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 1,315 records · Page 73Linked to original sources

Systematic feature evaluation for gene name recognition.

In task 1A of the BioCreAtIvE evaluation, systems had to be devised that recognize words and phrases forming gene or protein names in natural language sentences. We approach this problem by building a word classification system based on a sliding window approach with a Support Vector Machine, combined with a pattern-based post-processing for the recognition of phrases. The performance of such a system crucially depends on the type of features chosen for consideration by the classification method, such as pre- or postfixes, character n-grams, patterns of capitalization, or classification of preceding or following words. We present a systematic approach to evaluate the performance of different feature sets based on recursive feature elimination, RFE. Based on a systematic reduction of the number of features used by the system, we can quantify the impact of different feature sets on the results of the word classification problem. This helps us to identify descriptive features, to learn about the structure of the problem, and to design systems that are faster and easier to understand. We observe that the SVM is robust to redundant features. RFE improves the performance by 0.7%, compared to using the complete set of attributes. Moreover, a performance that is only 2.3% below this maximum can be obtained using fewer than 5% of the features.

Computational Biology↗

Nature of phonological delay in children with specific language impairment.

This study investigated the nature of phonological delay in a group of children with specific language impairment. It was asked whether phonological errors in this group of children were generated by a slow but normal language learning process or whether they reflected a selective impairment in some representations that enhance normal acquisition and use of a language phonology. A group of 10 children with SLI (mean age = 5.1) was compared with three groups of normal children who were matched in age (age control group, mean age = 5.1), in sentence comprehension and recalling (grammar control group, mean age = 3.7), or who exhibited a phonological performance lower than the age average (group with low phonological performance, mean age = 4.4). The four groups of children were assessed in terms of: (1) responses to a mispronunciation detection task; and (2) error profiles with complex and simple syllabic structures. Performance on the mispronunciation detection task showed that the group with SLI could distinguish a target lexical item from acoustic non-word stimuli that were highly similar to it in terms of phonetic characteristics. An analysis of overall error rate at this task showed, however, that four children with SLI had a much lower performance than normal children of the same age, even when the auditory stimuli were tokens of the target word, or non-words that were phonetically different from the target. A difficulty in coordinating vocal actions in an articulatory plan accounted for error profiles with simple syllabic structures both for some children with SLI and normal children with phonological performance lower than the age average. A severe difficulty with representing complex syllabic structures was a homogeneous characteristic of the group with SLI and worked as the main indicator of impaired, rather than simply slow, phonological development.

Articulation Disorders↗

The integration of a continuous-speech-recognition system with the QMR diagnostic program.

We describe a continuous-speech interface for Quick Medical Reference (QMR), which allows physicians to input spoken descriptions of physical-examination findings, or observations. We analyze the difficulties in designing a continuous-speech interface for systems that use medical terminology. We present a method for matching spoken findings names expressed in natural language to QMR terms. The method is based on a semantic representation of findings that both minimize the effect of misrecognition and derive grammars that are necessary for supporting the recognition process.

Diagnosis, Computer-Assisted↗

Velo-cardio-facial syndrome: language and psychological profiles.

The velo-cardio-facial syndrome (VCF) has been delineated as a relatively common recurrent-pattern malformation syndrome of clefting. As originally described, the syndrome's major features are clefting of the secondary palate, cardiac anomalies, characteristic facies, learning disabilities, and speech disorders. As characteristic of the syndrome, however, is a rather distinctive pattern of language disorders and personality characteristics that has not been previously described. The purpose of this report is to add to the phenotype of the velo-cardio-facial syndrome by providing a description of the language, academic, and psychological profiles of 26 patients. This information would prove useful in the process of differential diagnosis. Striking observations concerning changes manifest during the course of development from initial language acquisition through childhood and adolescence will also add to the information regarding this syndrome's natural history and prognosis.

Abnormalities, Multiple↗

Processing stages underlying word recognition in the anteroventral temporal lobe.

The anteroventral temporal lobe integrates visual, lexical, semantic and mnestic aspects of word processing, through its reciprocal connections with the ventral visual stream, language areas, and the hippocampal formation. We used linear microelectrode arrays to probe population synaptic currents and neuronal firing in different cortical layers of the anteroventral temporal lobe, during semantic judgments with implicit priming and overt word recognition. Since different extrinsic and associative inputs preferentially target different cortical layers, this method can help reveal the sequence and nature of local processing stages at a higher resolution than was previously possible. The initial response in inferotemporal and perirhinal cortices is a brief current sink beginning at approximately 120 ms and peaking at approximately 170 ms. Localization of this initial sink to middle layers suggests that it represents feedforward input from lower visual areas, and simultaneously increased firing implies that it represents excitatory synaptic currents. Until approximately 800 ms, the main focus of transmembrane current sinks alternates between middle and superficial layers, with the superficial focus becoming increasingly dominant after approximately 550 ms. Since superficial layers are the target of local and feedback associative inputs, this suggests an alternation in predominant synaptic input between feedforward and feedback modes. Word repetition does not affect the initial perirhinal and inferotemporal middle layer sink but does decrease later activity. Entorhinal activity begins later (approximately 200 ms), with greater apparent excitatory post-synaptic currents and multiunit activity in neocortically projecting than hippocampal-projecting layers. In contrast to perirhinal and entorhinal responses, entorhinal responses are larger to repeated words during memory retrieval. These results identify a sequence of physiological activation, beginning with a sharp activation from lower level visual areas carrying specific information to middle layers. This is followed by feedback and associative interactions involving upper cortical layers, which are abbreviated to repeated words. Following bottom-up and associative stages, top-down recollective processes may be driven by entorhinal cortex. Word processing involves a systematic sequence of fast feedforward information transfer from visual areas to anteroventral temporal cortex followed by prolonged interactions of this feedforward information with local associations and feedback mnestic information from the medial temporal lobe.

Adult↗

Perception of Mandarin lexical tones when F0 information is neutralized.

In tone languages, the identity of a word depends on its tone pattern as well as its phonetic structure. The primary cue to tone identity is the fundamental frequency (F0) contour. Two experiments explore spoken word recognition how listeners perceive Mandarin monosyllables in which all or part of the F0 information has been neutralized. In Experiment 1, tone languages supposedly critical portions of the tonal pattern were neutralized with signal processing techniques, yet identification of the tonal pattern remained quite good. In Experiment 2, even more drastic removal of tonal information was tested, using stimuli whispered by Mandarin speakers, or signal processed to remove the pitch cues. Again, performance was surprisingly good, showing that listeners can use secondary cues when the primary cue is unavailable. Moreover, a comparison of tone perception of naturally whispered monosyllables and the signal processed ones suggests that Mandarin speakers promote the utility of secondary cues when they know that the primary cue will be unavailable. The flexible use of cues to tone in Mandarin is similar to the flexibility that has been found in the production and perception of cues to phonetic identity in Western languages.

Adult↗

Assessment of a Newark neighborhood: process and outcomes.

In 1996, the members of the St. Columba Collaboration conducted a grassroots neighborhood assessment of a Hispanic area in Newark, New Jersey. This assessment was undertaken during an era of significant political and policy change in New Jersey. As a community-driven and implemented effort, the processes, methods, and outcomes of this assessment provide lessons on community activism, political awareness, and strategic planning. Quantitative surveys were distributed to local residents as well as users of the various services provided through Collaboration programs. Ten qualitative focus groups were held among various Collaboration groups. A total of 471 surveys were returned from a door-to-door distribution and 295 surveys were returned from users of Collaboration programs. Findings from both the quantitative and qualitative components were surprisingly similar. It was striking to note that youth violence, domestic violence, crime, and lack of job skills surpassed poor housing and chronic health problems, including HIV/AIDS and drug and alcohol addiction, as the most noted neighborhood problems. Overwhelmingly, social, welfare, and environmental issues were identified as priority items in a neighborhood marked by extreme poverty, poor childhood immunization rates, high HIV/AIDS rates, and high incidence of childhood asthma. Focus group findings revealed that stressful daily life events and circumstances far overshadowed health and wellness concerns. Recommendations emanating from the St. Columba Neighborhood needs assessment included: (a) establishment of principled partnerships between the Collaboration and other regional entities to extend capacity to design and implement solutions (e.g., partnerships with other higher education institutions, health care agencies); (b) development of strategic planning processes and procedures within the Collaboration; (c) establishment of collaborative partnerships with other Hispanic community-based organizations for political activism; and (d) reorganization of the Collaboration's internal structure and functions to capitalize on opportunities for change. Significant outcomes from this process, in evidence 4 years after the 1996 neighborhood assessment, include: (a) a successful grant application to study violence against Hispanic women, (b) a research program investigating the nature and extent of clinical depression among Hispanic women, (c) establishment of a teenage pregnancy program, (d) English classes for Hispanic women seeking language skills and eventual employment, and (e) partnership extended to the New Jersey Institute of Technology.

Community Health Nursing↗

[Health-related quality of life of patients receiving home mechanical ventilation: the Spanish version of the severe respiratory insufficiency questionnaire].

OBJECTIVE: Home mechanical ventilation is used with patients with severe, chronic respiratory failure, a condition that has a serious impact on quality of life. The aim of this study was to produce a translation and cultural adaptation of the Severe Respiratory Insufficiency. Questionnaire for the Spanish population, the first health-related quality of life questionnaire specifically designed for patients receiving home mechanical ventilation. METHODS: Four bilingual German-Spanish translators were used to translate and back-translate the questionnaire. Meetings were held with the translators following each step of the translation process to produce a single version that could be used in the next step. At the end of the process, the questionnaire was piloted to assess its comprehensibility. A scoring system using a scale of 1 (lowest) to 10 (highest) was used to rate both translation difficulty and the naturalness of the language produced. The equivalence of the original and translated items was also evaluated. RESULTS: Three Spanish versions of the questionnaire were produced. Task difficulty was rated as quite low: the mean (SD) ratings were 1.4 (0.6) for translation and 2.2 (1.1) for back translation. The naturalness of the translated items was rated as very high, with scores improving with the successive versions (version 1, 8.4; version 2, 8.7; version 3, 9.1; P< .001). Thirty of the questionnaire items (61.2%) were judged to be fully equivalent, 13 (26.5%) to be similar, and 6 (12.2%) to be non-equivalent. The meaning conveyed by 5 of the items was changed or clarified during piloting. CONCLUSIONS: The translation of the questionnaire using the translation-back-translation procedure has produced a version that is both comparable to the original and accessible to the Spanish population. Its validity is currently being tested in a multicenter study.

Aged↗

Age-related changes in transient and oscillatory brain responses to auditory stimulation in healthy adults 19-45 years old.

The capacity of the human cerebral cortex to track fast temporal changes in auditory stimuli is related to the development of language in children and to deficits in speech perception in the elderly. Although maturation of temporal processing in children and its deterioration in the elderly has been investigated previously, little is known about naturally occurring changes in auditory temporal processing between these limits. The present study examined age-related (19-45 years) changes in 3 electrophysiological measures of auditory processing: 1) the late transient auditory evoked potentials to tone onset, 2) the auditory steady-state response (ASSR) to a 40-Hz frequency-modulated tone, and 3) the envelope following response (EFR) to sweeps of amplitude-modulated white noise from 10 to 100 Hz. With increasing age, the latency of the auditory P1-N1 complex decreased, the oscillatory (ASSR) response became larger and more stable, and the resonant peak of the EFR increased from 38 Hz at 19 years to 46 Hz at 45 years. Source analysis localized these changes to the auditory regions of the temporal lobe. These results indicate persistent adaptation of cortical auditory processes into middle adulthood. We speculate that experience-driven myelination and/or refinement of inhibitory circuits may underlie these changes.

Adult↗

The narrative and rhetoric of dreams: six literary fragments by a novelist.

Four of a novelist's dreams and two contemporaneous pieces of her fiction are examined through the lens of poststructuralism; thus viewed they display narrative coherence in form and content, a reciprocal interaction between dream and written day residue, and a rhetorical function in trauma resolution. Lacan's theories about the linguistic nature of the unconscious are particularly powerful in understanding these six works especially their recourse to figurative language in deconstructing and reconstructing the traumatized self. Dream narratology suggests the close relation of unconscious processes to creativity and the unity of storymaking and personal meaning. Narrative conventions in these dreams and related fiction illustrate the functions of metaphor and metonymy in traversing Lacan's "registers of experience" and his ideas about the "itinerary of the signifier," the way dreams and art capture the elusive object of desire. Creativity serves not only a wish-fulfillment function but also a self-fulfillment function. Dreams, then, as creative acts, claim a privilege unto themselves and support Lacan's argument for a therapeutic approach of "desirelessness."

Creativity↗

[Understanding natural childbirth].

Childbirth is considered to be a physiological event in the sense that reproduction is so for all mammals, with a distinct trait for humans tied to human capability to think, use language and relate to one another. In itself, childbirth is a mechanical set having a chemical and hormonal origin connected to the procedure to expel an already mature fetus. As a result, one should know and understand which are the mechanisms that start this process, as well as which behaviors may favor or hinder the perfect functioning of this process. The goal is to achieve a birth which allows the natural process to work and which makes this an experience that mother, baby and father can call their own. "The health care team also partakes in this experience, one which it adds to its own experiences, while society receives a new individual."

Community Health Nursing↗

Cocaine recovery support groups and the language of recovery.

The authors have attempted to make clear that recovery is a lifelong process. In its early phases, clients are working primarily to achieve relief from guilt and pain created by their addiction. As recovery progresses, however, there is a movement from a relief mentality to a true experience of delight (Enright 1980). The goals of treatment have been achieved when this shift is evident: when one is living comfortably, responsibly and joyfully without cocaine or other drugs. The authors' experience indicates that treating cocaine addicts in cocaine-specific groups is useful in that the homogeneity facilitates group identification and the educational component of treatment. However, the content of the groups and nature of the recovery process are not drug specific or unique. The emergence of C.A., which is based on the same 12 steps as A.A., also illustrates this. What is being treated is addictive disease, not alcoholism or cocaine addiction. Regardless of the chemical, the essentials of treatment are the same: The language of recovery is universal.

Adaptation, Psychological↗

Are RAN- and phonological awareness-deficits additive in children with reading disabilities?

The double-deficit hypothesis (Wolf, M. and Bowers, P.G. (1999) The double-deficit hypothesis for the developmental dyslexias. Journal of Educational Psychology, 91, 415-438) proposes that deficits in phonological processing and rapid automatized naming (RAN) are separable sources of reading dysfunction. Further, the double-deficit hypothesis predicts that the presence of deficits in both phonological processing and RAN have an additive negative influence on reading performance above and beyond that of a single deficit. The purpose of this study was to examine the additive nature of phonological awareness (PA)- and RAN-deficits on written language skill in children with reading disabilities (RD). Concurrent relationships between PA, RAN, and written language skills were examined in 476 children with RD, ranging in age from 8 to 18 years of age. Hierarchical regression analysis revealed that PA and RAN skill have an additive effect on a majority of the reading and spelling measures. When participants were classified into three deficit subtypes based on the double-deficit model (i.e. phonological-, rate-, and double-deficit), comparisons across the subtypes confirmed that individuals with double-deficits performed below the single-deficit groups on both subtyping variables (RAN and PA) and all measures of written language. When the double- and single-deficit groups were matched on the subtyping variable (i.e. double- and rate-deficit groups matched on RAN and double- and phonological-deficit groups matched on PA) differences between the double- and rate-deficit groups remained in non-word reading, whereas differences between the double- and phonological-deficit groups remained in timed word recognition and reading comprehension. These results support an additive model in which RAN-deficits primarily affect tasks that require speeded/fluent response, and PA-deficits primarily affect tasks that emphasize phonological processing skill. Results are also presented that illustrate several statistical problems associated with the formation of deficit groups by dichotomizing the RAN and PA variables.

Awareness↗

Extraction of SNOMED concepts from medical record texts.

Clinicians have traditionally documented patient data using natural language text. With the increasing prevalence of computer systems in health care, an increasing amount of medical record text will be stored electronically. However, for such textual documents to be indexed, shared, and processed adequately by computers, it will be important to be able to identify concepts in the documents using a common medical terminology. Automated methods for extracting concepts in a standard terminology would enhance retrieval and analysis of medical record data. This paper discusses a method for extracting concepts from medical record documents using the medical terminology SNOMED-III (Systematized Nomenclature of Human and Veterinary Medicine, Version III). The technique employs a linear least squares fit that maps training set phrases to SNOMED concepts. This mapping can be used for unknown text inputs in the same domain as the training set to predict SNOMED concepts that are contained in the document. We have implemented the method in the domain of congestive heart failure for history and physical exam texts. Our system has a reasonable response time. We tested the system over a range of thresholds. The system performed with 90% sensitivity and 83% specificity at the lowest threshold, and 42% sensitivity and 99.9% specificity at the highest threshold.

Algorithms↗

Memory mechanisms in the processing of words and word-like symbols.

Modern functional imaging techniques such as positron emission tomography (PET) provide the opportunity to examine in some detail the implementation of mental activities in the human brain. Using measurements of changes in local brain blood flow obtained with PET as a marker of changes in local neuronal activity we have examined the processing of single words and word-like symbols. These studies reveal the very distributed, modular nature of this implementation and provide some preliminary insights into the role of memory mechanisms in the process.

Brain Mapping↗

Semantic and phonological processing in reading Korean Hangul and Hanja words.

The Korean orthography uses both alphabetic Hangul and logographic Hanja. Two experiments investigated semantic and phonological processing of words written in the two scripts. In the experiments, Korean readers had to respond to words either in a pure context with words from one single script or in a mixed context with words from the two scripts. The task was naming in Experiment 1 and semantic categorization in Experiment 2. The results showed that for Hangul words, there were significant word frequency effects in categorization, but not in naming, and that there were reliable script-switching effects in naming, but not in categorization. For Hanja words, however, there were clear and strong effects of words frequency, regardless of the task used, but significant effects of script-switching were only observed in categorization. These results suggest that the strategies adopted in processing Hangul and Hanja words are determined both by task demand and nature of the script.

Humans↗

Words and maps: developmental changes in mental models of spatial information acquired from descriptions and depictions.

People acquire spatial information from many sources, including maps, verbal descriptions, and navigating in the environment. The different sources present spatial information in different ways. For example, maps can show many spatial relations simultaneously, but in a description, each spatial relation must be presented sequentially. The present research investigated how these source differences influence the mental models that children and adults form of the presented information. In Experiment 1, 8-year-olds, 10-year-olds and adults learned the layout of a six-room space either from verbal descriptions or from a map. They then constructed the configuration and pointed to target locations. Participants who learned from the map performed significantly better than those who learned from the description. Ten-year-olds performed nearly as well as adults did. The 8-year-olds' mental models differed substantially from the older children's and adults' mental models. The younger children retained the sequential information but did not integrate the relations into a survey-like cognitive map. Experiment 2 demonstrated that viewing the shape of the configuration, without seeing the map in full, could facilitate 8-year-olds' use of the verbal information and their ability to integrate the locations. The results demonstrate developmental differences in the mental representation of spatial information from descriptions. In addition, the results reveal that maps and other graphic representations can facilitate children's spatial thinking by helping them to transcend the sequential nature of language and direct experience.

Adult↗

[Cognitive and emotional disorders in multiple sclerosis. Can a management strategy be envisioned?].

There is a lack of precise data concerning the natural history of cognitive disorders in multiple sclerosis (MS), but recent neuropsychological studies have demonstrated that the incidence of such disorders in MS appears to be frequent (40-65% of cases), and have shown in particular that recent memory, conceptual reasoning, attention, executive functions, visuospatial perception and information processing speed are negatively affected. In contrast, language functions, general intelligence and implicit memory appear to be relatively well preserved. Although the presence and the degree of cognitive disorders does not seem to be directly linked to disease duration or to the extent of physical disability, the relationship between cognitive decline and brain lesions detected by magnetic resonance imaging (MRI) is still a subject of discussion. The prevalence of emotional and affective disorders is difficult to estimate. Their frequency has only rarely been investigated, and the lack of data on the natural history of these disorders and those factors which they have in common (the psychosocial consequences of this chronic and disabling disease, cognitive impairment, and brain lesions) further complicate the determination of treatment strategy. The adoption of appropriate strategies could limit the negative impact of this disease on the social functioning of MS patients.

Cognition Disorders↗