A5064709498- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Topic Modeling
- Natural Language Processing Techniques
- Bioinformatics and Genomic Networks
- Data-Driven Disease Surveillance
- Disaster Response and Management
- Emergency and Acute Care Studies
- Machine Learning in Healthcare
- COVID-19 Clinical Research Studies
- Cardiac, Anesthesia and Surgical Outcomes
- Computational Drug Discovery Methods
- Genomics and Rare Diseases
- Advanced Text Analysis Techniques
- Social Media in Health Education
- Artificial Intelligence in Healthcare and Education
- Cerebrovascular and Carotid Artery Diseases
- Heart Failure Treatment and Management
- Respiratory Support and Mechanisms
- Cardiovascular Function and Risk Factors
- Gene expression and cancer classification
- Machine Learning in Materials Science
- Biotin and Related Studies
- Arduino and IoT Applications
- Family Caregiving in Mental Illness
University of Birmingham
2016-2025
Birmingham Research Park
2023-2025
Clinical Trial Investigators
2025
University Hospitals Birmingham NHS Foundation Trust
2020-2024
Sussex Partnership NHS Foundation Trust
2024
Health Data Research UK
2020-2023
IDEAconsult
2023
Genomics (United Kingdom)
2021-2023
National Health Service
2021
King Abdullah University of Science and Technology
2014-2016
Abstract Background The National Early Warning Score (NEWS2) is currently recommended in the UK for risk stratification of COVID-19 patients, but little known about its ability to detect severe cases. We aimed evaluate NEWS2 prediction outcome and identify validate a set blood physiological parameters routinely collected at hospital admission improve upon use alone medium-term stratification. Methods Training cohorts comprised 1276 patients admitted King’s College Hospital Health Service...
Artificial intelligence (AI) is increasingly being utilized in healthcare. This article provides clinicians and researchers with a step-wise foundation for high-value AI that can be applied to variety of different data modalities. The aim improve the transparency application methods, potential benefit patients routine cardiovascular care. Following clear research hypothesis, an AI-based workflow begins selection pre-processing prior analysis, type (structured, semi-structured, or...
Many ontologies have been developed in biology and these increasingly contain large volumes of formalized knowledge commonly expressed the Web Ontology Language (OWL). Computational access to contained within relies on use automated reasoning. We Aber-OWL infrastructure that provides reasoning services for bio-ontologies. consists an ontology repository, a set web interfaces enable ontology-based semantic biological data literature. is freely available at http://aber-owl.net . framework...
Chemoinformatics has developed efficient ways of representing chemical structures for small molecules as simple text strings, simplified molecular-input line-entry system (SMILES) and the IUPAC International Chemical Identifier (InChI), which are machine-readable. In particular, InChIs have been extended to encode formalized representations mixtures reactions, work is ongoing represent polymers other macromolecules in this way. The next frontier encoding multi-component nanomaterials (NMs) a...
Real-world evidence (RWE) plays an increasingly important role within global regulatory and reimbursement processes. RWE generation can be enhanced by collecting using patient-reported outcomes (PROs), which provide valuable information on the effectiveness, safety, tolerability of health interventions from patient perspective. This analysis aims to examine summarise utilisation measures (PROMs) in real-world studies.
In mediaeval Europe, the term “commons” described way that communities managed land was held “in common” and provided a clear set of rules for how this “common land” used developed by, for, community. Similarly, as we move towards an increasingly knowledge-based society where data is new oil, approaches to sharing jointly owning publicly funded research are needed maximise its added value. Such common management will extend data’s useful life facilitate reuse range additional purposes, from...
Ontology-based phenotype profiles have been utilised for the purpose of differential diagnosis rare genetic diseases, and decision support in specific disease domains. Particularly, semantic similarity facilitates diagnostic hypothesis generation through comparison with profiles. However, approach has not applied common or generalised clinical diagnostics from uncurated text-derived phenotypes. In this work, we describe development an deriving patient narrative text, apply to text associated...
Negation detection is an important task in biomedical text mining. Particularly clinical settings, it of critical importance to determine whether findings mentioned are present or absent. Rule-based negation algorithms a common approach the task, and more recent investigations have resulted development rule-based systems utilising rich grammatical information afforded by typed dependency graphs. However, interacting with these complex representations inevitably necessitates rules, which...
Adverse Outcome Pathways (AOPs) provide a basis for non-animal testing, by outlining the cascade of molecular and cellular events initiated upon stressor exposure, leading to adverse effects. In recent years, scientific community has shown interest in developing AOPs through crowdsourcing, with results archived AOP-Wiki: centralized repository coordinated OECD, hosting nearly 512 (April, 2023). However, AOP-Wiki platform currently lacks versatile querying system, which hinders developers'...
Abstract Summary Komenti is a reasoner-enabled semantic query and information extraction framework. It the only text mining tool that enables querying inferred knowledge from biomedical ontologies. also contains multiple novel components for vocabulary construction context disambiguation, which can improve power of ontology-based analysis tasks, with view towards making full use provision ontologies characterisation analysis. Here, we describe its features, present case wherein automate...
Abstract Background Ontologies are widely used throughout the biomedical domain. These ontologies formally represent classes and relations assumed to exist within a As scientific domains deeply interlinked, so too their representations. While individual can be tested for consistency coherency using automated reasoning methods, systematically combining of multiple together may reveal previously hidden contradictions. Methods We developed method that tests unsatisfiabilities in an ontology...
Reasoning over biomedical ontologies using their OWL semantics has traditionally been a challenging task due to the high theoretical complexity of OWL-based automated reasoning. As consequence, ontology repositories, as well most other tools utilizing ontologies, either provide access without use reasoning, or limit number for which reasoning-based is provided. We apply AberOWL infrastructure all accessible and consistent in BioPortal (368 ontologies). perform an extensive performance...
Abstract Background Biomedical ontologies contain a wealth of metadata that constitutes fundamental infrastructural resource for text mining. For several reasons, redundancies exist in the ontology ecosystem, which lead to same entities being described by concepts or similar contexts across ontologies. While these describe entities, they different sets complementary metadata. Linking definitions make use their combined could improved performance ontology-based information retrieval,...
Link prediction in complex networks has recently attracted a great deal of attraction diverse scientific domains, including social and biological sciences. Given snapshot network, the goal is to predict links that are missing network or likely occur near future. This problem both theoretical practical significance; it not only helps us identify more efficiently by avoiding expensive time consuming experimental processes, but also allows study evolution with time. To address link prediction,...
The era of high-throughput techniques created big data in the medical field and research disciplines. Machine intelligence (MI) approaches can overcome critical limitations on how those large-scale sets are processed, analyzed, interpreted. 67th Annual Meeting Radiation Research Society featured a symposium MI to highlight recent advancements radiation sciences their clinical applications. This article summarizes three presentations regarding developments for metadata processing ontological...
Abstract Background Biomedical ontologies contain a wealth of metadata that constitutes fundamental infrastructural resource for text mining. For several reasons, redundancies exist in the ontology ecosystem, which lead to same concepts being described by terms or similar contexts across ontologies. While these describe concepts, they different sets complementary metadata. Linking definitions make use their combined could improved performance ontology-based information retrieval, extraction,...
It is known that the aging process entails a cognitive decline in certain processes such as attention, episodic memory, working processing speed and executive functions. In recent years, efforts have been made to investigate potential of Information Communication Technologies imp rove functioning quality life older adults with without impairments. this paper, we propose Aging Neuro-Behaviour Ontology (ANBO), formal model involved day-to-day living whose performance usually age. ANBO has...
Abstract Background Negation detection is an important task in biomedical text mining. Particularly clinical settings, it of critical importance to determine whether findings mentioned are present or absent. Rule-based negation algorithms a common approach the task, and more recent investigations have resulted development rule-based systems utilising rich grammatical information afforded by typed dependency graphs. However, interacting with these complex representations inevitably...
Unstructured text created by patients represents a rich, but relatively inaccessible resource for advancing patient-centred care. This study aimed to develop an ontology ocular immune-mediated inflammatory diseases (OcIMIDo), as tool facilitate data extraction and analysis, illustrating its application online patient support forum data.
Abstract Identification of ontology concepts in clinical narrative text enables the creation phenotype profiles that can be associated with entities, such as patients or drugs. Constructing patient using formal ontologies their analysis via semantic similarity, turn enabling use background knowledge clustering classification analyses. However, traditional similarity approaches collapse complex relationships between phenotypes into a unitary scores for each pair patients. Moreover, single may...