PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Natural Language Processing”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 1,117 records · Page 62Linked to original sources
PubMed2025

AskBeacon-performing genomic data exchange and analytics with natural language.

MOTIVATION: Enabling clinicians and researchers to directly interact with global genomic data resources by removing technological barriers is vital for medical genomics. AskBeacon enables large language models (LLMs) to be applied to securely shared cohorts via the Global Alliance for Genomics and Health Beacon protocol. By simply "asking" Beacon, actionable insights can be gained, analyzed, and made publication-ready. RESULTS: In the Parkinson's Progression Markers Initiative (PPMI), we use natural language to ask whether the sex-differences observed in Parkinson's disease are due to X-linked or autosomal markers. AskBeacon returns a publication-ready visualization showing that for PPMI the autosomal marker occurred 1.4 times more often in males with Parkinson's disease than females, compared to no differences for the X-linked marker. We evaluate commercial and open-weight LLM models, as well as different architectures to identify the best strategy for translating research questions to Beacon queries. AskBeacon implements extensive safety guardrails to ensure that genomic data is not exposed to the LLM directly, and that generated code for data extraction, analysis and visualization process is sanitized and hallucination resistant, so data cannot be leaked or falsified. AVAILABILITY AND IMPLEMENTATION: AskBeacon is available at https://github.com/aehrc/AskBeacon.

Genomics↗
PubMed2002

Motion events in language and cognition.

This study investigated whether different lexicalization patterns of motion events in English and Spanish predict how speakers of these languages perform in non-linguistic tasks. Using 36 motion events, we compared English and Spanish speakers' linguistic descriptions to their performance on two non-linguistic tasks: recognition memory and similarity judgments. We investigated the effect of language processing on non-linguistic performance by varying the nature of the encoding before testing for recognition and similarity. Participants encoded the events while describing them verbally or not. No effect of language was obtained in the recognition memory task after either linguistic or non-linguistic encoding and in the similarity task after non-linguistic encoding. We did find a linguistic effect in the similarity task after verbal encoding, an effect that conformed to language-specific patterns. Linguistic descriptions directed attention to certain aspects of the events later used to make a non-linguistic judgment. This suggests that linguistic and non-linguistic performance are dissociable, but language-specific regularities made available in the experimental context may mediate the speaker's performance in specific tasks.

Adult↗
PubMed1998

The minimal standard terminology for digestive endoscopy: introduction to structured reporting.

The wider use of computers for the management of endoscopic data and the use of electronic endoscopes for the production of high quality endoscopic images has made the standardization of terminology and images formats necessary in digestive endoscopy reports. The European Society for Gastrointestinal Endoscopy and the American Society for Gastrointestinal Endoscopy have combined their efforts to propose a Minimal Standard Terminology for Computerized Databases in Endoscopy. This terminology is based on the following principles: no term describing findings less frequent than 1%, of the daily practice, and no term based on subjective impressions. The Minimal Standard Terminology has been developed according to the natural process of constructing an endoscopic report in natural language and deals with the following: reasons for performing the examination, endoscopic findings, endoscopic diagnosis, additional therapeutic and diagnosis procedures (biopsies, etc.). It is subdivided according to the main organs examined with an endoscopy. Until now, the Minimal Standard Terminology was tested in many centers and was shown to accurately cover 95% of routine examinations for the upper gastrointestinal tract, colonoscopy and cholangio-pancreatography. It is currently being tested in an a prospective way in several centers in Europe (with a grant from the European Commission DGXIII-C4) and in the USA (with grant from the AHDHF).

Endoscopy, Digestive System↗
PubMed1981

Correspondences between biomathematical and causal models for clinical decision making.

Due to incompleteness and other uncertainties, biomathematical models are unsuitable for direct use in clinical decision making. In this research work, we develop a procedure to derive clinical decision-making causal models from mathematical representation. The process involves obtaining the determination ordering for an incompletely specified system of equations. The concept of determination ordering is extended to dynamic systems of equations, in order to derive clinically usable models. The procedure to transform biomathematical models into causal representation has been machine-implemented for fluid flow models of the eye. A case-structured natural language system (CHRONOS) has been developed to accept, process, and store causal as well as biomathematical models. The system obtains the determination ordering for the biomathematical models and stores their causal representation. The system has the capability to compare the causal models. The deductive capabilities of the system can be used by a clinician to consult the diagnostic reasonings of the biomathematical and causal models.

Aqueous Humor↗
PubMed2000

The role of the human thalamus in language and memory: evidence from electrophysiological studies.

The data reviewed here indicate that electrical stimulation of the dominant ventrolateral thalamus can produce deficits in language processing that are not seen after similar stimulation of the nondominant ventrolateral thalamus. The nature of the language deficit produced varies, depending upon the rostrocaudal location of the stimulation site. Stimulation of the anterior left ventrolateral thalamus in right-handed patients resulted in production of a repeated erroneous word, stimulation of the medial ventrolateral thalamus evoked perseveration, and stimulation of the posterior ventrolateral thalamus and anterior pulvinar resulted in misnaming and omissions. Additional studies have examined the effect of electrical thalamic stimulation on verbal and nonverbal short-term memory. Left (but not right) ventrolateral thalamic stimulation during verbal memory input greatly decreased subsequent recall errors, while stimulation during verbal memory retrieval increased recall errors. This finding contrasted with those obtained from studies on nonverbal memory, in which right ventrolateral stimulation during memory input decreased recall errors, while left thalamic stimulation at the same stage increased recall errors. Left pulvinar stimulation disrupted verbal memory processing, while right pulvinar stimulation disrupted nonverbal memory processing. Limited evidence suggests that the effects of thalamic electrical stimulation on verbal memory may persist for several days after the stimulation has ended. The lateralization of thalamic functions also affects the motoric aspects of speech production. Left (but not right) ventrolateral thalamic stimulation disrupted speech articulation and increased the expiratory phase of respiration. The fact that these motor effects were evoked from the same general area of the thalamus that produced the language deficits discussed above raises the possibility that the thalamus is involved in coordinating the cognitive and motoric aspects of language production. A model of thalamic function is discussed in which defined regions of the thalamus operate as a "specific alerting response," increasing the input to memory of category-specific material while simultaneously inhibiting retrieval from memory.

Electrophysiology↗
PubMed2006

Nature and nurture in language acquisition: anatomical and functional brain-imaging studies in infants.

Speech processing in adults relies on precise and specialized networks, located primarily in the left hemisphere. Behavioral studies in infants indicate that a considerable amount of language learning already takes place in the first year of life in the domains of phonology, prosody and word segmentation. Thanks to neuroimaging, we can move beyond behavioral methods and examine how the infant brain processes verbal stimuli before learning. These studies reveal a structural and functional organization close to what is described in adults and suggest a strong bias for speech processing in these regions that might guide infants as they discover the properties of their native language, although no evidence can be provided as yet for speech specificity of such networks. This review is part of the INMED/TINS special issue "Nature and nurture in brain development and neurological disorders", based on presentations at the annual INMED/TINS symposium (http://inmednet.com/).

Animals↗
PubMed1995

Linguistic processes in the two cerebral hemispheres: implications for modularity vs interactionism.

Three experiments are reported on lexical decision to target stimuli presented to the right or left visual field (RVF, LVF) following a variety of priming stimuli, words, incomplete sentences, and scrambled sentences. Lexical decision performance is always superior for stimuli presented to the RVF. Primes always facilitate the discrimination of words from nonword target stimuli presented to either visual field. However, when the prime is a sentence which is completed syntactically and semantically by a target word (normal, congruent sentence), the facilitation for RVF presented targets is significantly greater than for LVF targets. When the prime is either: (1) a single word, (2) a nonstructured (scrambled) sentence, or (3) a noncongruent-related sentence, the difference in facilitation between RVF and LVF presented targets is much smaller. These data are discussed with respect to (1) the nature of priming by sentences versus words, (2) language processing by the two hemispheres, and (3) modularity versus interactionism in language processing.

Adult↗
PubMed2000

The application of computerized content analysis of natural language in psychotherapy research now and in the future.

For many years the author and his colleagues have been involved in studying the roots and processes of the conveyance of semantic messages via spoken language and verbal texts. After establishing that reliable and valid measurements of highly relevant neuropsychiatric categories, such as anxiety, depression, and cognitive impairment, can be made by identifying and counting the occurrence per grammatical clause of language content and form categories typifying specific content-analysis scales, the research focus has turned towards computerizing this process of content analysis. This report summarizes the achievements and applications of the current empirical status of this method of computerized content analysis of natural language to psychotherapy research, and it speculates on possible future applications in the millennium.

Computing Methodologies↗
PubMed1997

Deafness, language skills, and rehearsal: a model for the development of a memory strategy.

We review a series of studies that evaluate the role of developing language skills as a prerequisite to spontaneous rehearsal use in deaf populations. We propose a theoretical model that summarizes the contribution of language skills by highlighting the interrelations among age, language proficiency, and automatized language skills. In an initial test of the model, an index of deaf children's language experience was found to be an almost complete mediator of strategy use. Increasing language proficiency, therefore, was implicated as a critical variable in predicting children's spontaneous rehearsal use, minimizing any direct contribution from age per se. In a more direct assessment of the link between general language proficiency and rehearsal use, pragmatic language skills (as measured by the Language Proficiency Profile: LPP-I) were found to be a nearly complete mediator of rehearsal use, with the remaining contributions of age and language experience being nonsignificant. Language proficiency, therefore, was identified as a strong and necessary prerequisite for rehearsal to be used spontaneously as a memory strategy. The additional hypothesis that the automatization of these general language skills, measured by a rapid automatized naming task (RAN), contributes to spontaneous rehearsal was also evaluated. Automatized language emerged as a partial mediator of the language proficiency → rehearsal use relation but additional language-processing variables were implicated. We discuss these findings as they relate to issues around the nature of language proficiency and the identification of those automatized language skills involved in rehearsal.

Journal Article↗
PubMed2000

Speech-like cerebral activity in profoundly deaf people processing signed languages: implications for the neural basis of human language.

For more than a century we have understood that our brain's left hemisphere is the primary site for processing language, yet why this is so has remained more elusive. Using positron emission tomography, we report cerebral blood flow activity in profoundly deaf signers processing specific aspects of sign language in key brain sites widely assumed to be unimodal speech or sound processing areas: the left inferior frontal cortex when signers produced meaningful signs, and the planum temporale bilaterally when they viewed signs or meaningless parts of signs (sign-phonetic and syllabic units). Contrary to prevailing wisdom, the planum temporale may not be exclusively dedicated to processing speech sounds, but may be specialized for processing more abstract properties essential to language that can engage multiple modalities. We hypothesize that the neural tissue involved in language processing may not be prespecified exclusively by sensory modality (such as sound) but may entail polymodal neural tissue that has evolved unique sensitivity to aspects of the patterning of natural language. Such neural specialization for aspects of language patterning appears to be neurally unmodifiable in so far as languages with radically different sensory modalities such as speech and sign are processed at similar brain sites, while, at the same time, the neural pathways for expressing and perceiving natural language appear to be neurally highly modifiable.

Cerebrovascular Circulation↗
PubMed1989

Final consonant repetition: a linguistic perspective.

A case of final consonant repetition in the speech of a normal child is presented. It is argued that this production pattern is the result of a convergence of phonological factors, including phonetic constraints and cognitively based rule generation, rather than a pathologic process. Final consonant repetition is discussed relative to natural languages and other cases of rule generation in normal children and relative to earlier cases examining this pattern in terms of models of dysfluency. Additionally, the clinical ramifications of the findings are discussed.

Child, Preschool↗
PubMed1978

The interactional process in preadolescent friendships.

The study of friendship in children has long been a neglected area of human development. As Hartup (1975) pointed out, there is a paucity of data both with respect to the nature of the interactional process between friends and the language children use in conceptualizing friendship. The purpose of the present investigation was to examine the interactional process in preadolescent friendships within the framework of Harry Stack Sullivan's social development theory.

Child↗
PubMed1989

Expert systems in medicine.

The emergence of the artificial intelligence (AI) in computer technology and its application in the medical field enables the researchers to carry out such intelligent activities like image processing, medical reasoning systems, clinical decision supporting and natural language understanding, etc. A gastroenterological expert system application is briefly demonstrated in this paper. Similar expert systems can be seen to be useful in the research of gastrointestinal cytoprotection, including the plan of different compounds with cytoprotective effect, experimental and clinical medical research.

Decision Making, Computer-Assisted↗
PubMedDate not supplied

RGSS-ID: an approach to new radiologic reporting system.

RGSS-ID is a developmental computer system that applies artificial intelligence (AI) methods to a reporting system. The representation scheme called Generalized Finding Representation (GFR) is proposed to bridge the gap between natural language expressions in the radiology report and AI methods. The entry process of RGSS-ID is made mainly by selecting items; our system allows a radiologist to compose a sentence which can be completely parsed by the computer. Further RGSS-ID encodes findings into the expression corresponding to GFR, and stores this expression into the knowledge data base. The final printed report is made in the natural language.

Artificial Intelligence↗
PubMed2004

On the neurobiological investigation of language understanding in context.

There are two significant problems in using functional neuroimaging methods to study language. Improving the state of functional brain imaging will depend on understanding how the dependent measure of brain imaging differs from behavioral dependent measures (the "dependent measure problem") and how the activation of the motor system may be confounded with non-motor aspects of processing in certain experimental designs (the "motor output problem"). To address these problems, it may be necessary to shift the focus of language research from the study of linguistic competence to the understanding of language use. This will require investigations of language processing in full multi-modal and environmental context, monitoring of natural behaviors, novel experimental design, and network-based analysis. Such a combined naturalistic approach could lead to tremendous new insights into language and the brain.

Brain Mapping↗
PubMed1999

Adaptation and novelty: teleological explanations in evolutionary biology.

Knives, birds' wings, and mountain slopes are used for certain purposes: cutting, flying, and climbing. A bird's wings have in common with knives that they have been 'designed' for the purpose they serve, which purpose accounts for their existence, whereas mountain slopes have come about by geological processes independently of their uses for climbing. A bird's wings differ from a knife in that they have not been designed or produced by any conscious agent; rather, the wings, like the slopes, are outcomes of natural processes without any intentional causation. Evolutionary biologists use teleological language and teleological explanations. I propose that this use is appropriate, because teleological explanations are hypotheses that can be subject to empirical testing. The distinctiveness of teleological hypotheses is that they account for the existence of a feature in terms of the function it serves; for example, wings have evolved and persist because flying is beneficial to birds by increasing their chances of surviving and reproducing. Features of organisms that are explained with teleological hypotheses include structures, such as wings; processes, such as development from egg to adult; and behaviours, such as nest building. A proximate explanation of these features is the function they serve; an ultimate explanation that they all share is their contribution to the reproductive fitness of the organisms. I distinguish several kinds of teleological explanations, such as natural and artificial, as well as bounded and unbounded, some of which but not others apply to biological explanations.

Adaptation, Biological↗
PubMed1991

Selective impairment of thematic role assignment in sentence processing.

We report the performance of a brain-damaged subject showing a particularly pure dissociation between impairment in processing thematic roles and spared ability to process the morphological structure of sentences. The thematic role processing impairment was observed in both comprehension and production of active and passive reversible sentences, although it was more severe for the latter sentence type. This pattern of performance poses interesting challenges for current conceptions of the nature of language breakdown in aphasia and for models of normal sentence processing.

Aphasia, Wernicke↗