Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Natural Language Processing”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14Linked to original sources
PubMed2003

Computational knowledge integration in biopharmaceutical research.

An initiative to increase biopharmaceutical research productivity by capturing, sharing and computationally integrating proprietary scientific discoveries with public knowledge is described. This initiative involves both organisational process change and multiple interoperating software systems. The software components rely on mutually supporting integration techniques. These include a richly structured ontology, statistical analysis of experimental data against stored conclusions, natural language processing of public literature, secure document repositories with lightweight metadata, web services integration, enterprise web portals and relational databases. This approach has already begun to increase scientific productivity in our enterprise by creating an organisational memory (OM) of internal research findings, accessible on the web. Through bringing together these components it has also been possible to construct a very large and expanding repository of biological pathway information linked to this repository of findings which is extremely useful in analysis of DNA microarray data. This repository, in turn, enables our research paradigm to be shifted towards more comprehensive systems-based understandings of drug action.

Algorithms↗
PubMed1984

Phonemic and phonetic factors in adult cross-language speech perception.

Previous research has indicated that young infants can discriminate speech sounds across phonetic boundaries regardless of specific relevant experience, and that there is a modification in this ability during ontogeny such that adults often have difficulty discriminating phonetic contrasts which are not used contrastively in their native language. This pattern of findings has often been interpreted as suggesting that humans are endowed with innate auditory sensitivities which enable them to discriminate speech sounds according to universal phonetic boundaries and that there is a decline or loss in this ability after being exposed to a language which contrasts only a subset of those distinctions. The present experiments were designed to determine whether this modification represents a loss of sensorineural response capabilities or whether it shows a shift in attentional focus and/or processing strategies. In experiment 1, adult English-speaking subjects were tested on their ability to discriminate two non-English speech contrasts in a category-change discrimination task after first being predisposed to adopt one of four perceptual sets. In experiments 2, 3, and 4 subjects were tested in an AX (same/different) procedure, and the effects of both limited training and duration of the interstimulus interval were assessed. Results suggest that the previously observed ontogenetic modification in the perception of non-native phonetic contrasts involves a change in processing strategies rather than a sensorineural loss. Adult listeners can discriminate sounds across non-native phonetic categories in some testing conditions, but are not able to use that ability in testing conditions which have demands similar to those required in natural language processing.

Adolescent↗
PubMed2026

The AI Revolution: Shaping the Present and Future of Pharmaceutical Research and Development.

The transformative role of artificial intelligence (AI) in the pharmaceutical industry is examined, with a focus on its significant contributions to drug discovery, development, and clinical trial processes. It highlights the inefficiencies and high costs associated with traditional drug development and explores how AI and machine learning (ML) can enhance these processes by analyzing extensive biological datasets. The historical context of AI in pharmaceutical development is examined, noting how advances in computational power and data accessibility have facilitated innovative methodologies, such as predictive analytics and natural language processing. Contemporary trends reveal the integration of AI technologies in drug design, repurposing, and patient response forecasting. This study also addresses the challenges of participant recruitment for clinical trials and proposes AI-driven solutions to optimize patient selection and data management. Furthermore, it discusses AI's role in tailored medicine, emphasizing its potential for advancing precision therapy through targeted drug development and personalized treatment strategies. The importance of digital tools, genomic data analysis, and AI-driven imaging technologies for customizing therapeutic approaches is underscored, along with the regulatory and ethical challenges posed by AI deployment in healthcare. This study illustrates the complexities of AI applications in the pharmaceutical sector, offering insights into both successful and unsuccessful initiatives. The findings suggest that the digitalization of the pharmaceutical industry and enhanced AI integration hold promise for developing safer and more effective therapeutic strategies, while also identifying obstacles to their widespread adoption and optimal functionality.

Artificial intelligence↗
PubMed1994

Creating a knowledge base of biological research papers.

Intelligent text-oriented tools for representing and searching the biological research literature are being developed, which combine object-oriented databases with artificial intelligence techniques to create a richly structured knowledge based of Materials and Methods sections of biological research papers. A knowledge model of experimental processes, biological and chemical substances, and analytical techniques is described, based on the representation techniques of taxonomic semantic nets and knowledge frames. Two approaches to populating the knowledge base with the contents of biological research papers are described: natural language processing and an interactive knowledge definition tool.

Algorithms↗
PubMed1999

Telemedicine and terminology: different needs of context information.

Traditionally, communication between healthcare providers, including the provision of physicians with information and knowledge, works quite well because there are implicitly common conventions and assumptions in the collaboration of all involved actors. The basic prerequisite of the communication process between humans is a mutual agreement on syntax and semantics of oral and written language, i.e., of the medical sublanguage. With telemedicine, i.e., the use of telecommunication and informatics in medicine, this prerequisite is no longer sufficient. First, various professionals from different clinical communities, characterized by specialty, nationality, school, etc., share the management of the patient's health. Second, electronically communicated information is more and more intended for processing by computer applications rather than for direct interpretation by human users. Third, the interconnection of distributed heterogeneous software systems in medicine raises the issue of semantic interoperability, especially the problem of data integration. A faithful communication in such a scenario must be based on explicit assumptions "behind" a message. Interpreting an usually highly context-dependent utterance demands for mechanisms on a pragmatic level in natural language processing. The need for additional processing and integration of the transferred data by the receiving system demands for standardization and mediation, taking into consideration contextual knowledge that cannot entirely be explained and processed with linguistic and terminological approaches. This paper describes different categories of contexts and also different needs of applications concerning "context awareness."

Telemedicine↗
PubMed2004

Mental imagery for a conversational robot.

To build robots that engage in fluid face-to-face spoken conversations with people, robots must have ways to connect what they say to what they see. A critical aspect of how language connects to vision is that language encodes points of view. The meaning of my left and your left differs due to an implied shift of visual perspective. The connection of language to vision also relies on object permanence. We can talk about things that are not in view. For a robot to participate in situated spoken dialog, it must have the capacity to imagine shifts of perspective, and it must maintain object permanence. We present a set of representations and procedures that enable a robotic manipulator to maintain a "mental model" of its physical environment by coupling active vision to physical simulation. Within this model, "imagined" views can be generated from arbitrary perspectives, providing the basis for situated language comprehension and production. An initial application of mental imagery for spatial language understanding for an interactive robot is described.

Algorithms↗
PubMed2002

A review of medical imaging informatics.

This review of medical imaging informatics is a survey of current developments in an exciting field. The focus is on informatics issues rather than traditional data processing and information systems, such as picture archiving and communications systems (PACS) and image processing and analysis systems. In this review, we address imaging informatics issues within the requirements of an informatics system defined by the American Medical Informatics Association. With these requirements as a framework, we review, in four sections: (1) Methods to present imaging and associated data without causing an overload, including image study summarization, content-based medical image retrieval, and natural language processing of text data. (2) Data modeling techniques to represent clinical data with focus on an image data model, including general-purpose time-based multimedia data models, health-care-specific data models, knowledge models, and problem-centric data models. (3) Methods to integrate medical data information from heterogeneous clinical data sources. Advances in centralized databases and mediated architectures are reviewed along with a discussion on our efforts at data integration based on peer-to-peer networking and shared file systems. (4) Visualization schemas to present imaging and clinical data: the large volume of medical data presents a daunting challenge for an efficient visualization paradigm. In this section we review current multimedia visualization methods including temporal modeling, problem-specific data organization, including our problem-centric, context and user-specific visualization interface.

Databases, Factual↗
PubMed2006

Tools for Czech biomedical ontologies creation.

The paper describes procedures and a tool we have developed to simplify and speed up creating of Czech biomedical ontologies. Our method is based on searching for concepts in a corpus of medical texts and binding those concepts to an established international ontology. The new ontology will have two major advantages: it will be compatible with the international ontology and it will possibly cover all concepts used in the Czech healthcare. The tool supports an author of ontology by mechanizing some routine tasks that occurs in the process of an ontology creation. It tries to learn how to identify concepts in texts and how to bind them to the ontology. The tool then displays the suggestions to a user, who can correct them and add some new ones. Based on this feedback the tool adjusts rules for concept finding and binding. To accomplish such behaviour we have employed some natural language processing methods and information extraction tools.

Czech Republic↗
PubMed1994

International Federation of Clinical Chemistry. Use of artificial intelligence in analytical systems for the clinical laboratory. IFCC Committee on Analytical Systems.

The incorporation of information-processing technology into analytical systems in the form of standard computing software has recently been advanced by the introduction of artificial intelligence (AI) both as expert systems and as neural networks. This paper considers the role of software in system operation, control and automation and attempts to define intelligence. AI is characterized by its ability to deal with incomplete and imprecise information and to accumulate knowledge. Expert systems, building on standard computing techniques, depend heavily on the domain experts and knowledge engineers that have programmed them to represent the real world. Neural networks are intended to emulate the pattern-recognition and parallel-processing capabilities of the human brain and are taught rather than programmed. The future may lie in a combination of the recognition ability of the neural network and the rationalization capability of the expert system. In the second part of this paper, examples are given of applications of AI in stand-alone systems for knowledge engineering and medical diagnosis and in embedded systems for failure detection, image analysis, user interfacing, natural language processing, robotics and machine learning, as related to clinical laboratories. It is concluded that AI constitutes a collective form of intellectual property and that there is a need for better documentation, evaluation and regulation of the systems already being used widely in clinical laboratories.

Artificial Intelligence↗
PubMed1995

Use of artificial intelligence in analytical systems for the clinical laboratory.

OBJECTIVE: To consider the role of software in system operation, control and automation, and attempts to define intelligence. METHODS AND RESULTS: Artificial intelligence (Al) is characterized by its ability to deal with incomplete and imprecise information and to accumulate knowledge. Expert systems, building on standard computing techniques, depend heavily on the domain experts and knowledge engineers that have programmed them to represent the real world. Neural networks are intended to emulate the pattern-recognition and parallel processing capabilities of the human brain and are taught rather than programmed. The future may lie in a combination of the recognition ability of the neural network and the rationalization capability of the expert system. In the second part of this paper, examples are given of applications of Al in stand-alone systems for knowledge engineering and medical diagnosis and in embedded systems for failure detection, image analysis, user interfacing, natural language processing, robotics and machine learning, as related to clinical laboratories. CONCLUSION: Al constitutes a collective form of intellectual property, and that there is a need for better documentation, evaluation and regulation of the systems already being used widely in clinical laboratories.

Artificial Intelligence↗
PubMed2004

Textmining in support of knowledge discovery for vaccine development.

Complete genome data of infectious microorganisms permit systematic computational sequence-based predictions and experimental testing of candidate vaccine epitopes. Both, predictions and the interpretation of experiments rely on existing information in the literature which is mostly manually extracted and curated. The growing amount of data and literature information has created a major bottleneck for the interpretation of results and maintenance of curated databases. The lack of suitable free-text information extraction, processing, and reporting tools prompted us to develop a knowledge discovery support system that enhances the understanding of immune response and vaccine development. The current prototype system, Gene expression/epitpopes/protein interaction (GEpi), focuses on molecular functions of HIV-infected T-cells and HIV epitope information, using textmining, and interrelation of biomolecular data from domain-specific databases with MEDLINE abstract-inferred information. Results showed that extraction and processing of molecular interaction, disease associations, and gene ontology-derived functional information generate intuitive knowledge reports that aid the interpretation of host-pathogen interaction. In contrast, epitope (word and sequence) information in MEDLINE abstracts is surprisingly sparse and often lacks necessary context information, such as HLA-restriction. Since the majority of epitope information is found in tables, figures, and legends of full-text articles, its extraction may not require sophisticated natural language processing techniques. Support of vaccine development through textmining requires therefore the timely development of domain-specific extraction rules for full-text articles, and a knowledge model for epitope-related information.

Animals↗
PubMed2026

Identification of Risk Factors for Acral Melanoma in US Veterans.

IMPORTANCE: Acral melanoma (AM), localized to the palms, soles, and nail units, is a unique melanoma subtype less associated with UV radiation. Few studies have evaluated AM risk factors in a population of US veterans. OBJECTIVE: To identify AM risk factors in US veterans. DESIGN, SETTING, AND PARTICIPANTS: Nested case-control study (2000-2024) in the Veterans Affairs (VA) health care system. Individuals with AM were identified using the VA Cancer Registry and a validated natural language processing pipeline applied to pathology reports. Each AM case was matched to 4 nonacral cutaneous melanoma (CM) controls and 4 controls with no melanoma diagnoses at any time by diagnosis year and outpatient visit frequency. Controls with acral, mucosal, or ocular melanoma diagnoses at any time were excluded. Participants were veterans with histologically confirmed AM, nonacral CM controls, and controls with no melanoma diagnoses at any time. EXPOSURE: Age, sex, race and ethnicity, rurality, region, military branch, comorbidities (National Cancer Institute Comorbidity Index), smoking status, unhealthy alcohol use as measured by the Alcohol Use Disorders Identification Test-Consumption, body mass index, Agent Orange exposure (AOE), prior photosensitizing medications, nevi, keratinocyte carcinoma (KC), actinic keratosis (AK), and number of dermatology visits in the 2 years before diagnosis. MAIN OUTCOMES AND MEASURES: Adjusted odds ratios (AORs) comparing AM with controls using conditional logistic regression. Secondary outcomes included analyses limited to Vietnam Era veterans and AM localized to palmoplantar and subungual sites. RESULTS: In total, 1292 individuals with AM (median age, 70.13 [IQR, 61.87-78.66] years; 1215 [94.0%] male) were matched to 5168 controls without melanoma (median age, 73.97 [IQR, 65.53-82.08] years; 5044 [97.6%] male), and 1286 individuals with AM (median age, 70.13 [IQR, 61.97-78.67] years; 1210 [94.1%] male) were matched to 5144 CM controls (median age, 74.58 [IQR, 66.86-82.05] years; 5068 [98.5%] male); 6 individuals with AM were excluded from AM vs CM analyses due to lack of matches. AOE was significantly associated with higher odds of AM vs CM (AOR, 1.31; 95% CI, 1.06-1.62) and vs controls without melanoma (AOR, 1.27; 95% CI, 1.04-1.56). Current smoking was associated with lower odds of AM (vs CM: AOR, 0.65; 95% CI, 0.52-0.81; vs controls without melanoma: AOR, 0.50; 95% CI, 0.40-0.62). Prior KC and AK were associated with higher odds vs controls without melanoma but lower odds vs CM. Prior nevus was associated with higher odds of AM vs controls without melanoma. CONCLUSIONS AND RELEVANCE: Results of this study suggest that several factors were associated with AM in veterans and a need for continued investigation of AM as a distinct entity from CM and may inform future evaluations of the associations between AOE and AM in veteran populations.

Aged↗
PubMed1993

Integrating knowledge-based systems and databases.

In recent years, there has been an explosion of interest among the computing community in the field of artificial intelligence, particularly in the areas of natural language processing and knowledge-based systems (KBS). The medical domain has seen the development of hundreds of KBSs and there is substantial evidence to show that the application of a knowledge-based approach to decision support can go a long way towards overcoming the information overload experienced by many clinicians today. Yet many of these medical KBSs are still at the prototype stage and are mainly confined to research laboratories. There are many reasons for this apparently slow take-up of the technology, but one of the most significant is the lack of integration into the regular routine information processing of the organisation, in particular the database processing. This paper discusses the benefits of such integration and methods for achieving it in the context of general trends in information systems. Database technology provides efficient and secure management of large amounts of data in a multi-user, multi-application environment. Knowledge-based technology, on the other hand, provides mechanisms for building intelligent systems. Thus, for example, given a set of facts about a domain (symptoms, laboratory test results, etc.) together with a set of rules which apply to that domain (e.g. 'if TT4 > 150 nmol/l then suspect hyperthyroidism'), a KBS can deduce new information about that domain automatically. The effective integration of these two technologies is seen as a means of achieving the intelligent information systems of the future. There are three basic approaches to integrating KBSs and databases. The first is to start with the KBS and incorporate data management functions. Alternatively, intelligence from the KBS can be incorporated into the database. Finally, the two systems can be allowed to co-exist as independent systems which can talk to each other by means of standard interfaces. There are many advantages to this last approach since it offers much more flexibility and extensibility and is consistent with the general trend in computing towards open systems.

Artificial Intelligence↗
PubMed1995

Developing interactive computer-based simulations: an object-oriented development methodology enhances computer-assisted instruction.

The purpose of this research was to investigate the application of object-oriented technology and AI techniques to enhance development of computer-based training simulations. Towards that end, a comprehensive computer-assisted instructional unit was developed to teach the skills and concepts of window-based applications, the OS/2 desktop, and the use of a patient care information system. By taking advantage of sophisticated computer graphics for the visual representation of objects and the behavioral modeling capabilities of the object-oriented language, domain knowledge modeling and human-computer interactions were implemented without complex natural language processing techniques. The results of this research indicate that nurses and physicians are able to learn the basic skills and concepts of computer systems and how to query for patient information. The new methodology described for building these computer-assisted instructional simulations significantly eased the training and teaching of large numbers of nurses and physicians and simplified their transition to a complex, computer-based hospital information system environment.

Computer Graphics↗
PubMed1992

Semantic commitments as a mode of non-programmable computation in the brain.

The natural language processor in the brain can cope with non-programmable computation. The average number of different lexical meanings per word serves as a quantitative figure in terms of which the extent of being non-programmable can be evaluated. The possible maximum average number of different lexical meanings per word that the brain of the subject reading the text can cope with while comprehending the context is found to be 3.3 with its standard deviation 0.15, beyond which the brain can no more succeed in comprehending the context. In contrast, the maximum average number of different lexical meanings per word that would make lexical disambiguation programmable is e = 2.718. Natural language processing in the brain is non-programmable in the sense that the manageable average number of different meanings per word is greater than e, but does not exceed roughly 3.3.

Brain↗
PubMed2005

Assisting medical annotation in Swiss-Prot using statistical classifiers.

Bio-medical knowledge bases are valuable resources for the research community. Original scientific publications are the main source used to annotate them. Medical annotation in Swiss-Prot is specifically targeted at finding and extracting data about human genetic diseases and polymorphisms. Curators have to scan through hundreds of publications to select the relevant ones. This workload can be greatly reduced by using bio-text mining techniques. Using a combination of natural language processing (NLP) techniques and statistical classifiers, we achieve recall points of up to 84% on the potentially interesting documents and a precision of more than 96% in detecting irrelevant documents. Careful analysis of the document pre-processing chain allows us to measure the impact of some steps on the overall result, as well as test different classifier configurations. The best combination was used to create a prototype of a search and classification tool that is currently tested by the database curators.

Databases, Protein↗
PubMedDate not supplied

Towards linking patients and clinical information: detecting UMLS concepts in e-mail.

The purpose of this project is to explore the feasibility of detecting terms within the electronic messages of patients that could be used to effectively search electronic knowledge resources and bring health information resources into the hands of patients. Our team is exploring the application of the natural language processing (NLP) tools built within the Lister Hill Center at the National Library of Medicine (NLM) to the challenge of detecting relevant concepts from the Unified Medical Language System (UMLS) within the free text of lay people's electronic messages (e-mail). We obtained a sample of electronic messages sent by patients participating in a randomized field evaluation of an internet-based home care support service to the project nurse, and we subjected elements of these messages to a series of analyses using several vocabularies from the UMLS Metathesaurus and the selected NLP tools. The nursing vocabularies provide an excellent starting point for this exercise because their domain encompasses patient's responses to health challenges. In successive runs we augmented six nursing vocabularies (NANDA Nursing Diagnosis, Nursing Interventions Classification, Nursing Outcomes Classification, Home Health Classification, Omaha System, and the Patient Care Data Set) with selected sets of clinical terminologies (International Classification of Primary Care; International Classification of Primary Care- American English; Micromedex DRUGDEX; National Drug Data File; Thesaurus of Psychological Terms; WHO Adverse Drug Reaction Terminology) and then additionally with either Medical Subject Heading (MeSH) or SNOMED International terms. The best performance was obtained when the nursing vocabularies were complemented with selected clinical terminologies. These findings have implications not only for facilitating lay people's access to electronic knowledge resources but may also be of assistance in developing new tools to aid in linking free text (e.g., clinical notes) to lexically complex knowledge resources such as those emerging from the Human Genome Project.

Artificial Intelligence↗
PubMed2005

Beyond emotion archetypes: databases for emotion modelling using neural networks.

There has been rapid development in conceptions of the kind of database that is needed for emotion research. Familiar archetypes are still influential, but the state of the art has moved beyond them. There is concern to capture emotion as it occurs in action and interaction ('pervasive emotion') as well as in short episodes dominated by emotion, and therefore in a range of contexts, which shape the way it is expressed. Context links to modality-different contexts favour different modalities. The strategy of using acted data is not suited to those aims, and has been supplemented by work on both fully natural emotion and emotion induced by various technique that allow more controlled records. Applications for that kind of work go far beyond the 'trouble shooting' that has been the focus for application: 'really natural language processing' is a key goal. The descriptions included in such a database ideally cover quality, emotional content, emotion-related signals and signs, and context. Several schemes are emerging as candidates for describing pervasive emotion. The major contemporary databases are listed, emphasising those which are naturalistic or induced, multimodal, and influential.

Computer Simulation↗