to identify currently unmet needs in self-harm risk assessment, and small-scale usability testing of the CDSS prototype software. DISCUSSION: Through the development of the proposed CDSS software prototype, PERMANENS aims to standardize care, enhance clinician confidence, improve patient satisfaction, and increase treatment compliance. The routine integration of CDSS for self-harm risk assessment within healthcare systems holds significant potential in effectively reducing suicide mortality rates by facilitating personalized and timely delivery of effective interventions on a large scale for individuals at risk of suicide.

BioLORD-2023: semantic textual representations fusing large language models and clinical knowledge graph insights.

OBJECTIVE: In this study, we investigate the potential of large language models (LLMs) to complement biomedical knowledge graphs in the training of semantic models for the biomedical and clinical domains. MATERIALS AND METHODS: Drawing on the wealth of the Unified Medical Language System knowledge graph and harnessing cutting-edge LLMs, we propose a new state-of-the-art approach for obtaining high-fidelity representations of biomedical concepts and sentences, consisting of 3 steps: an improved contrastive learning phase, a novel self-distillation phase, and a weight averaging phase. RESULTS: Through rigorous evaluations of diverse downstream tasks, we demonstrate consistent and substantial improvements over the previous state of the art for semantic textual similarity (STS), biomedical concept representation (BCR), and clinically named entity linking, across 15+ datasets. Besides our new state-of-the-art biomedical model for English, we also distill and release a multilingual model compatible with 50+ languages and finetuned on 7 European languages. DISCUSSION: Many clinical pipelines can benefit from our latest models. Our new multilingual model enables a range of languages to benefit from our advancements in biomedical semantic representation learning, opening a new avenue for bioinformatics researchers around the world. As a result, we hope to see BioLORD-2023 becoming a precious tool for future biomedical applications. CONCLUSION: In this article, we introduced BioLORD-2023, a state-of-the-art model for STS and BCR designed for the clinical domain.

What-You-See-Is-What-You-Get Computer-Interpretable Guidelines: The Case of NoviGuide Neonatal.

Complex clinical decision support (CDS) that goes beyond representing simple clinical flowcharts to supporting the totality of a care encounter may help improve care quality and consistency. However, integrating a large volume of clinical guidelines applicable to a care encounter poses unique design and safety considerations. We present the visual and technical methods employed in developing NoviGuide, a platform for complex CDS. Assuring safe functioning required transparency of all outputs, which we achieved using a JSON formalism for capturing logic. Unlike raw computer code, logic-as-data can be presented clearly in context to non-informatician reviewers. Two different styles for visualizing CDS logic, random-access and narrative, support different review contexts. We assess the fitness of these solutions for encoding hundreds of neonatal-care guidelines into integrated multi-topic CDS.

Normalization of drug and therapeutic concepts with Thera-Py.

Objective: The diversity of nomenclature and naming strategies makes therapeutic terminology difficult to manage and harmonize. As the number and complexity of available therapeutic ontologies continues to increase, the need for harmonized cross-resource mappings is becoming increasingly apparent. This study creates harmonized concept mappings that enable the linking together of like-concepts despite source-dependent differences in data structure or semantic representation. Materials and Methods: For this study, we created Thera-Py, a Python package and web API that constructs searchable concepts for drugs and therapeutic terminologies using 9 public resources and thesauri. By using a directed graph approach, Thera-Py captures commonly used aliases, trade names, annotations, and associations for any given therapeutic and combines them under a single concept record. Results: We highlight the creation of 16 069 unique merged therapeutic concepts from 9 distinct sources using Thera-Py and observe an increase in overlap of therapeutic concepts in 2 or more knowledge bases after harmonization using Thera-Py (9.8%-41.8%). Conclusion: We observe that Thera-Py tends to normalize therapeutic concepts to their underlying active ingredients (excluding nondrug therapeutics, eg, radiation therapy, biologics), and unifies all available descriptors regardless of ontological origin.

The Wolfson Prize: designing the hospital of the future.

Background: The 2021 Wolfson Economics Prize asked how new hospitals should be designed to radically improve patient experiences, clinical outcomes, staff wellbeing and integration with wider health and social care. With a major programme to rebuild and renew hospitals in England underway, the Prize offered an opportunity to understand current thinking about hospitals and their future place. Methods: The 41 submissions that were identified as 'most promising' were reviewed and subjected to framework analysis. Emerging themes were identified and discussed iteratively. Results: Five dominant themes were identified: a calming environment; systems of care; distribution of services; use of technology; and going green. Several tensions and trade-offs were evident across the submissions and a number of gaps were identified in the knowledge base that need to be remedied to ensure that new hospitals are safe and efficient. Conclusion: The previous approach to building new hospitals, with its over-riding drive to reduce costs, has not served the UK well. New ways of thinking about hospital building and design are urgently needed, especially the funding of research and the creation of a national repository devoted to design solutions and post-build evaluations of new hospitals.

A knowledge-based decision support system for inferring supportive treatment recommendations for diabetes mellitus.

BACKGROUND: Diabetes Mellitus (DM) is a significant risk, mostly causing blindness, kidney failure, heart attack, stroke, and lower limb amputation. A Clinical Decision Support System (CDSS) can assist healthcare practitioners in their daily effort and can improve the quality of healthcare provided to DM patients and save time. OBJECTIVE: In this study, a CDSS that can predict DM risk at an early stage has been developed for use by health professionals, general practitioners, hospital clinicians, health educators, and other primary care clinicians. The CDSS infers a set of personalized and suitable supportive treatment suggestions for patients. METHODS: Demographic data (e.g., age, gender, habits), body measurements (e.g., weight, height, waist circumference), comorbid conditions (e.g., autoimmune disease, heart failure), and laboratory data (e.g., IFG, IGT, OGTT, HbA1c) were collected from patients during clinical examinations and used to deduce a DM risk score and a set of personalized and suitable suggestions for the patients with the ontology reasoning ability of the tool. In this study, OWL ontology language, SWRL rule language, Java programming, Protégé ontology editor, SWRL API and OWL API tools, which are well known Semantic Web and ontology engineering tools, are used to develop the ontology reasoning module that provides to deduce a set of appropriate suggestions for a patient evaluated. RESULTS: After our first-round of tests, the consistency of the tool was obtained as 96.5%. At the end of our second-round of tests, the performance was obtained as 100.0% after some necessary rule changes and ontology revisions were done. While the developed semantic medical rules can predict only Type 1 and Type 2 DM in adults, the rules do not yet make DM risk assessments and deduce suggestions for pediatric patients. CONCLUSION: The results obtained are promising in demonstrating the applicability, effectiveness, and efficiency of the tool. It can ensure that necessary precautions are taken in advance by raising awareness of society against the DM risk.

A pipeline for the retrieval and extraction of domain-specific information with application to COVID-19 immune signatures.

BACKGROUND: The accelerating pace of biomedical publication has made it impractical to manually, systematically identify papers containing specific information and extract this information. This is especially challenging when the information itself resides beyond titles or abstracts. For emerging science, with a limited set of known papers of interest and an incomplete information model, this is of pressing concern. A timely example in retrospect is the identification of immune signatures (coherent sets of biomarkers) driving differential SARS-CoV-2 infection outcomes. IMPLEMENTATION: We built a classifier to identify papers containing domain-specific information from the document embeddings of the title and abstract. To train this classifier with limited data, we developed an iterative process leveraging pre-trained SPECTER document embeddings, SVM classifiers and web-enabled expert review to iteratively augment the training set. This training set was then used to create a classifier to identify papers containing domain-specific information. Finally, information was extracted from these papers through a semi-automated system that directly solicited the paper authors to respond via a web-based form. RESULTS: We demonstrate a classifier that retrieves papers with human COVID-19 immune signatures with a positive predictive value of 86%. The type of immune signature (e.g., gene expression vs. other types of profiling) was also identified with a positive predictive value of 74%. Semi-automated queries to the corresponding authors of these publications requesting signature information achieved a 31% response rate. CONCLUSIONS: Our results demonstrate the efficacy of using a SVM classifier with document embeddings of the title and abstract, to retrieve papers with domain-specific information, even when that information is rarely present in the abstract. Targeted author engagement based on classifier predictions offers a promising pathway to build a semi-structured representation of such information. Through this approach, partially automated literature mining can help rapidly create semi-structured knowledge repositories for automatic analysis of emerging health threats.

Mental Health Recovery in Social Psychiatric Policies: A Reflexive Thematic Analysis.

The realisation of recovery as an overarching goal of mental health care services has proven difficult to achieve in practice. At present, concepts of recovery are contested and unclear, which affects their implementation in psychiatric practices. We examined social psychiatric policies about recovery with the aim to explore their underlying assumptions about recovery. Relevant texts from the policies' knowledge bases were subjected to reflexive thematic analysis. We developed a central theme: "A clinical standardisation of the concept of recovery". The theme involved meaning clusters that encompassed conflicting and commonly shared assumptions about recovery across the text corpus. We discussed the findings from discourse analytical and governmentality perspectives. In conclusion, the policies' aim of providing clarity about recovery was circumvented by the very knowledge bases used to support their endeavours.

ELGA Terminology Server for Clinical Decision Support: A Case-Study Using an Existing Knowledge Base, CDS Hooks and FHIR.

BACKGROUND: There are many medical knowledge bases with potential for supporting medical professionals in their decision-making during routine care, yet usage of these sources remains low. Standardized linking of Clinical Decision Support (CDS) applications and existing medical knowledge bases is not a common practice. OBJECTIVES: Using existing eHealth standards to increase the utilization of knowledge bases and implement a prototype. METHODS: Linking an existing online knowledge base via a FHIR CodeSystem supplement to the Austrian national EHR (ELGA) terminology server and accessing these data using CDS Hooks and FHIR. RESULTS: We tested the approach by incorporating photosensitivity data of medications into a local copy of the Austrian terminology server. These data are directly used by a CDS Hooks compliant CDS service. CONCLUSION: The Austrian Terminology Server could be an important interface to access existing knowledge bases from within EHR systems. FHIR and CDS Hooks could lead the way for a simple and open integration of CDS services into EHR systems.

KEBLM: Knowledge-Enhanced Biomedical Language Models.

Pretrained language models (PLMs) have demonstrated strong performance on many natural language processing (NLP) tasks. Despite their great success, these PLMs are typically pretrained only on unstructured free texts without leveraging existing structured knowledge bases that are readily available for many domains, especially scientific domains. As a result, these PLMs may not achieve satisfactory performance on knowledge-intensive tasks such as biomedical NLP. Comprehending a complex biomedical document without domain-specific knowledge is challenging, even for humans. Inspired by this observation, we propose a general framework for incorporating various types of domain knowledge from multiple sources into biomedical PLMs. We encode domain knowledge using lightweight adapter modules, bottleneck feed-forward networks that are inserted into different locations of a backbone PLM. For each knowledge source of interest, we pretrain an adapter module to capture the knowledge in a self-supervised way. We design a wide range of self-supervised objectives to accommodate diverse types of knowledge, ranging from entity relations to description sentences. Once a set of pretrained adapters is available, we employ fusion layers to combine the knowledge encoded within these adapters for downstream tasks. Each fusion layer is a parameterized mixer of the available trained adapters that can identify and activate the most useful adapters for a given input. Our method diverges from prior work by including a knowledge consolidation phase, during which we teach the fusion layers to effectively combine knowledge from both the original PLM and newly-acquired external knowledge using a large collection of unannotated texts. After the consolidation phase, the complete knowledge-enhanced model can be fine-tuned for any downstream task of interest to achieve optimal performance. Extensive experiments on many biomedical NLP datasets show that our proposed framework consistently improves the performance of the underlying PLMs on various downstream tasks such as natural language inference, question answering, and entity linking. These results demonstrate the benefits of using multiple sources of external knowledge to enhance PLMs and the effectiveness of the framework for incorporating knowledge into PLMs. While primarily focused on the biomedical domain in this work, our framework is highly adaptable and can be easily applied to other domains, such as the bioenergy sector.

Functional Annotation Routines Used by ABRF Bioinformatics Core Facilities - Observations, Comparisons, and Considerations.

The functional annotation of gene lists is a common analysis routine required for most genomics experiments, and bioinformatics core facilities must support these analyses. In contrast to methods such as the quantitation of RNA-Seq reads or differential expression analysis, our research group noted a lack of consensus in our preferred approaches to functional annotation. To investigate this observation, we selected 4 experiments that represent a range of experimental designs encountered by our cores and analyzed those data with 6 tools used by members of the Association of Biomolecular Resource Facilities (ABRF) Genomic Bioinformatics Research Group (GBIRG). To facilitate comparisons between tools, we focused on a single biological result for each experiment. These results were represented by a gene set, and we analyzed these gene sets with each tool considered in our study to map the result to the annotation categories presented by each tool. In most cases, each tool produces data that would facilitate identification of the selected biological result for each experiment. For the exceptions, Fisher's exact test parameters could be adjusted to detect the result. Because Fisher's exact test is used by many functional annotation tools, we investigated input parameters and demonstrate that, while background set size is unlikely to have a significant impact on the results, the numbers of differentially expressed genes in an annotation category and the total number of differentially expressed genes under consideration are both critical parameters that may need to be modified during analyses. In addition, we note that differences in the annotation categories tested by each tool, as well as the composition of those categories, can have a significant impact on results.

Utility of public knowledge bases for the interpretation of comprehensive tumor molecular profiling results.

With the growing use of comprehensive tumor molecular profiling (CTMP), the therapeutic landscape of cancer is rapidly evolving. NGS produces large amounts of genomic data requiring complex analysis and subsequent interpretation. We sought to determine the utility of publicly available knowledge bases (KB) for the interpretation of the cancer mutational profile in clinical practice. Analysis was performed across patients who previously underwent CTMP. Independent interpretation of the CTMP was performed manually, and then, the recommendations were compared to ones present in KBs (OncoKB, CIViC, CGI, CGA, VICC, MolecularMatch). A total of 222 CTMP reports from 222 patients with 932 genomic alterations (GA) were identified. For 368 targetable GA identified in 171 (77%) of the patients, 1381 therapy recommendations were compiled. Except for CGA, therapy ESCAT LOE I, II, IIIA and IIIB therapy options were equally represented in the majority of KB. Personalized treatment options with ESCAT LOE I-II were provided for 35 patients (16%); MolecularMatch/CIViC allowed to collect ESCAT I-II treatment options for 34 of them (97%), OncoKB/CGI-for 33 of them (94%). Employing VICC and CGA 6 (17%) and 20 (57%) of patients were left without ESCAT I or II treatment options. For 88 patients with ESCAT level III-B therapy recommendations: only 2 (2%), 3 (3%), 4 (5%) and 6 (7%) of patients were left without options with CIViC, MolecularMatch, CGI and OncoKB, and with VICC-12 (14%). Highest overlap ratio was observed for IIIA (0.81) biomarkers, with the comparable results for LOE I-II. Meanwhile, overlap ratio for ESCAT LOE IV was 0.22. Public KBs provide substantial information on ESCAT-I/R1 biomarkers, but the information on ESCAT II-IV and resistance biomarkers is underrepresented. Manual curation should be considered the gold standard for the CTMP interpretation.

Toward a theorizing strategy with components of terminologies, classifications, and nursing theories.

PURPOSE: This article describes a theorizing strategy that integrates the components of classifications or terminologies with elements of grand or middle-range theories. METHODS: The source of metatheoretical data to support the strategy was the levels of theories by Dickoff et al. (1968). Terminological data sources were professional classifications and terminologies. FINDINGS: The authors synthesized data and philosophical, metatheoretical, theoretical, and terminological knowledge from primary sources on the subject to construct arguments and demonstrate suitable links. CONCLUSIONS: The proposal presented in this article of a strategy for building theories integrates theories and classifications or standardized nomenclatures. It applies levels of theorization: scrutiny of phenomena, description, conceptualization, naming, relationship, modeling, and operationalization to achieve higher levels of explanatory, predictive, and prescriptive properties on generated theory. IMPLICATIONS FOR NURSING PRACTICE: The implications for practice and research are connected to the theorizing strategy proposed in this article. We assume that using professional language at all levels of theorization can ensure that the concepts generated are closer to clinical practice.

Querying semantic catalogues of biomedical databases.

BACKGROUND: Secondary use of health data is a valuable source of knowledge that boosts observational studies, leading to important discoveries in the medical and biomedical sciences. The fundamental guiding principle for performing a successful observational study is the research question and the approach in advance of executing a study. However, in multi-centre studies, finding suitable datasets to support the study is challenging, time-consuming, and sometimes impossible without a deep understanding of each dataset. METHODS: We propose a strategy for retrieving biomedical datasets of interest that were semantically annotated, using an interface built by applying a methodology for transforming natural language questions into formal language queries. The advantages of creating biomedical semantic data are enhanced by using natural language interfaces to issue complex queries without manipulating a logical query language. RESULTS: Our methodology was validated using Alzheimer's disease datasets published in a European platform for sharing and reusing biomedical data. We converted data to semantic information format using biomedical ontologies in everyday use in the biomedical community and published it as a FAIR endpoint. We have considered natural language questions of three types: single-concept questions, questions with exclusion criteria, and multi-concept questions. Finally, we analysed the performance of the question-answering module we used and its limitations. The source code is publicly available at https://bioinformatics-ua.github.io/BioKBQA/. CONCLUSION: We propose a strategy for using information extracted from biomedical data and transformed into a semantic format using open biomedical ontologies. Our method uses natural language to formulate questions to be answered by this semantic data without the direct use of formal query languages.

Adaptación transcultural y validación del Pieper-Zulkowski Pressure Ulcer Knowledge Test (PZ-PUKT) al español / Cross-cultural adaptation and validation of the Pieper Zulkowski Pressure Ulcer Knowledge Test (PZ-PUKT) into Spanish

Objetivo: Realizar la adaptación transcultural del PZ-PUKT al español y un análisis descriptivo, bivariante y psicométrico del PZ PUKT en español. Metodología: En primer lugar, se realizó una adaptación transcultural siguiendo las etapas de la International Society for Pharmacoeconomics and Outcomes Research, estimando la validez aparente y la de contenido. Después, se realizó un estudio observacional con análisis descriptivo, bivariante y psicométrico: Rasch, fiabilidad, estabilidad y validez mediante técnica de grupos conocidos. Resultados: El PZ-PUKT en español tiene buena equivalencia semanticoconceptual con el cuestionario original, así como muy buena validez aparente y validez de contenido (x–: 0,96; R: 0,87-1). La muestra fue de 123 sanitarios, con una media de 44,2 años y 105 mujeres (85,4%). La puntuación promedio fue del 73,5%, con diferencias estadísticamente significativas entre puntuación y variables sociodemográficas. Los ítems tienen un buen ajuste del modelo de Rasch y un amplio rango de dificultad (R: –5,07-2,62). El coeficiente de correlación intraclase fue de 0,956 y la estabilidad representada con el diagrama de Bland-Altman, aceptable. El grupo de expertos puntuó mejor que el de noveles (p = 0,009). Conclusiones: El PZ-PUKT en español tiene buena validez aparente y de contenido con respecto a la versión original, mostrando unas características psicométricas apropiadas. Precisa de estudios que evalúen sus propiedades en otras muestras y la posibilidad de dividir el instrumento en 3 subescalas, pero es un instrumento válido y fiable para medir el conocimiento sobre lesiones por presión (AU)

Objective: Carry out a cross-cultural adaptation of PZ-PUKT to Spanish and a descriptive, bivariate and psychometric analysis of the Spanish PZ-PUKT. Methodology: First, a cross-cultural adaptation was carried out following the stages of the International Society for Pharmacoeconomics and Outcomes Research, estimating face and content validity. Afterwards, a observational study was carried out with descriptive, bivariate and psychometric analysis: Rasch, reliability, stability and validity using the known groups technique. Results: The Spanish PZ-PUKT has good semantic-conceptual equivalence with the original questionnaire, as well as very good face validity and content validity (x–: 0.96; R: 0.87-1). The sample consisted of 123 health workers, with a mean age of 44.2 years and 105 women (85.4%). The average score was 73.5%, with significant differences between scores and sociodemographic variables. The items have a good fit of the Rasch model and a wide range of difficulty (R: –5.07-2.62). The intraclass correlation coefficient was 0.956 and the stability represented by the Bland-Altman diagram was acceptable. The expert group scored better than the novice group (p = 0.009). Conclusions: The Spanish PZ-PUKT has good face and content validity with respect to the original version, showing appropriate psychometric characteristics. It requires studies that evaluate its properties in other samples and the possibility of dividing the instrument into 3 subscales, but it is a valid and reliable instrument to measure knowledge about pressure injuries (AU)

Sharing is caring: a call for a new era of rare disease research and development.

Scientific advances in the understanding of the genetics and mechanisms of many rare diseases with previously unknown etiologies are inspiring optimism in the patient, clinical, and research communities and there is hope that disease-specific treatments are on the way. However, the rare disease community has reached a critical point in which its increasingly fragmented structure and operating models are threatening its ability to harness the full potential of advancing genomic and computational technologies. Changes are therefore needed to overcome these issues plaguing many rare diseases while also supporting economically viable therapy development. In "Data silos are undermining drug development and failing rare disease patients (Orphanet Journal of Rare Disease, Apr 2021)," we outlined many of the broad issues underpinning the increasingly fragmented and siloed nature of the rare disease space, as well as how the issues encountered by this community are representative of biomedical research more generally. Here, we propose several initiatives for key stakeholders - including regulators, private and public foundations, and research institutions - to reorient the rare disease ecosystem and its incentives in a way that we believe would cultivate and accelerate innovation. Specifically, we propose supporting non-proprietary patient registries, greater data standardization, global regulatory harmonization, and new business models that encourage data sharing and research collaboration as the default mode. Leadership needs to be integrated across sectors to drive meaningful change between patients, industry, sponsors, and academic medical centers. To transform the research and development landscape and unlock its vast healthcare, economic, and scientific potential for rare disease patients, a new model is ultimately the goal for all.

Evaluating and Extending the Informed Consent Ontology for Representing Permissions from the Clinical Domain.

The purpose of this study was to evaluate, revise, and extend the Informed Consent Ontology (ICO) for expressing clinical permissions, including reuse of residual clinical biospecimens and health data. This study followed a formative evaluation design and used a bottom-up modeling approach. Data were collected from the literature on US federal regulations and a study of clinical consent forms. Eleven federal regulations and fifteen permission-sentences from clinical consent forms were iteratively modeled to identify entities and their relationships, followed by community reflection and negotiation based on a series of predetermined evaluation questions. ICO included fifty-two classes and twelve object properties necessary when modeling, demonstrating appropriateness of extending ICO for the clinical domain. Twenty-six additional classes were imported into ICO from other ontologies, and twelve new classes were recommended for development. This work addresses a critical gap in formally representing permissions clinical permissions, including reuse of residual clinical biospecimens and health data. It makes missing content available to the OBO Foundry, enabling use alongside other widely-adopted biomedical ontologies. ICO serves as a machine-interpretable and interoperable tool for responsible reuse of residual clinical biospecimens and health data at scale.

Development of a Knowledge Base for Chronic Wound Management Using the Decision Model & Notation.

Chronic wounds have significant impacts on patient health-related quality of life (HRQoL) and the healthcare expenditures. Various complex decision-making scenarios arise from wound management. Clinical decision-making systems (CDSS) can assist in relieving healthcare providers in these complex decision-making processes and improve the quality of care. In our study, we used the Decision Model & Notation (DMN) standard as a knowledge representation format to implement a knowledge base for chronic wound material recommendation in phase-based therapy. The resulting decision model is theoretically consistent and sustainable. With this study, we also emphasized the need of a semantic interoperability framework. This opens further research possibilities regarding the improvement of the model and the interest of DMN for decision models in clinical fields.

NILINKER: Attention-based approach to NIL Entity Linking.

The existence of unlinkable (NIL) entities is a major hurdle affecting the performance of Named Entity Linking approaches, and, consequently, the performance of downstream models that depend on them. Existing approaches to deal with NIL entities focus mainly on clustering and prediction and are limited to general entities. However, other domains, such as the biomedical sciences, are also prone to the existence of NIL entities, given the growing nature of scientific literature. We propose NILINKER, a model that includes a candidate retrieval module for biomedical NIL entities and a neural network that leverages the attention mechanism to find the top-k relevant concepts from target Knowledge Bases (MEDIC, CTD-Chemicals, ChEBI, HP, CTD-Anatomy and Gene Ontology-Biological Process) that may partially represent a given NIL entity. We also make available a new evaluation dataset designated by EvaNIL, suitable for training and evaluating models focusing on the NIL entity linking task. This dataset contains 846,165 documents (abstracts and full-text biomedical articles), including 1,071,776 annotations, distributed by six different partitions: EvaNIL-MEDIC, EvaNIL-CTD-Chemicals, EvaNIL-ChEBI, EvaNIL-HP, EvaNIL-CTD-Anatomy and EvaNIL-Gene Ontology-Biological Process. NILINKER was integrated into a graph-based Named Entity Linking model (REEL) and the results of the experiments show that this approach is able to increase the performance of the Named Entity Linking model.