SEARCH · Search PubMed

Results for “Large language model”

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.

SourceResearch connectionFrom yearThrough year

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

At least 217 records · Page 12Linked to original sources

PubMed1997

Simulators in clinical surgery.

Simulators are no replacement for patients in surgical learning. Live patients are required for teaching clinical signs and skills. Large numbers of students, a relative lack of motivation, a decreasing number of common cases, unwilling patients, differences in language, etc., make clinical teaching in India a bitter problem. Because patient-related problems are important, surgical training using models can help students to gain effective control over surgical signs and skills.

Education, Medical, Undergraduate↗

PubMed2006

Why is that? Structural prediction and ambiguity resolution in a very large corpus of English sentences.

Previous psycholinguistic research has shown that a variety of contextual factors can influence the interpretation of syntactically ambiguous structures, but psycholinguistic experimentation inherently does not allow for the investigation of the role that these factors play in natural (uncontrolled) language use. We use regression modeling in conjunction with data from the British National Corpus to measure the amount and specificity of the information available for disambiguation in natural language use. We examine the Direct Object/Sentential Complement ambiguity and the closely related issue of complementizer use in sentential complements, and find that both ambiguity resolution and complementizer use can be predicted from contextual information.

Cognition↗

PubMed2006

Terminology model discovery using natural language processing and visualization techniques.

Medical terminologies are important for unambiguous encoding and exchange of clinical information. The traditional manual method of developing terminology models is time-consuming and limited in the number of phrases that a human developer can examine. In this paper, we present an automated method for developing medical terminology models based on natural language processing (NLP) and information visualization techniques. Surgical pathology reports were selected as the testing corpus for developing a pathology procedure terminology model. The use of a general NLP processor for the medical domain, MedLEE, provides an automated method for acquiring semantic structures from a free text corpus and sheds light on a new high-throughput method of medical terminology model development. The use of an information visualization technique supports the summarization and visualization of the large quantity of semantic structures generated from medical documents. We believe that a general method based on NLP and information visualization will facilitate the modeling of medical terminologies.

Automation↗

PubMed1987

Trends in computational tools for biomagnetism: from procedural codes to intelligent scientific models.

The nature of the available computing tools strongly influences modern scientific investigations. The sources of well known problems associated with the use of procedural computer languages are traced and their consequences investigated. The likely impact of recent quantitative and qualitative advances in software and hardware is examined with emphasis on its relevance to the biomagnetic inverse problem. Gradual changes in the use of computers, some already employed in a recent study of a specific biomagnetic inverse problem, are outlined which take into account the large investment in conventional codes.

Animals↗

PubMed2026

Fast, accurate construction of multiple sequence alignments from protein language embeddings.

Multiple sequence alignment (MSA) is a foundational task in computational biology, underpinning protein structure prediction, evolutionary analysis, and domain annotation. Traditional MSA algorithms rely on pairwise amino acid substitution matrices derived from conserved protein families. While effective for aligning closely related sequences, these scoring schemes struggle in the low-identity "twilight zone." Here, we present a new approach for constructing MSAs leveraging amino acid embeddings generated by protein language models (PLMs), which capture rich evolutionary and contextual information from massive and diverse sequence datasets. We introduce a windowed reciprocal-weighted embedding similarity metric that is surprisingly effective in identifying corresponding amino acids across sequences. Building on this metric, we develop ARIES (Alignment via RecIprocal Embedding Similarity), an algorithm that constructs a PLM-generated template embedding and aligns each sequence to this template via dynamic time warping in order to build a global MSA. Across diverse benchmark datasets, ARIES achieves higher accuracies than existing state-of-the-art approaches, especially in low-identity regimes where traditional methods degrade, while scaling almost linearly with the number of sequences to be aligned. Together, these results provide the first large-scale demonstration of the power of PLMs for accurate and scalable MSA construction across protein families of varying sizes and levels of similarity, highlighting the potential of PLMs to transform comparative sequence analysis.

Deep Learning↗

PubMed2001

Age, consumer direction, and outcomes of supportive services at home.

PURPOSE: Supportive services at home are essential for older people with severe chronic impairments. Newer "consumer-directed" models of organizing home-based services rely heavily on service recipients rather than home care agencies to arrange and direct care at home. This study examined differences in service experience and outcomes between recipients over and under age 65 who direct their own services in one large Medicaid program. DESIGN AND METHODS: A random sample of 1,095 recipients of In-Home Supportive Services in California was selected and interviewed by telephone. Interviews were conducted in English, Spanish, and three Asian languages; those with severe cognitive impairment were excluded from the study. RESULTS: Findings indicate that although younger recipients embrace self-direction more enthusiastically than older ones, age differences are small on a majority of service outcomes. On average, older users embrace this model and manage within it much like younger users. Some differences emerge between the young-old (65-74) and old-old (75+), but these are neither consistent nor determinative. IMPLICATIONS: Old age is far from an inevitable barrier to self-direction. As with other age groups, there are opportunities and obstacles to be addressed as this newer approach to home care is disseminated.

Activities of Daily Living↗

PubMed2004

Autism spectrum disorder in fragile X syndrome: communication, social interaction, and specific behaviors.

The present study extends our previous work on social behavior impairment in young males with fragile X syndrome (FraX). Specifically, we evaluated whether the autistic phenomenon in FraX is expressed as a range of behavioral impairments as in idiopathic autism (Aut). We also examined whether there are behaviors, identified as items of the Autism Diagnostic Interview-Revised (ADI-R), that in FraX predispose to or differentiate subjects with autism spectrum disorder (ASD) diagnosis. Finally, regression models were utilized to test the relative contribution of reduced communication and socialization skills to ADI-R scores and diagnoses. A cohort of 56 boys (3-8 years) with FraX was examined in terms of scores on measures of cognition (IQ was a co-variate in most analyses.), autistic behavior, problem/aberrant behavior, adaptive behavior, and language development. We found that, indeed, in terms of problem behavior and adaptive skills, there is a range of severity from FraX + Aut to FraX + PDD (Pervasive Developmental Disorder) to FraX + none. ADI-R items representing "Play" types of interaction appear to be "susceptibility" factors since they were abnormal across the FraX cohort. Integrated regression models demonstrated that items reflecting complex social interaction differentiated the FraX + ASD (Aut + PDD) subgroup from the rest of the FraX cohort, while abnormalities in basic verbal and non-verbal communication distinguished the most severely affected boys with FraX + Aut from the milder FraX + PDD cohort. Models incorporating language, adaptive communication, and adaptive socialization skills revealed that socialization was not only the main influence on scores but also a predictor of ASD diagnosis. Altogether, our findings demonstrate that the diagnosis of ASD in FraX reflects, to a large extent, an impairment in social interaction that is expressed with variable severity in young males with FraX.

Adaptation, Psychological↗

PubMed2004

A case for consideration of cultural diversity in heart failure management--Part 1: Rationale for the DISCOVER Study.

Heart failure is a condition increasing in prevalence and responsible for high health care utilization, morbidity and mortality. Randomised controlled trials of nurse-coordinated interventions have determined self-care and the incorporation of the patient and their family in care planning as critical elements of service delivery. Coping with a chronic illness, such as heart failure, forces the individual to adjust to changed physical, social and emotional functioning and to modify their lifestyle accordingly. Clinicians increasingly use models of care that focus care delivery on the community setting. In order to develop strategies to assist patients and their families with self-care it is important that clinicians understand the health-care seeking behaviours of all individuals targeted in the community. Australia is a culturally diverse nation, yet evaluations of models of care have been undertaken largely in individuals from predominately Anglo-Celtic origins. The end result of this approach is failure to understand the full range of diverse perspectives that individuals hold that can have an impact on self-care behaviours. Consideration of cultural diversity should extend beyond language to a broader appreciation of cultural values, health seeking beliefs and engagement of culturally unique communities. The 'Understanding the cultural experiences of individuals with chronic heart failure (CHF) in South East Health (DISCOVER) Study' seeks to uncover information on the health patterns, information needs and the adjustment process for overseas-born individuals with heart failure. Such information will assist clinicians to tailor health care service delivery and ensure the delivery of appropriate, quality care. This manuscript provides the background, rationale and methods for this study.

Adaptation, Psychological↗

PubMed2004

Quantile regression via vector generalized additive models.

One of the most popular methods for quantile regression is the LMS method of Cole and Green. The method naturally falls within a penalized likelihood framework, and consequently allows for considerable flexible because all three parameters may be modelled by cubic smoothing splines. The model is also very understandable: for a given value of the covariate, the LMS method applies a Box-Cox transformation to the response in order to transform it to standard normality; to obtain the quantiles, an inverse Box-Cox transformation is applied to the quantiles of the standard normal distribution. The purposes of this article are three-fold. Firstly, LMS quantile regression is presented within the framework of the class of vector generalized additive models. This confers a number of advantages such as a unifying theory and estimation process. Secondly, a new LMS method based on the Yeo-Johnson transformation is proposed, which has the advantage that the response is not restricted to be positive. Lastly, this paper describes a software implementation of three LMS quantile regression methods in the S language. This includes the LMS-Yeo-Johnson method, which is estimated efficiently by a new numerical integration scheme. The LMS-Yeo-Johnson method is illustrated by way of a large cross-sectional data set from a New Zealand working population.

Adolescent↗

PubMed2006

Finding regions of significance in SELDI measurements for identifying protein biomarkers.

MOTIVATION: There is a well-recognized potential of protein expression profiling using the surface-enhanced laser desorption and ionization technology for discovering biomarkers that can be applied in clinical diagnosis, prognosis and therapy prediction. The pre-processing of the raw data, however, is still problematic. METHODS: We focus on the peak detection step, where the standard method is marked by poor specificity. Currently, scientists need to inspect individual spectra visually and laboriously in order to verify that spectral peaks identified by the standard method are real. Motivated by this multi-spectral process, we investigate an analytical approach-called RS for 'regions of significance'-that reduces the data to a single spectrum of F-statistics capturing significant variability between spectra. To account for multiple testing, we use a false discovery rate criterion for identifying potentially interesting proteins. RESULTS: We show that RS has better operating characteristics than several existing methods and demonstrate routine applications on a number of large datasets.

Algorithms↗

PubMed1998

Modeling global and focal hyperarticulation during human-computer error resolution.

When resolving errors with interactive systems, people sometimes hyperarticulate--or adopt a clarified style of speech that has been associated with increased recognition errors. The primary goals of the present study were: (1) to provide a comprehensive analysis of acoustic, prosodic, and phonological adaptations to speech during human-computer error resolution after different types of recognition error; and (2) to examine changes in speech during both global and focal utterance repairs. A semi-automatic simulation method with a novel error-generation capability was used to compare speech immediately before and after system recognition errors. Matched original-repeat utterance pairs then were analyzed for type and magnitude of linguistic adaption during global and focal repairs. Results indicated that the primary hyperarticulate changes in speech following all error types were durational, with increases in number and length of pauses most noteworthy. Speech also was adapted toward a more deliberate and hyperclear articulatory style. During focal error repairs, large durational effects functioned together with pitch and amplitude to provide selective prominence marking of the repair region. These results corroborate and generalize the computer-elicited hyperarticulate adaptation model (CHAM). Implications are discussed for improved error handling in next-generation spoken language and multimodal systems.

Computers↗

PubMed2004

Monitoring amiodarone's toxicities: recommendations, evidence, and clinical practice.

OBJECTIVES: We sought to develop an explicit evidence-based model of medication monitoring and to evaluate monitoring practices and adverse drug events in patients taking amiodarone at one institution. METHODS: We searched MEDLINE (1966 through 2000) for English-language publications providing specific monitoring recommendations for amiodarone. A cross-sectional retrospective chart review of 99 outpatients receiving amiodarone therapy between Jan 1, 2000, and Jan 1, 2001, at a large tertiary-care hospital was performed to assess monitoring practices. Adverse drug events were identified by use of structured implicit reviews. The main outcome measure was the proportion of patients receiving the monitoring recommended in the literature and having amiodarone-related adverse drug events. RESULTS: Forty-three articles were identified that provided specific monitoring recommendations, although no studies were found that compared the outcomes of patients managed with different monitoring regimens. Overall, 70% of the recommended monitoring criteria were satisfied, although only 9 patients (9%; 95% confidence interval [95% CI], 3%-15%) received all of the recommended monitoring. Variability in monitoring practices was identified at all stages of the monitoring model. Of the patients, 52 (52%; 95% CI, 42%-62%) received minimum baseline evaluations, 22 (22%; 95% CI, 14%-31%) underwent ongoing surveillance, 75 (75%; 95% CI, 61%-89%) had appropriate responses to abnormal surveillance results, and 71 (71%; 95% CI, 62%-80%) had timely follow-up visits. Of the patients, 8 (8%; 95% CI, 3%-13%) had 9 amiodarone-related adverse drug events, of which 3 were judged to be preventable. Interrater agreement for monitoring processes (kappa = 0.83) and adverse drug events (kappa = 0.67) was good. CONCLUSIONS: Current standards for amiodarone toxicity monitoring are based on expert opinion with limited evidence to support most recommendations. Monitoring practices appear to vary significantly, with few patients receiving all of the recommended monitoring. Some amiodarone-related adverse drug events may be preventable and patient safety might be improved with a better understanding of monitoring processes.

Adult↗

PubMed1998

Exploring the ontology of surgical procedures in the Read Thesaurus.

The Read Thesaurus is a comprehensive user-led clinical vocabulary developed from earlier, and structurally simpler, versions of the Read Codes, with substantial input from United Kingdom health care professionals. A constituent template table underpins a range of functions, including semantic definition of concepts using object-attribute-value triples. Concept representation for surgical procedures has been investigated by a number of groups and a standard European structure has been proposed. Over 50% of the surgical procedures in the Read Thesaurus have been fully characterised using a number of attributes each with a defined concept field. We report progress to date and, based on our large-scale experience, examine the applicability of the European model to a user-defined terminology.

Europe↗

PubMedDate not supplied

Contrasting contributions of phonological short-term memory and long-term knowledge to vocabulary learning in a foreign language.

The contributions of phonological short-term memory and existing foreign vocabulary knowledge to the learning of new words in a second language were compared in a sample of 40 Greek children studying English at school. The children's speed of learning new English words in a paired-associate learning task was strongly influenced by their current English vocabulary, but was independent of phonological memory skill, indexed by nonword repetition ability. However, phonological memory performance was closely linked to English vocabulary scores. The findings suggest that in learners with considerable familiarity with a second language, foreign vocabulary acquisition is mediated largely by use of existing knowledge representations.

Adolescent↗

PubMed2003

Towards a broad-coverage biomedical ontology based on description logics.

We describe an ontology engineering methodology by which conceptual knowledge is extracted from an informal medical thesaurus (UMLS) and automatically converted into a formal description logics system (LOOM). Our approach consists of four steps: concept definitions are automatically generated from the UMLS, integrity checking of taxonomic and partonomic hierarchies is performed by LOOM's terminological classifier, cycles and inconsistencies are eliminated, as well as incremental refinement of the evolving knowledge base is performed by a domain expert. We report on experiments with a very large knowledge base composed of 164,000 concepts and 76,000 relations.

Artificial Intelligence↗

PubMed2004

Canadian dentists' willingness to be involved in dental research.

BACKGROUND: Building a collaborative research network reuniting dentists and academics constitutes a solution in order to bridge the gap between dental research and patient care. The purpose of this study was to identify the kind of clinicians willing to be involved in research and to determine their research priorities. METHODS: A questionnaire was mailed to all registered dentists in Canada in December 2001. This questionnaire comprised sociodemographic variables and questions on research utility, research results availability and dental research priorities. The statistical analyses were performed with 2,595 questionnaires completed by dentists working in a clinical setting. RESULTS: 27% of respondents were willing to be involved in dental research, 23% did not know and 50% did not want to be involved. A multiple logistic regression model shows that being open to participate (Yes and Don't know) is associated with: younger age (OR = 2.83), perception that research has a very big impact on the oral health of the population (OR = 1.93), perception that dental research results are not easily available to dentists (OR = 1.47), practice as a specialist (OR = 1.45) and French spoken as a first language (OR = 1.45). A large majority (80%) of dentists who would like to be involved in research think that effectiveness of techniques and treatments are a very high priority. CONCLUSIONS: There is a significant group of dentists who wish to be involved in research. This information could be used to reunite dentists and researchers in a collaborative network.

Adult↗

PubMed1996

A simulation model of the dynamics of HIV transmission in intravenous drug users.

The complex dynamics of HIV transmission and subsequent progression to AIDS make the use of traditional mathematical modeling techniques problematic. In a previous paper for this journal, Leslie and Brunham established the utility of a nonmathematical simulation language in modeling HIV transfer under conditions similar to those found among homosexual males. This study considers the application of such an approach in modeling HIV spread among intravenous drug users (IDUs) injecting within a "shooting gallery," a location providing a common needle supply to a large number of users. Modeling HIV transmission in this population involves not only consideration of heterogeneity in partnership selection, but also of the fact that spread of the virus is not directly from person to person, but via injection equipment. The General Purpose Simulation System was used to create a hypothetical cohort of IDUs, drawing from a common needle supply. Following introduction of an index case, the HIV infection rate in this cohort was followed over 5 simulated years. The model was then used to consider the effects of systematic variation in the frequency of injection and needle-cleaning behavior.

Acquired Immunodeficiency Syndrome↗

PubMedDate not supplied

Maternal correlates of growth in toddler vocabulary production in low-income families.

This study investigated predictors of growth in toddlers' vocabulary production between the ages of 1 and 3 years by analyzing mother-child communication in 108 low-income families. Individual growth modeling was used to describe patterns of growth in children's observed vocabulary production and predictors of initial status and between-person change. Results indicate large variation in growth across children. Observed variation was positively related to diversity of maternal lexical input and maternal language and literacy skills, and negatively related to maternal depression. Maternal talkativeness was not related to growth in children's vocabulary production in this sample. Implications of the examination of longitudinal data from this relatively large sample of low-income families are discussed.

Child, Preschool↗