Journal Of Biomedical Semantics[JOURNAL]
Sun
200 papers
An extensible and unifying approach to retrospective clinical data modeling: the BrainTeaser Ontology.
Faggioli G, Menotti L, Marchesin S … +9 more , Chió A, Dagliati A, de Carvalho M, Gromicho M, Manera U, Tavazzi E, Di Nunzio GM, Silvello G, Ferro N
J Biomed Semantics · 2024 Aug · PMID 39210467 · Full text
Automatic disease progression prediction models require large amounts of training data, which are seldom available, especially when it comes to rare diseases. A possible solution is to integrate data from different medic...
Automatic disease progression prediction models require large amounts of training data, which are seldom available, especially when it comes to rare diseases. A possible solution is to integrate data from different medical centres. Nevertheless, various centres often follow diverse data collection procedures and assign different semantics to collected data. Ontologies, used as schemas for interoperable knowledge bases, represent a state-of-the-art solution to homologate the semantics and foster data integration from various sources. This work presents the BrainTeaser Ontology (BTO), an ontology that models the clinical data associated with two brain-related rare diseases (ALS and MS) in a comprehensive and modular manner. BTO assists in organizing and standardizing the data collected during patient follow-up. It was created by harmonizing schemas currently used by multiple medical centers into a common ontology, following a bottom-up approach. As a result, BTO effectively addresses the practical data collection needs of various real-world situations and promotes data portability and interoperability. BTO captures various clinical occurrences, such as disease onset, symptoms, diagnostic and therapeutic procedures, and relapses, using an event-based approach. Developed in collaboration with medical partners and domain experts, BTO offers a holistic view of ALS and MS for supporting the representation of retrospective and prospective data. Furthermore, BTO adheres to Open Science and FAIR (Findable, Accessible, Interoperable, and Reusable) principles, making it a reliable framework for developing predictive tools to aid in medical decision-making and patient care. Although BTO is designed for ALS and MS, its modular structure makes it easily extendable to other brain-related diseases, showcasing its potential for broader applicability.Database URL https://zenodo.org/records/7886998 .
Concretizing plan specifications as realizables within the OBO foundry.
Duncan WD, Diller M, Dooley D … +2 more , Hogan WR, Beverley J
J Biomed Semantics · 2024 Aug · PMID 39160586 · Full text
BACKGROUND: Within the Open Biological and Biomedical Ontology (OBO) Foundry, many ontologies represent the execution of a plan specification as a process in which a realizable entity that concretizes the plan specificat...
BACKGROUND: Within the Open Biological and Biomedical Ontology (OBO) Foundry, many ontologies represent the execution of a plan specification as a process in which a realizable entity that concretizes the plan specification, a "realizable concretization" (RC), is realized. This representation, which we call the "RC-account", provides a straightforward way to relate a plan specification to the entity that bears the realizable concretization and the process that realizes the realizable concretization. However, the adequacy of the RC-account has not been evaluated in the scientific literature. In this manuscript, we provide this evaluation and, thereby, give ontology developers sound reasons to use or not use the RC-account pattern. RESULTS: Analysis of the RC-account reveals that it is not adequate for representing failed plans. If the realizable concretization is flawed in some way, it is unclear what (if any) relation holds between the realizable entity and the plan specification. If the execution (i.e., realization) of the realizable concretization fails to carry out the actions given in the plan specification, it is unclear under the RC-account how to directly relate the failed execution to the entity carrying out the instructions given in the plan specification. These issues are exacerbated in the presence of changing plans. CONCLUSIONS: We propose two solutions for representing failed plans. The first uses the Common Core Ontologies 'prescribed by' relation to connect a plan specification to the entity or process that utilizes the plan specification as a guide. The second, more complex, solution incorporates the process of creating a plan (in the sense of an intention to execute a plan specification) into the representation of executing plan specifications. We hypothesize that the first solution (i.e., use of 'prescribed by') is adequate for most situations. However, more research is needed to test this hypothesis as well as explore the other solutions presented in this manuscript.
Mapping vaccine names in clinical trials to vaccine ontology using cascaded fine-tuned domain-specific language models.
Li J, Li Y, Pan Y … +5 more , Guo J, Sun Z, Li F, He Y, Tao C
J Biomed Semantics · 2024 Aug · PMID 39123237 · Full text
BACKGROUND: Vaccines have revolutionized public health by providing protection against infectious diseases. They stimulate the immune system and generate memory cells to defend against targeted diseases. Clinical trials...
BACKGROUND: Vaccines have revolutionized public health by providing protection against infectious diseases. They stimulate the immune system and generate memory cells to defend against targeted diseases. Clinical trials evaluate vaccine performance, including dosage, administration routes, and potential side effects. CLINICALTRIALS: gov is a valuable repository of clinical trial information, but the vaccine data in them lacks standardization, leading to challenges in automatic concept mapping, vaccine-related knowledge development, evidence-based decision-making, and vaccine surveillance. RESULTS: In this study, we developed a cascaded framework that capitalized on multiple domain knowledge sources, including clinical trials, the Unified Medical Language System (UMLS), and the Vaccine Ontology (VO), to enhance the performance of domain-specific language models for automated mapping of VO from clinical trials. The Vaccine Ontology (VO) is a community-based ontology that was developed to promote vaccine data standardization, integration, and computer-assisted reasoning. Our methodology involved extracting and annotating data from various sources. We then performed pre-training on the PubMedBERT model, leading to the development of CTPubMedBERT. Subsequently, we enhanced CTPubMedBERT by incorporating SAPBERT, which was pretrained using the UMLS, resulting in CTPubMedBERT + SAPBERT. Further refinement was accomplished through fine-tuning using the Vaccine Ontology corpus and vaccine data from clinical trials, yielding the CTPubMedBERT + SAPBERT + VO model. Finally, we utilized a collection of pre-trained models, along with the weighted rule-based ensemble approach, to normalize the vaccine corpus and improve the accuracy of the process. The ranking process in concept normalization involves prioritizing and ordering potential concepts to identify the most suitable match for a given context. We conducted a ranking of the Top 10 concepts, and our experimental results demonstrate that our proposed cascaded framework consistently outperformed existing effective baselines on vaccine mapping, achieving 71.8% on top 1 candidate's accuracy and 90.0% on top 10 candidate's accuracy. CONCLUSION: This study provides a detailed insight into a cascaded framework of fine-tuned domain-specific language models improving mapping of VO from clinical trials. By effectively leveraging domain-specific information and applying weighted rule-based ensembles of different pre-trained BERT models, our framework can significantly enhance the mapping of VO from clinical trials.
Chemical entity normalization for successful translational development of Alzheimer's disease and dementia therapeutics.
Mullin S, McDougal R, Cheung KH … +3 more , Kilicoglu H, Beck A, Zeiss CJ
J Biomed Semantics · 2024 Jul · PMID 39080729 · Full text
BACKGROUND: Identifying chemical mentions within the Alzheimer's and dementia literature can provide a powerful tool to further therapeutic research. Leveraging the Chemical Entities of Biological Interest (ChEBI) ontolo...
BACKGROUND: Identifying chemical mentions within the Alzheimer's and dementia literature can provide a powerful tool to further therapeutic research. Leveraging the Chemical Entities of Biological Interest (ChEBI) ontology, which is rich in hierarchical and other relationship types, for entity normalization can provide an advantage for future downstream applications. We provide a reproducible hybrid approach that combines an ontology-enhanced PubMedBERT model for disambiguation with a dictionary-based method for candidate selection. RESULTS: There were 56,553 chemical mentions in the titles of 44,812 unique PubMed article abstracts. Based on our gold standard, our method of disambiguation improved entity normalization by 25.3 percentage points compared to using only the dictionary-based approach with fuzzy-string matching for disambiguation. For the CRAFT corpus, our method outperformed baselines (maximum 78.4%) with a 91.17% accuracy. For our Alzheimer's and dementia cohort, we were able to add 47.1% more potential mappings between MeSH and ChEBI when compared to BioPortal. CONCLUSION: Use of natural language models like PubMedBERT and resources such as ChEBI and PubChem provide a beneficial way to link entity mentions to ontology terms, while further supporting downstream tasks like filtering ChEBI mentions based on roles and assertions to find beneficial therapies for Alzheimer's and dementia.
Empowering standardization of cancer vaccines through ontology: enhanced modeling and data analysis.
Zheng J, Li X, Masci AM … +10 more , Kahn H, Huffman A, Asfaw E, Pan Y, Guo J, He V, Song J, Seleznev AI, Lin AY, He Y
J Biomed Semantics · 2024 Jun · PMID 38890666 · Full text
BACKGROUND: The exploration of cancer vaccines has yielded a multitude of studies, resulting in a diverse collection of information. The heterogeneity of cancer vaccine data significantly impedes effective integration an...
BACKGROUND: The exploration of cancer vaccines has yielded a multitude of studies, resulting in a diverse collection of information. The heterogeneity of cancer vaccine data significantly impedes effective integration and analysis. While CanVaxKB serves as a pioneering database for over 670 manually annotated cancer vaccines, it is important to distinguish that a database, on its own, does not offer the structured relationships and standardized definitions found in an ontology. Recognizing this, we expanded the Vaccine Ontology (VO) to include those cancer vaccines present in CanVaxKB that were not initially covered, enhancing VO's capacity to systematically define and interrelate cancer vaccines. RESULTS: An ontology design pattern (ODP) was first developed and applied to semantically represent various cancer vaccines, capturing their associated entities and relations. By applying the ODP, we generated a cancer vaccine template in a tabular format and converted it into the RDF/OWL format for generation of cancer vaccine terms in the VO. '12MP vaccine' was used as an example of cancer vaccines to demonstrate the application of the ODP. VO also reuses reference ontology terms to represent entities such as cancer diseases and vaccine hosts. Description Logic (DL) and SPARQL query scripts were developed and used to query for cancer vaccines based on different vaccine's features and to demonstrate the versatility of the VO representation. Additionally, ontological modeling was applied to illustrate cancer vaccine related concepts and studies for in-depth cancer vaccine analysis. A cancer vaccine-specific VO view, referred to as "CVO," was generated, and it contains 928 classes including 704 cancer vaccines. The CVO OWL file is publicly available on: http://purl.obolibrary.org/obo/vo/cvo.owl , for sharing and applications. CONCLUSION: To facilitate the standardization, integration, and analysis of cancer vaccine data, we expanded the Vaccine Ontology (VO) to systematically model and represent cancer vaccines. We also developed a pipeline to automate the inclusion of cancer vaccines and associated terms in the VO. This not only enriches the data's standardization and integration, but also leverages ontological modeling to deepen the analysis of cancer vaccine information, maximizing benefits for researchers and clinicians. AVAILABILITY: The VO-cancer GitHub website is: https://github.com/vaccineontology/VO/tree/master/CVO .
Multi-task transfer learning for the prediction of entity modifiers in clinical text: application to opioid use disorder case detection.
Almudaifer AI, Covington W, Hairston J … +9 more , Deitch Z, Anand A, Carroll CM, Crisan E, Bradford W, Walter LA, Eaton EF, Feldman SS, Osborne JD
J Biomed Semantics · 2024 Jun · PMID 38849884 · Full text
BACKGROUND: The semantics of entities extracted from a clinical text can be dramatically altered by modifiers, including entity negation, uncertainty, conditionality, severity, and subject. Existing models for determinin...
BACKGROUND: The semantics of entities extracted from a clinical text can be dramatically altered by modifiers, including entity negation, uncertainty, conditionality, severity, and subject. Existing models for determining modifiers of clinical entities involve regular expression or features weights that are trained independently for each modifier. METHODS: We develop and evaluate a multi-task transformer architecture design where modifiers are learned and predicted jointly using the publicly available SemEval 2015 Task 14 corpus and a new Opioid Use Disorder (OUD) data set that contains modifiers shared with SemEval as well as novel modifiers specific for OUD. We evaluate the effectiveness of our multi-task learning approach versus previously published systems and assess the feasibility of transfer learning for clinical entity modifiers when only a portion of clinical modifiers are shared. RESULTS: Our approach achieved state-of-the-art results on the ShARe corpus from SemEval 2015 Task 14, showing an increase of 1.1% on weighted accuracy, 1.7% on unweighted accuracy, and 10% on micro F1 scores. CONCLUSIONS: We show that learned weights from our shared model can be effectively transferred to a new partially matched data set, validating the use of transfer learning for clinical text modifiers.
Optimized continuous homecare provisioning through distributed data-driven semantic services and cross-organizational workflows.
De Brouwer M, Bonte P, Arndt D … +5 more , Vander Sande M, Dimou A, Verborgh R, De Turck F, Ongenae F
J Biomed Semantics · 2024 Jun · PMID 38845042 · Full text
BACKGROUND: In healthcare, an increasing collaboration can be noticed between different caregivers, especially considering the shift to homecare. To provide optimal patient care, efficient coordination of data and workfl...
BACKGROUND: In healthcare, an increasing collaboration can be noticed between different caregivers, especially considering the shift to homecare. To provide optimal patient care, efficient coordination of data and workflows between these different stakeholders is required. To achieve this, data should be exposed in a machine-interpretable, reusable manner. In addition, there is a need for smart, dynamic, personalized and performant services provided on top of this data. Flexible workflows should be defined that realize their desired functionality, adhere to use case specific quality constraints and improve coordination across stakeholders. User interfaces should allow configuring all of this in an easy, user-friendly way. METHODS: A distributed, generic, cascading reasoning reference architecture can solve the presented challenges. It can be instantiated with existing tools built upon Semantic Web technologies that provide data-driven semantic services and constructing cross-organizational workflows. These tools include RMLStreamer to generate Linked Data, DIVIDE to adaptively manage contextually relevant local queries, Streaming MASSIF to deploy reusable services, AMADEUS to compose semantic workflows, and RMLEditor and Matey to configure rules to generate Linked Data. RESULTS: A use case demonstrator is built on a scenario that focuses on personalized smart monitoring and cross-organizational treatment planning. The performance and usability of the demonstrator's implementation is evaluated. The former shows that the monitoring pipeline efficiently processes a stream of 14 observations per second: RMLStreamer maps JSON observations to RDF in 13.5 ms, a C-SPARQL query to generate fever alarms is executed on a window of 5 s in 26.4 ms, and Streaming MASSIF generates a smart notification for fever alarms based on severity and urgency in 1539.5 ms. DIVIDE derives the C-SPARQL queries in 7249.5 ms, while AMADEUS constructs a colon cancer treatment plan and performs conflict detection with it in 190.8 ms and 1335.7 ms, respectively. CONCLUSIONS: Existing tools built upon Semantic Web technologies can be leveraged to optimize continuous care provisioning. The evaluation of the building blocks on a realistic homecare monitoring use case demonstrates their applicability, usability and good performance. Further extending the available user interfaces for some tools is required to increase their adoption.
Correction to: Semantic units: organizing knowledge graphs into semantically meaningful units of representation.
Vogt L, Kuhn T, Hoehndorf R
J Biomed Semantics · 2024 Jun · PMID 38844997 · Full text
Abstract loading — click title to view on PubMed.
Explanatory argumentation in natural language for correct and incorrect medical diagnoses.
Molinet B, Marro S, Cabrio E … +1 more , Villata S
J Biomed Semantics · 2024 May · PMID 38816758 · Full text
BACKGROUND: A huge amount of research is carried out nowadays in Artificial Intelligence to propose automated ways to analyse medical data with the aim to support doctors in delivering medical diagnoses. However, a main...
BACKGROUND: A huge amount of research is carried out nowadays in Artificial Intelligence to propose automated ways to analyse medical data with the aim to support doctors in delivering medical diagnoses. However, a main issue of these approaches is the lack of transparency and interpretability of the achieved results, making it hard to employ such methods for educational purposes. It is therefore necessary to develop new frameworks to enhance explainability in these solutions. RESULTS: In this paper, we present a novel full pipeline to generate automatically natural language explanations for medical diagnoses. The proposed solution starts from a clinical case description associated with a list of correct and incorrect diagnoses and, through the extraction of the relevant symptoms and findings, enriches the information contained in the description with verified medical knowledge from an ontology. Finally, the system returns a pattern-based explanation in natural language which elucidates why the correct (incorrect) diagnosis is the correct (incorrect) one. The main contribution of the paper is twofold: first, we propose two novel linguistic resources for the medical domain (i.e, a dataset of 314 clinical cases annotated with the medical entities from UMLS, and a database of biological boundaries for common findings), and second, a full Information Extraction pipeline to extract symptoms and findings from the clinical cases and match them with the terms in a medical ontology and to the biological boundaries. An extensive evaluation of the proposed approach shows the our method outperforms comparable approaches. CONCLUSIONS: Our goal is to offer AI-assisted educational support framework to form clinical residents to formulate sound and exhaustive explanations for their diagnoses to patients.
Semantic units: organizing knowledge graphs into semantically meaningful units of representation.
Vogt L, Kuhn T, Hoehndorf R
J Biomed Semantics · 2024 May · PMID 38802877 · Full text
BACKGROUND: In today's landscape of data management, the importance of knowledge graphs and ontologies is escalating as critical mechanisms aligned with the FAIR Guiding Principles-ensuring data and metadata are Findable...
BACKGROUND: In today's landscape of data management, the importance of knowledge graphs and ontologies is escalating as critical mechanisms aligned with the FAIR Guiding Principles-ensuring data and metadata are Findable, Accessible, Interoperable, and Reusable. We discuss three challenges that may hinder the effective exploitation of the full potential of FAIR knowledge graphs. RESULTS: We introduce "semantic units" as a conceptual solution, although currently exemplified only in a limited prototype. Semantic units structure a knowledge graph into identifiable and semantically meaningful subgraphs by adding another layer of triples on top of the conventional data layer. Semantic units and their subgraphs are represented by their own resource that instantiates a corresponding semantic unit class. We distinguish statement and compound units as basic categories of semantic units. A statement unit is the smallest, independent proposition that is semantically meaningful for a human reader. Depending on the relation of its underlying proposition, it consists of one or more triples. Organizing a knowledge graph into statement units results in a partition of the graph, with each triple belonging to exactly one statement unit. A compound unit, on the other hand, is a semantically meaningful collection of statement and compound units that form larger subgraphs. Some semantic units organize the graph into different levels of representational granularity, others orthogonally into different types of granularity trees or different frames of reference, structuring and organizing the knowledge graph into partially overlapping, partially enclosed subgraphs, each of which can be referenced by its own resource. CONCLUSIONS: Semantic units, applicable in RDF/OWL and labeled property graphs, offer support for making statements about statements and facilitate graph-alignment, subgraph-matching, knowledge graph profiling, and for management of access restrictions to sensitive data. Additionally, we argue that organizing the graph into semantic units promotes the differentiation of ontological and discursive information, and that it also supports the differentiation of multiple frames of reference within the graph.
Leveraging logical definitions and lexical features to detect missing IS-A relations in biomedical terminologies.
Abeysinghe R, Zheng F, Shi J … +2 more , Lhatoo SD, Cui L
J Biomed Semantics · 2024 May · PMID 38693592 · Full text
Biomedical terminologies play a vital role in managing biomedical data. Missing IS-A relations in a biomedical terminology could be detrimental to its downstream usages. In this paper, we investigate an approach combinin...
Biomedical terminologies play a vital role in managing biomedical data. Missing IS-A relations in a biomedical terminology could be detrimental to its downstream usages. In this paper, we investigate an approach combining logical definitions and lexical features to discover missing IS-A relations in two biomedical terminologies: SNOMED CT and the National Cancer Institute (NCI) thesaurus. The method is applied to unrelated concept-pairs within non-lattice subgraphs: graph fragments within a terminology likely to contain various inconsistencies. Our approach first compares whether the logical definition of a concept is more general than that of the other concept. Then, we check whether the lexical features of the concept are contained in those of the other concept. If both constraints are satisfied, we suggest a potentially missing IS-A relation between the two concepts. The method identified 982 potential missing IS-A relations for SNOMED CT and 100 for NCI thesaurus. In order to assess the efficacy of our approach, a random sample of results belonging to the "Clinical Findings" and "Procedure" subhierarchies of SNOMED CT and results belonging to the "Drug, Food, Chemical or Biomedical Material" subhierarchy of the NCI thesaurus were evaluated by domain experts. The evaluation results revealed that 118 out of 150 suggestions are valid for SNOMED CT and 17 out of 20 are valid for NCI thesaurus.
Elucidating the semantics-topology trade-off for knowledge inference-based pharmacological discovery.
Sosa DN, Neculae G, Fauqueur J … +1 more , Altman RB
J Biomed Semantics · 2024 May · PMID 38693563 · Full text
Leveraging AI for synthesizing the deluge of biomedical knowledge has great potential for pharmacological discovery with applications including developing new therapeutics for untreated diseases and repurposing drugs as...
Leveraging AI for synthesizing the deluge of biomedical knowledge has great potential for pharmacological discovery with applications including developing new therapeutics for untreated diseases and repurposing drugs as emergent pandemic treatments. Creating knowledge graph representations of interacting drugs, diseases, genes, and proteins enables discovery via embedding-based ML approaches and link prediction. Previously, it has been shown that these predictive methods are susceptible to biases from network structure, namely that they are driven not by discovering nuanced biological understanding of mechanisms, but based on high-degree hub nodes. In this work, we study the confounding effect of network topology on biological relation semantics by creating an experimental pipeline of knowledge graph semantic and topological perturbations. We show that the drop in drug repurposing performance from ablating meaningful semantics increases by 21% and 38% when mitigating topological bias in two networks. We demonstrate that new methods for representing knowledge and inferring new knowledge must be developed for making use of biomedical semantics for pharmacological innovation, and we suggest fruitful avenues for their development.
Ontological representation, modeling, and analysis of parasite vaccines.
Huffman A, Zhang X, Lanka M … +3 more , Zheng J, Masci AM, He Y
J Biomed Semantics · 2024 Apr · PMID 38664818 · Full text
BACKGROUND: Pathogenic parasites are responsible for multiple diseases, such as malaria and Chagas disease, in humans and livestock. Traditionally, pathogenic parasites have been largely an evasive topic for vaccine desi...
BACKGROUND: Pathogenic parasites are responsible for multiple diseases, such as malaria and Chagas disease, in humans and livestock. Traditionally, pathogenic parasites have been largely an evasive topic for vaccine design, with most successful vaccines only emerging recently. To aid vaccine design, the VIOLIN vaccine knowledgebase has collected vaccines from all sources to serve as a comprehensive vaccine knowledgebase. VIOLIN utilizes the Vaccine Ontology (VO) to standardize the modeling of vaccine data. VO did not model complex life cycles as seen in parasites. With the inclusion of successful parasite vaccines, an update in parasite vaccine modeling was needed. RESULTS: VIOLIN was expanded to include 258 parasite vaccines against 23 protozoan species, and 607 new parasite vaccine-related terms were added to VO since 2022. The updated VO design for parasite vaccines accounts for parasite life stages and for transmission-blocking vaccines. A total of 356 terms from the Ontology of Parasite Lifecycle (OPL) were imported to VO to help represent the effect of different parasite life stages. A new VO class term, 'transmission-blocking vaccine,' was added to represent vaccines able to block infectious transmission, and one new VO object property, 'blocks transmission of pathogen via vaccine,' was added to link vaccine and pathogen in which the vaccine blocks the transmission of the pathogen. Additionally, our Gene Set Enrichment Analysis (GSEA) of 140 parasite antigens used in the parasitic vaccines identified enriched features. For example, significant patterns, such as signal, plasma membrane, and entry into host, were found in the antigens of the vaccines against two parasite species: Plasmodium falciparum and Toxoplasma gondii. The analysis found 18 out of the 140 parasite antigens involved with the malaria disease process. Moreover, a majority (15 out of 54) of P. falciparum parasite antigens are localized in the cell membrane. T. gondii antigens, in contrast, have a majority (19/24) of their proteins related to signaling pathways. The antigen-enriched patterns align with the life cycle stage patterns identified in our ontological parasite vaccine modeling. CONCLUSIONS: The updated VO modeling and GSEA analysis capture the influence of the complex parasite life cycles and their associated antigens on vaccine development.
Comparing generative and extractive approaches to information extraction from abstracts describing randomized clinical trials.
Witte C, Schmidt DM, Cimiano P
J Biomed Semantics · 2024 Apr · PMID 38654304 · Full text
BACKGROUND: Systematic reviews of Randomized Controlled Trials (RCTs) are an important part of the evidence-based medicine paradigm. However, the creation of such systematic reviews by clinical experts is costly as well...
BACKGROUND: Systematic reviews of Randomized Controlled Trials (RCTs) are an important part of the evidence-based medicine paradigm. However, the creation of such systematic reviews by clinical experts is costly as well as time-consuming, and results can get quickly outdated after publication. Most RCTs are structured based on the Patient, Intervention, Comparison, Outcomes (PICO) framework and there exist many approaches which aim to extract PICO elements automatically. The automatic extraction of PICO information from RCTs has the potential to significantly speed up the creation process of systematic reviews and this way also benefit the field of evidence-based medicine. RESULTS: Previous work has addressed the extraction of PICO elements as the task of identifying relevant text spans or sentences, but without populating a structured representation of a trial. In contrast, in this work, we treat PICO elements as structured templates with slots to do justice to the complex nature of the information they represent. We present two different approaches to extract this structured information from the abstracts of RCTs. The first approach is an extractive approach based on our previous work that is extended to capture full document representations as well as by a clustering step to infer the number of instances of each template type. The second approach is a generative approach based on a seq2seq model that encodes the abstract describing the RCT and uses a decoder to infer a structured representation of a trial including its arms, treatments, endpoints and outcomes. Both approaches are evaluated with different base models on a manually annotated dataset consisting of RCT abstracts on an existing dataset comprising 211 annotated clinical trial abstracts for Type 2 Diabetes and Glaucoma. For both diseases, the extractive approach (with flan-t5-base) reached the best score, i.e. 0.547 ( ) for type 2 diabetes and 0.636 ( ) for glaucoma. Generally, the scores were higher for glaucoma than for type 2 diabetes and the standard deviation was higher for the generative approach. CONCLUSION: In our experiments, both approaches show promising performance extracting structured PICO information from RCTs, especially considering that most related work focuses on the far easier task of predicting less structured objects. In our experimental results, the extractive approach performs best in both cases, although the lead is greater for glaucoma than for type 2 diabetes. For future work, it remains to be investigated how the base model size affects the performance of both approaches in comparison. Although the extractive approach currently leaves more room for direct improvements, the generative approach might benefit from larger models.
RecSOI: recommending research directions using statements of ignorance.
Bibal A, Salem NM, Cardon R … +4 more , White EK, Acuna DE, Burke R, Hunter LE
J Biomed Semantics · 2024 Apr · PMID 38650032 · Full text
The more science advances, the more questions are asked. This compounding growth can make it difficult to keep up with current research directions. Furthermore, this difficulty is exacerbated for junior researchers who e...
The more science advances, the more questions are asked. This compounding growth can make it difficult to keep up with current research directions. Furthermore, this difficulty is exacerbated for junior researchers who enter fields with already large bases of potentially fruitful research avenues. In this paper, we propose a novel task and a recommender system for research directions, RecSOI, that draws from statements of ignorance (SOIs) found in the research literature. By building researchers' profiles based on textual elements, RecSOI generates personalized recommendations of potential research directions tailored to their interests. In addition, RecSOI provides context for the recommended SOIs, so that users can quickly evaluate how relevant the research direction is for them. In this paper, we provide an overview of RecSOI's functioning, implementation, and evaluation, demonstrating its effectiveness in guiding researchers through the vast landscape of potential research directions.
Enriching the FIDEO ontology with food-drug interactions from online knowledge sources.
Azzi R, Bordea G, Griffier R … +2 more , Nikiema JN, Mougin F
J Biomed Semantics · 2024 Mar · PMID 38438913 · Full text
The increasing number of articles on adverse interactions that may occur when specific foods are consumed with certain drugs makes it difficult to keep up with the latest findings. Conflicting information is available in...
The increasing number of articles on adverse interactions that may occur when specific foods are consumed with certain drugs makes it difficult to keep up with the latest findings. Conflicting information is available in the scientific literature and specialized knowledge bases because interactions are described in an unstructured or semi-structured format. The FIDEO ontology aims to integrate and represent information about food-drug interactions in a structured way. This article reports on the new version of this ontology in which more than 1700 interactions are integrated from two online resources: DrugBank and Hedrine. These food-drug interactions have been represented in FIDEO in the form of precompiled concepts, each of which specifies both the food and the drug involved. Additionally, competency questions that can be answered are reviewed, and avenues for further enrichment are discussed.
The use of foundational ontologies in biomedical research.
Bernabé CH, Queralt-Rosinach N, Silva Souza VE … +4 more , Bonino da Silva Santos LO, Mons B, Jacobsen A, Roos M
J Biomed Semantics · 2023 Dec · PMID 38082345 · Full text
BACKGROUND: The FAIR principles recommend the use of controlled vocabularies, such as ontologies, to define data and metadata concepts. Ontologies are currently modelled following different approaches, sometimes describi...
BACKGROUND: The FAIR principles recommend the use of controlled vocabularies, such as ontologies, to define data and metadata concepts. Ontologies are currently modelled following different approaches, sometimes describing conflicting definitions of the same concepts, which can affect interoperability. To cope with that, prior literature suggests organising ontologies in levels, where domain specific (low-level) ontologies are grounded in domain independent high-level ontologies (i.e., foundational ontologies). In this level-based organisation, foundational ontologies work as translators of intended meaning, thus improving interoperability. Despite their considerable acceptance in biomedical research, there are very few studies testing foundational ontologies. This paper describes a systematic literature mapping that was conducted to understand how foundational ontologies are used in biomedical research and to find empirical evidence supporting their claimed (dis)advantages. RESULTS: From a set of 79 selected papers, we identified that foundational ontologies are used for several purposes: ontology construction, repair, mapping, and ontology-based data analysis. Foundational ontologies are claimed to improve interoperability, enhance reasoning, speed up ontology development and facilitate maintainability. The complexity of using foundational ontologies is the most commonly cited downside. Despite being used for several purposes, there were hardly any experiments (1 paper) testing the claims for or against the use of foundational ontologies. In the subset of 49 papers that describe the development of an ontology, it was observed a low adherence to ontology construction (16 papers) and ontology evaluation formal methods (4 papers). CONCLUSION: Our findings have two main implications. First, the lack of empirical evidence about the use of foundational ontologies indicates a need for evaluating the use of such artefacts in biomedical research. Second, the low adherence to formal methods illustrates how the field could benefit from a more systematic approach when dealing with the development and evaluation of ontologies. The understanding of how foundational ontologies are used in the biomedical field can drive future research towards the improvement of ontologies and, consequently, data FAIRness. The adoption of formal methods can impact the quality and sustainability of ontologies, and reusing these methods from other fields is encouraged.
BioBLP: a modular framework for learning on multimodal biomedical knowledge graphs.
Daza D, Alivanistos D, Mitra P … +3 more , Pijnenburg T, Cochez M, Groth P
J Biomed Semantics · 2023 Dec · PMID 38066573 · Full text
BACKGROUND: Knowledge graphs (KGs) are an important tool for representing complex relationships between entities in the biomedical domain. Several methods have been proposed for learning embeddings that can be used to pr...
BACKGROUND: Knowledge graphs (KGs) are an important tool for representing complex relationships between entities in the biomedical domain. Several methods have been proposed for learning embeddings that can be used to predict new links in such graphs. Some methods ignore valuable attribute data associated with entities in biomedical KGs, such as protein sequences, or molecular graphs. Other works incorporate such data, but assume that entities can be represented with the same data modality. This is not always the case for biomedical KGs, where entities exhibit heterogeneous modalities that are central to their representation in the subject domain. OBJECTIVE: We aim to understand how to incorporate multimodal data into biomedical KG embeddings, and analyze the resulting performance in comparison with traditional methods. We propose a modular framework for learning embeddings in KGs with entity attributes, that allows encoding attribute data of different modalities while also supporting entities with missing attributes. We additionally propose an efficient pretraining strategy for reducing the required training runtime. We train models using a biomedical KG containing approximately 2 million triples, and evaluate the performance of the resulting entity embeddings on the tasks of link prediction, and drug-protein interaction prediction, comparing against methods that do not take attribute data into account. RESULTS: In the standard link prediction evaluation, the proposed method results in competitive, yet lower performance than baselines that do not use attribute data. When evaluated in the task of drug-protein interaction prediction, the method compares favorably with the baselines. Further analyses show that incorporating attribute data does outperform baselines over entities below a certain node degree, comprising approximately 75% of the diseases in the graph. We also observe that optimizing attribute encoders is a challenging task that increases optimization costs. Our proposed pretraining strategy yields significantly higher performance while reducing the required training runtime. CONCLUSION: BioBLP allows to investigate different ways of incorporating multimodal biomedical data for learning representations in KGs. With a particular implementation, we find that incorporating attribute data does not consistently outperform baselines, but improvements are obtained on a comparatively large subset of entities below a specific node-degree. Our results indicate a potential for improved performance in scientific discovery tasks where understudied areas of the KG would benefit from link prediction methods.
Assessing resolvability, parsability, and consistency of RDF resources: a use case in rare diseases.
Zhang S, Benis N, Cornet R
J Biomed Semantics · 2023 Dec · PMID 38053130 · Full text
INTRODUCTION: Healthcare data and the knowledge gleaned from it play a key role in improving the health of current and future patients. These knowledge sources are regularly represented as 'linked' resources based on the...
INTRODUCTION: Healthcare data and the knowledge gleaned from it play a key role in improving the health of current and future patients. These knowledge sources are regularly represented as 'linked' resources based on the Resource Description Framework (RDF). Making resources 'linkable' to facilitate their interoperability is especially important in the rare-disease domain, where health resources are scattered and scarce. However, to benefit from using RDF, resources need to be of good quality. Based on existing metrics, we aim to assess the quality of RDF resources related to rare diseases and provide recommendations for their improvement. METHODS: Sixteen resources of relevance for the rare-disease domain were selected: two schemas, three metadatasets, and eleven ontologies. These resources were tested on six objective metrics regarding resolvability, parsability, and consistency. Any URI that failed the test based on any of the six metrics was recorded as an error. The error count and percentage of each tested resource were recorded. The assessment results were represented in RDF, using the Data Quality Vocabulary schema. RESULTS: For three out of the six metrics, the assessment revealed quality issues. Eleven resources have non-resolvable URIs with proportion to all URIs ranging from 0.1% (6/6,712) in the Anatomical Therapeutic Chemical Classification to 13.7% (17/124) in the WikiPathways Ontology; seven resources have undefined URIs; and two resources have incorrectly used properties of the 'owl:ObjectProperty' type. Individual errors were examined to generate suggestions for the development of high-quality RDF resources, including the tested resources. CONCLUSION: We assessed the resolvability, parsability, and consistency of RDF resources in the rare-disease domain, and determined the extent of these types of errors that potentially affect interoperability. The qualitative investigation on these errors reveals how they can be avoided. All findings serve as valuable input for the development of a guideline for creating high-quality RDF resources, thereby enhancing the interoperability of biomedical resources.
Impact of COVID-19 research: a study on predicting influential scholarly documents using machine learning and a domain-independent knowledge graph.
Rabby G, D'Souza J, Oelen A … +3 more , Dvorackova L, Svátek V, Auer S
J Biomed Semantics · 2023 Nov · PMID 38017587 · Full text
Multiple studies have investigated bibliometric features and uncategorized scholarly documents for the influential scholarly document prediction task. In this paper, we describe our work that attempts to go beyond biblio...
Multiple studies have investigated bibliometric features and uncategorized scholarly documents for the influential scholarly document prediction task. In this paper, we describe our work that attempts to go beyond bibliometric metadata to predict influential scholarly documents. Furthermore, this work also examines the influential scholarly document prediction task over categorized scholarly documents. We also introduce a new approach to enhance the document representation method with a domain-independent knowledge graph to find the influential scholarly document using categorized scholarly content. As the input collection, we use the WHO corpus with scholarly documents on the theme of COVID-19. This study examines different document representation methods for machine learning, including TF-IDF, BOW, and embedding-based language models (BERT). The TF-IDF document representation method works better than others. From various machine learning methods tested, logistic regression outperformed the other for scholarly document category classification, and the random forest algorithm obtained the best results for influential scholarly document prediction, with the help of a domain-independent knowledge graph, specifically DBpedia, to enhance the document representation method for predicting influential scholarly documents with categorical scholarly content. In this case, our study combines state-of-the-art machine learning methods with the BOW document representation method. We also enhance the BOW document representation with the direct type (RDF type) and unqualified relation from DBpedia. From this experiment, we did not find any impact of the enhanced document representation for the scholarly document category classification. We found an effect in the influential scholarly document prediction with categorical data.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe