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 217 records · Page 12Linked to original sources
PubMed2004

Gene name ambiguity of eukaryotic nomenclatures.

MOTIVATION: With more and more scientific literature published online, the effective management and reuse of this knowledge has become problematic. Natural language processing (NLP) may be a potential solution by extracting, structuring and organizing biomedical information in online literature in a timely manner. One essential task is to recognize and identify genomic entities in text. 'Recognition' can be accomplished using pattern matching and machine learning. But for 'identification' these techniques are not adequate. In order to identify genomic entities, NLP needs a comprehensive resource that specifies and classifies genomic entities as they occur in text and that associates them with normalized terms and also unique identifiers so that the extracted entities are well defined. Online organism databases are an excellent resource to create such a lexical resource. However, gene name ambiguity is a serious problem because it affects the appropriate identification of gene entities. In this paper, we explore the extent of the problem and suggest ways to address it. RESULTS: We obtained gene information from 21 organisms and quantified naming ambiguities within species, across species, with English words and with medical terms. When the case (of letters) was retained, official symbols displayed negligible intra-species ambiguity (0.02%) and modest ambiguities with general English words (0.57%) and medical terms (1.01%). In contrast, the across-species ambiguity was high (14.20%). The inclusion of gene synonyms increased intra-species ambiguity substantially and full names contributed greatly to gene-medical-term ambiguity. A comprehensive lexical resource that covers gene information for the 21 organisms was then created and used to identify gene names by using a straightforward string matching program to process 45,000 abstracts associated with the mouse model organism while ignoring case and gene names that were also English words. We found that 85.1% of correctly retrieved mouse genes were ambiguous with other gene names. When gene names that were also English words were included, 233% additional 'gene' instances were retrieved, most of which were false positives. We also found that authors prefer to use synonyms (74.7%) to official symbols (17.7%) or full names (7.6%) in their publications. CONTACT: lifeng.chen@dbmi.columbia.edu

Abstracting and Indexing↗
PubMed2005

Evaluation of Medical Problem Extraction from Electronic Clinical Documents Using MetaMap Transfer (MMTx).

To improve the use and quality of the electronic Problem List, which is at the heart of the problem-oriented medical record in development in our institution (Intermountain Health Care, Utah, U.S.), we developed an Automated Problem List system using Natural Language Processing (NLP) technologies. A key part of this system is a module that automatically extracts potential medical problems from free-text clinical documents. The NLP module uses MMTx, developed at the U.S. National Library of Medicine. Negation detection was added to this application by adapting a negation detection algorithm called NegEx. To evaluate the adequacy of the performance of the NLP module for our Automated Problem List system, we evaluated it with 160 electronic clinical documents of different types. Two different data sets for MMTx were used: the default full UMLS data set and a customised subset adapted to detect the set of 80 medical problems we are interested in. With the default data set, we measured a recall of 0.74 (95% CI 0.68-0.8) and a precision of 0.76 (0.69-0.82). The customised subset had a significantly better recall of 0.9 (0.85-0.94), and a non-significantly different precision of 0.69 (0.63-0.75).

Algorithms↗
PubMed2003

A shallow parser based on closed-class words to capture relations in biomedical text.

Natural language processing for biomedical text currently focuses mostly on entity and relation extraction. These entities and relations are usually pre-specified entities, e.g., proteins, and pre-specified relations, e.g., inhibit relations. A shallow parser that captures the relations between noun phrases automatically from free text has been developed and evaluated. It uses heuristics and a noun phraser to capture entities of interest in the text. Cascaded finite state automata structure the relations between individual entities. The automata are based on closed-class English words and model generic relations not limited to specific words. The parser also recognizes coordinating conjunctions and captures negation in text, a feature usually ignored by others. Three cancer researchers evaluated 330 relations extracted from 26 abstracts of interest to them. There were 296 relations correctly extracted from the abstracts resulting in 90% precision of the relations and an average of 11 correct relations per abstract.

Abstracting and Indexing↗
PubMed2002

Rutabaga by any other name: extracting biological names.

As the pace of biological research accelerates, biologists are becoming increasingly reliant on computers to manage the information explosion. Biologists communicate their research findings by relying on precise biological terms; these terms then provide indices into the literature and across the growing number of biological databases. This article examines emerging techniques to access biological resources through extraction of entity names and relations among them. Information extraction has been an active area of research in natural language processing and there are promising results for information extraction applied to news stories, e.g., balanced precision and recall in the 93-95% range for identifying person, organization and location names. But these results do not seem to transfer directly to biological names, where results remain in the 75-80% range. Multiple factors may be involved, including absence of shared training and test sets for rigorous measures of progress, lack of annotated training data specific to biological tasks, pervasive ambiguity of terms, frequent introduction of new terms, and a mismatch between evaluation tasks as defined for news and real biological problems. We present evidence from a simple lexical matching exercise that illustrates some specific problems encountered when identifying biological names. We conclude by outlining a research agenda to raise performance of named entity tagging to a level where it can be used to perform tasks of biological importance.

Abstracting and Indexing↗
PubMed2001

Comparing syntactic complexity in medical and non-medical corpora.

With the growing use of Natural Language Processing (NLP) techniques as solutions in Medical Informatics, the need to quickly and efficiently create the knowledge structures used by these systems has grown concurrently. Automatic discovery of a lexicon for use by an NLP system through machine learning will require information about the syntax of medical language. Understanding the syntactic differences between medical and non-medical corpora may allow more efficient acquisition of a lexicon. Three experiments designed to quantify the syntactic differences in medical and non-medical corpora were conducted. The results show that the syntax of medical language shows less variation than non-medical language and is likely simpler. The differences were great enough to question the applicability of general language tools on medical language. These differences may reduce the difficulty of some free text machine learning problems by capitalizing on the simpler nature of narrative medical syntax.

Artificial Intelligence↗
PubMed2006

Developing an NLP and IR-based algorithm for analyzing gene-disease relationships.

OBJECTIVES: High-throughput techniques such as cDNA microarray, oligonucleotide arrays, and serial analysis of gene expression (SAGE) have been developed and used to automatically screen huge amounts of gene expression data. However, researchers usually spend lots of time and money on discovering gene-disease relationships by utilizing these techniques. We prototypically implemented an algorithm that can provide some kind of predicted results for biological researchers before they proceed with experiments, and it is very helpful for them to discover gene-disease relationships more efficiently. METHODS: Due to the fast development of computer technology, many information retrieval techniques have been applied to analyze huge digital biomedical databases available worldwide. Therefore we highly expect that we can apply information retrieval (IR) technique to extract useful information for the relationship of specific diseases and genes from MEDLINE articles. Furthermore, we also applied natural language processing (NLP) methods to do the semantic analysis for the relevant articles to discover the relationships between genes and diseases. RESULTS: We have extracted gene symbols from our literature collection according to disease MeSH classifications. We have also built an IR-based retrieval system, "Biomedical Literature Retrieval System (BLRS)" and applied the N-gram model to extract the relationship features which can reveal the relationship between genes and diseases. Finally, a relationship network of a specific disease has been built to represent the gene-disease relationships. CONCLUSIONS: A relationship feature is a functional word that can reveal the relationship between one single gene and a disease. By incorporating many modern IR techniques, we found that BLRS is a very powerful information discovery tool for literature searching. A relationship network which contains the information on gene symbol, relationship feature, and disease MeSH term can provide an integrated view to discover gene-disease relationships.

Algorithms↗
PubMed2006

Using discordance to improve classification in narrative clinical databases: an application to community-acquired pneumonia.

Data mining in electronic medical records may facilitate clinical research, but much of the structured data may be miscoded, incomplete, or non-specific. The exploitation of narrative data using natural language processing may help, although nesting, varying granularity, and repetition remain challenges. In a study of community-acquired pneumonia using electronic records, these issues led to poor classification. Limiting queries to accurate, complete records led to vastly reduced, possibly biased samples. We exploited knowledge latent in the electronic records to improve classification. A similarity metric was used to cluster cases. We defined discordance as the degree to which cases within a cluster give different answers for some query that addresses a classification task of interest. Cases with higher discordance are more likely to be incorrectly classified, and can be reviewed manually to adjust the classification, improve the query, or estimate the likely accuracy of the query. In a study of pneumonia--in which the ICD9-CM coding was found to be very poor--the discordance measure was statistically significantly correlated with classification correctness (.45; 95% CI .15-.62).

Adult↗
PubMed1991

Extending a natural language parser with UMLS knowledge.

Over the past several years our research efforts have been directed toward the identification of natural language processing methods and techniques for improving access to biomedical information stored in computerized form. To provide a testing ground for some of these ideas we have undertaken the development of SPECIALIST, a prototype system for parsing and accessing biomedical text. The system includes linguistic and biomedical knowledge. Linguistic knowledge involves rules and facts about the grammar of the language. Biomedical knowledge involves rules and facts about the domain of biomedicine. The UMLS knowledge sources, Meta-1 and the Semantic Network, as well as the UMLS test collection, have recently contributed to the development of the SPECIALIST system.

Information Storage and Retrieval↗
PubMed2026

The Role of Artificial Intelligence for Intimate Partner Violence Prevention: A Systematic Review.

INTRODUCTION: Intimate partner violence (IPV), encompassing physical, sexual, emotional and economic abuse, remains a pervasive global health concern. Traditional prevention efforts face obstacles such as underreporting, delayed detection and limited personalised support. Emerging artificial intelligence (AI) approaches offer new opportunities to enhance IPV prevention. AIM: This systematic review maps and synthesises evidence on AI-driven tools in IPV prevention based on studies published between 2004 and 2024. METHODS: Following PRISMA 2020 guidelines and PROSPERO registration, we searched PubMed, Embase, CINAHL, PsycINFO, IEEE Xplore and Web of Science. Eligible studies explicitly evaluated AI technologies targeting IPV prediction, screening, intervention or support delivery. Study quality was appraised using the Mixed Methods Appraisal Tool (MMAT). RESULTS: Of 1304 records initially identified, 41 studies met eligibility criteria. AI applications ranged from machine learning (ML) for risk prediction and natural language processing (NLP) for IPV detection in clinical and social media data, to image analysis for forensic evaluation and chatbot-based support. Predictive modelling demonstrated strong discriminative performance, while NLP-based screening detected IPV with notable sensitivity. Chatbots showed feasibility and user acceptability, but evidence of their direct impact on reducing IPV incidence was limited, with one randomised controlled trial showing a modest reduction. Key challenges identified included algorithmic bias, data privacy risks and barriers to integration across health and social care systems. DISCUSSION: AI-informed interventions show promise for improving IPV detection, risk assessment, and scalable support, but questions remain about long-term effectiveness, ethical fairness, transparency and equitable implementation. Future interdisciplinary research should address these concerns to responsibly deploy AI in IPV prevention. RELEVANCE TO CLINICAL PRACTICE: The findings highlight the importance of trauma-informed, culturally responsive care and provider training in AI applications. Nurse-led innovation and policy advocacy will be crucial for safe, equitable integration of AI in IPV prevention.

Artificial Intelligence↗
PubMed2005

Analysis of polarity information in medical text.

Knowing the polarity of clinical outcomes is important in answering questions posed by clinicians in patient treatment. We treat analysis of this information as a classification problem. Natural language processing and machine learning techniques are applied to detect four possibilities in medical text: no outcome, positive outcome, negative outcome, and neutral outcome. A supervised learning method is used to perform the classification at the sentence level. Five feature sets are constructed: unigrams, bigrams, change phrases, negations, and categories. The performance of different combinations of feature sets is compared. The results show that generalization using the category information in the domain knowledge base Unified Medical Language System is effective in the task. The effect of context information is significant. Combining linguistic features and domain knowledge leads to the highest accuracy.

Artificial Intelligence↗
PubMed2001

Disambiguating ambiguous biomedical terms in biomedical narrative text: an unsupervised method.

With the growing use of Natural Language Processing (NLP) techniques for information extraction and concept indexing in the biomedical domain, a method that quickly and efficiently assigns the correct sense of an ambiguous biomedical term in a given context is needed concurrently. The current status of word sense disambiguation (WSD) in the biomedical domain is that handcrafted rules are used based on contextual material. The disadvantages of this approach are (i) generating WSD rules manually is a time-consuming and tedious task, (ii) maintenance of rule sets becomes increasingly difficult over time, and (iii) handcrafted rules are often incomplete and perform poorly in new domains comprised of specialized vocabularies and different genres of text. This paper presents a two-phase unsupervised method to build a WSD classifier for an ambiguous biomedical term W. The first phase automatically creates a sense-tagged corpus for W, and the second phase derives a classifier for W using the derived sense-tagged corpus as a training set. A formative experiment was performed, which demonstrated that classifiers trained on the derived sense-tagged corpora achieved an overall accuracy of about 97%, with greater than 90% accuracy for each individual ambiguous term.

Algorithms↗
PubMed2005

Modeling public health interventions for improved access to the gray literature.

OBJECTIVE: Much of the useful information in public health (PH) is considered gray literature, literature that is not available through traditional, commercial pathways. The diversity and nontraditional format of this information makes it difficult to locate. The aim of this Robert Wood Johnson Foundation-funded project is to improve access to PH gray literature reports through established natural language processing (NLP) techniques. This paper summarizes the development of a model for representing gray literature documents concerning PH interventions. METHODS: The authors established a model-based approach for automatically analyzing and representing the PH gray literature through the evaluation of a corpus of PH gray literature from seven PH Websites. Input from fifteen PH professionals assisted in the development of the model and prioritization of elements for NLP extraction. RESULTS: Of 365 documents collected, 320 documents were used for analysis to develop a model of key text elements of gray literature documents relating to PH interventions. Survey input from a group of potential users directed the selection of key elements to include in the document summaries. CONCLUSIONS: A model of key elements relating to PH interventions in the gray literature can be developed from the ground up through document analysis and input from members of the PH workforce. The model provides a framework for developing a method to identify and store key elements from documents (metadata) as document surrogates that can be used for indexing, abstracting, and determining the shape of the PH gray literature.

Access to Information↗
PubMed2026

Toward a Better Paradigm for Head and Neck Cancer Treatment Applying AI (HNC-TACTIC): Protocol for an International Cohort Study of Electronic Health Records.

BACKGROUND: Head and neck squamous cell carcinomas (HNSCCs) cause considerable morbidity and mortality. Multimodal treatment strategies can cause significant toxicity, and therapy options are limited for recurrent disease. Immunotherapy has emerged as a promising approach. However, patient response variability underscores the need for better predictive markers. OBJECTIVE: This study aims to use artificial intelligence to develop two predictive models in patients with HNSCC to assess (1) progression or recurrence following primary curative treatment and (2) long-term survival after immunotherapy schemes in recurrent and metastatic disease. This study will also describe the characteristics of patients with early, locally advanced, and recurrent or metastatic cancers. METHODS: This is a retrospective, observational study of data captured in electronic health records (EHRs) from participating hospitals between January 1, 2014, and December 31, 2021. This study's population comprises adults diagnosed with HNSCC at any stage. Study variables, including demographics, comorbidities, clinical variables, treatments, and outcomes, will be extracted using EHRead, a technology that applies natural language processing and machine learning to extract and analyze structured and unstructured clinical information in deidentified EHRs. Predictive models based on dynamic risk stratification for treatment response and progression or recurrence will be developed using multivariable logistic regressions, decision tree classifiers, and random forest approaches. Descriptive and outcome analyses will be shown for different anatomic subsites and stratified by stage and treatment. RESULTS: This study began enrolling sites in July 2021 and is currently ongoing. By December 2025, data from 10 centers has been collected, comprising a total of 151,934,990 EHRs from 2,159,719 patients. CONCLUSIONS: Development of predictive models using artificial intelligence will advance clinical understanding of HNSCC to improve patient outcomes.

Humans↗
PubMed2005

Ambiguity resolution analysis in incremental parsing of natural language.

Incremental parsing gains its importance in natural language processing and psycholinguistics because of its cognitive plausibility. Modeling the associated cognitive data structures, and their dynamics, can lead to a better understanding of the human parser. In earlier work, we have introduced a recursive neural network (RNN) capable of performing syntactic ambiguity resolution in incremental parsing. In this paper, we report a systematic analysis of the behavior of the network that allows us to gain important insights about the kind of information that is exploited to resolve different forms of ambiguity. In attachment ambiguities, in which a new phrase can be attached at more than one point in the syntactic left context, we found that learning from examples allows us to predict the location of the attachment point with high accuracy, while the discrimination amongst alternative syntactic structures with the same attachment point is slightly better than making a decision purely based on frequencies. We also introduce several new ideas to enhance the architectural design, obtaining significant improvements of prediction accuracy, up to 25% error reduction on the same dataset used in previous work. Finally, we report large scale experiments on the entire Wall Street Journal section of the Penn Treebank. The best prediction accuracy of the model on this large dataset is 87.6%, a relative error reduction larger than 50% compared to previous results.

Algorithms↗
PubMedDate not supplied

Present and future trends with NLP.

This paper reflects some desiderata on the role of Natural Language Processing (NLP) in the coming years as foreseen in the medical domain. During the Medical Informatics Europe (MIE) conference in 1997, the NLP track was composed by numerous papers on natural language, knowledge representation, nomenclatures and classifications. Indeed, the medical community is looking for solutions for the future which are going to emerge from more powerful desktop and for which the successful softwares of tomorrow are not yet identified. Presently this same community's needs remains unsatisfied with healthcare professionals writing at best their patient medical records in a text processing system. We stand today closer to the typewriter than to any modern solution which could radically transform the treatment of information related to patients. What kind of hurdles are there still in front of us before we reach this new territory?

Europe↗
PubMed2006

Quantitative assessment of dictionary-based protein named entity tagging.

OBJECTIVE: Natural language processing (NLP) approaches have been explored to manage and mine information recorded in biological literature. A critical step for biological literature mining is biological named entity tagging (BNET) that identifies names mentioned in text and normalizes them with entries in biological databases. The aim of this study was to provide quantitative assessment of the complexity of BNET on protein entities through BioThesaurus, a thesaurus of gene/protein names for UniProt knowledgebase (UniProtKB) entries that was acquired using online resources. METHODS: We evaluated the complexity through several perspectives: ambiguity (i.e., the number of genes/proteins represented by one name), synonymy (i.e., the number of names associated with the same gene/protein), and coverage (i.e., the percentage of gene/protein names in text included in the thesaurus). We also normalized names in BioThesaurus and measures were obtained twice, once before normalization and once after. RESULTS: The current version of BioThesaurus has over 2.6 million names or 2.1 million normalized names covering more than 1.8 million UniProtKB entries. The average synonymy is 3.53 (2.86 after normalization), ambiguity is 2.31 before normalization and 2.32 after, while the coverage is 94.0% based on the BioCreAtive data set comprising MEDLINE abstracts containing genes/proteins. CONCLUSION: The study indicated that names for genes/proteins are highly ambiguous and there are usually multiple names for the same gene or protein. It also demonstrated that most gene/protein names appearing in text can be found in BioThesaurus.

Dictionaries as Topic↗
PubMed2004

Gene name identification and normalization using a model organism database.

Biology has now become an information science, and researchers are increasingly dependent on expert-curated biological databases to organize the findings from the published literature. We report here on a series of experiments related to the application of natural language processing to aid in the curation process for FlyBase. We focused on listing the normalized form of genes and gene products discussed in an article. We broke this into two steps: gene mention tagging in text, followed by normalization of gene names. For gene mention tagging, we adopted a statistical approach. To provide training data, we were able to reverse engineer the gene lists from the associated articles and abstracts, to generate text labeled (imperfectly) with gene mentions. We then evaluated the quality of the noisy training data (precision of 78%, recall 88%) and the quality of the HMM tagger output trained on this noisy data (precision 78%, recall 71%). In order to generate normalized gene lists, we explored two approaches. First, we explored simple pattern matching based on synonym lists to obtain a high recall/low precision system (recall 95%, precision 2%). Using a series of filters, we were able to improve precision to 50% with a recall of 72% (balanced F-measure of 0.59). Our second approach combined the HMM gene mention tagger with various filters to remove ambiguous mentions; this approach achieved an F-measure of 0.72 (precision 88%, recall 61%). These experiments indicate that the lexical resources provided by FlyBase are complete enough to achieve high recall on the gene list task, and that normalization requires accurate disambiguation; different strategies for tagging and normalization trade off recall for precision.

Abstracting and Indexing↗
PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗