Text Processing Pipeline Research Articles

Development and validation of a pulmonary function test data extraction tool for the US department of veterans affairs electronic health record

ObjectivePulmonary function test (PFT) results are recorded variably across hospitals in the Department of Veterans Affairs (VA) electronic health record (EHR), using both unstructured and semi-structured notes. We developed and validated a hospital-specific code to extract pre-bronchodilator measures of obstruction (ratio of forced expiratory volume in one second [FEV1] to forced vital capacity [FVC]) and severity of obstruction (percent predicted of FEV1).ResultsAmong 36 VA facilities with the most PFTs completed between 2018 and 2022 from a parent cohort of veterans receiving long-acting controller inhalers, 12 had a consistent syntactical convention or template for reporting PFT data in the EHR. Of the 42,718 PFTs identified from these 12 facilities, the hospital-specific text processing pipeline yielded 24,860 values for the FEV1:FVC ratio and 23,729 values for FEV1. A ratio of FEV1:FVC less than 0.7 was identified in 17,615 of 24,922 studies (70.7%); 8864 of 24,922 (35.6%) had a severe or very severe reduction in FEV1 (< 50% of the predicted value). Among 100 randomly selected PFT reports reviewed by two pulmonary physicians, the coding solution correctly identified the presence of obstruction in 99 out of 100 studies and the degree of obstruction in 96 out of 100 studies.

How Could Semantic Processing and Other NLP Tools Improve Online Legal Databases?

Abstract The spread of online databases and the increasingly sophisticated search solutions in the past 10–15 years have opened up many new opportunities for lawyers to find relevant documents. However, it is still a common problem that the various legal databases and legal search engines face an information crisis. Legal database providers use various information extraction solutions, especially named entity recognition (NER), to mitigate this problem. These solutions can improve the relevance of the lists of results. Their limitation, however, is that they can only extract and create searchable metadata entities if the latter have a well-defined location or regularity in the text. Therefore, the next era of search support for legal databases is semantic processing. Semantic processing solutions are fundamentally different from information extraction and NER because they do not only extract and make visible and/or searchable the specific information element contained in the text but allow for the analytical analysis of the text as a whole. In addition, in many cases, legal database developments using machine learning can be a significant burden on a company, as it is not always known what kind of an AI solution is needed, and how the providers could compare the different solutions. Legal database providers need to customize processing their documents and texts in the most optimal way possible, considering all their legal, linguistic, statistical, or other characteristics. This is where text processing pipelines can help. So, the article reviews the two main natural language processing (NLP) solutions which can help legal database providers to increase the value of legal data within legal databases. The article then shows the importance of text-processing pipelines and frameworks in the era of digitized documents and presents the digital-twin-distiller.

Automated Matching of Patients to Clinical Trials: A Patient-Centric Natural Language Processing Approach for Pediatric Leukemia.

Matching patients to clinical trials is cumbersome and costly. Attempts have been made to automate the matching process; however, most have used a trial-centric approach, which focuses on a single trial. In this study, we developed a patient-centric matching tool that matches patient-specific demographic and clinical information with free-text clinical trial inclusion and exclusion criteria extracted using natural language processing to return a list of relevant clinical trials ordered by the patient's likelihood of eligibility. Records from pediatric leukemia clinical trials were downloaded from ClinicalTrials.gov. Regular expressions were used to discretize and extract individual trial criteria. A multilabel support vector machine (SVM) was trained to classify sentence embeddings of criteria into relevant clinical categories. Labeled criteria were parsed using regular expressions to extract numbers, comparators, and relationships. In the validation phase, a patient-trial match score was generated for each trial and returned in the form of a ranked list for each patient. In total, 5,251 discretized criteria were extracted from 216 protocols. The most frequent criterion was previous chemotherapy/biologics (17%). The multilabel SVM demonstrated a pooled accuracy of 75%. The text processing pipeline was able to automatically extract 68% of eligibility criteria rules, as compared with 80% in a manual version of the tool. Automated matching was accomplished in approximately 4 seconds, as compared with several hours using manual derivation. To our knowledge, this project represents the first open-source attempt to generate a patient-centric clinical trial matching tool. The tool demonstrated acceptable performance when compared with a manual version, and it has potential to save time and money when matching patients to trials.

Optimizing healthcare system by amalgamation of text processing and deep learning: a systematic review.

The explosion of clinical textual data has drawn the attention of researchers. Owingto the abundance of clinical data, it is becoming difficult for healthcare professionals to take real-time measures. The tools and methods are lacking when compared to the amount of clinical data generated every day. This review aims to survey the text processing pipeline with deep learning methods such as CNN, RNN, LSTM, and GRU in the healthcare domain and discuss various applications such as clinical concept detection and extraction, medically aware dialogue systems, sentiment analysis of drug reviews shared online, clinical trial matching, and pharmacovigilance. In addition, we highlighted the major challenges in deploying text processing with deep learning to clinical textual data and identified the scope of research in this domain. Furthermore, we have discussed various resources that can be used in the future to optimize the healthcare domain by amalgamating text processing and deep learning.

Discovering Content through Text Mining for a Synthetic Biology Knowledge System.

Scientific articles contain a wealth of information about experimental methods and results describing biological designs. Due to its unstructured nature and multiple sources of ambiguity and variability, extracting this information from text is a difficult task. In this paper, we describe the development of the synthetic biology knowledge system (SBKS) text processing pipeline. The pipeline uses natural language processing techniques to extract and correlate information from the literature for synthetic biology researchers. Specifically, we apply named entity recognition, relation extraction, concept grounding, and topic modeling to extract information from published literature to link articles to elements within our knowledge system. Our results show the efficacy of each of the components on synthetic biology literature and provide future directions for further advancement of the pipeline.

Monitoring COVID-19 on Social Media: Development of an End-to-End Natural Language Processing Pipeline Using a Novel Triage and Diagnosis Approach.

BackgroundThe COVID-19 pandemic has created a pressing need for integrating information from disparate sources in order to assist decision makers. Social media is important in this respect; however, to make sense of the textual information it provides and be able to automate the processing of large amounts of data, natural language processing methods are needed. Social media posts are often noisy, yet they may provide valuable insights regarding the severity and prevalence of the disease in the population. Here, we adopt a triage and diagnosis approach to analyzing social media posts using machine learning techniques for the purpose of disease detection and surveillance. We thus obtain useful prevalence and incidence statistics to identify disease symptoms and their severities, motivated by public health concerns.ObjectiveThis study aims to develop an end-to-end natural language processing pipeline for triage and diagnosis of COVID-19 from patient-authored social media posts in order to provide researchers and public health practitioners with additional information on the symptoms, severity, and prevalence of the disease rather than to provide an actionable decision at the individual level.MethodsThe text processing pipeline first extracted COVID-19 symptoms and related concepts, such as severity, duration, negations, and body parts, from patients’ posts using conditional random fields. An unsupervised rule-based algorithm was then applied to establish relations between concepts in the next step of the pipeline. The extracted concepts and relations were subsequently used to construct 2 different vector representations of each post. These vectors were separately applied to build support vector machine learning models to triage patients into 3 categories and diagnose them for COVID-19.ResultsWe reported macro- and microaveraged F1 scores in the range of 71%-96% and 61%-87%, respectively, for the triage and diagnosis of COVID-19 when the models were trained on human-labeled data. Our experimental results indicated that similar performance can be achieved when the models are trained using predicted labels from concept extraction and rule-based classifiers, thus yielding end-to-end machine learning. In addition, we highlighted important features uncovered by our diagnostic machine learning models and compared them with the most frequent symptoms revealed in another COVID-19 data set. In particular, we found that the most important features are not always the most frequent ones.ConclusionsOur preliminary results show that it is possible to automatically triage and diagnose patients for COVID-19 from social media natural language narratives, using a machine learning pipeline in order to provide information on the severity and prevalence of the disease for use within health surveillance systems.

Using Machine Learning to Collect and Facilitate Remote Access to Biomedical Databases: Development of the Biomedical Database Inventory.

BackgroundCurrently, existing biomedical literature repositories do not commonly provide users with specific means to locate and remotely access biomedical databases.ObjectiveTo address this issue, we developed the Biomedical Database Inventory (BiDI), a repository linking to biomedical databases automatically extracted from the scientific literature. BiDI provides an index of data resources and a path to access them seamlessly.MethodsWe designed an ensemble of deep learning methods to extract database mentions. To train the system, we annotated a set of 1242 articles that included mentions of database publications. Such a data set was used along with transfer learning techniques to train an ensemble of deep learning natural language processing models targeted at database publication detection.ResultsThe system obtained an F1 score of 0.929 on database detection, showing high precision and recall values. When applying this model to the PubMed and PubMed Central databases, we identified over 10,000 unique databases. The ensemble model also extracted the weblinks to the reported databases and discarded irrelevant links. For the extraction of weblinks, the model achieved a cross-validated F1 score of 0.908. We show two use cases: one related to “omics” and the other related to the COVID-19 pandemic.ConclusionsBiDI enables access to biomedical resources over the internet and facilitates data-driven research and other scientific initiatives. The repository is openly available online and will be regularly updated with an automatic text processing pipeline. The approach can be reused to create repositories of different types (ie, biomedical and others).

Machine Learning and Natural Language Processing for Geolocation-Centric Monitoring and Characterization of Opioid-Related Social Media Chatter

Automatic curation of consumer-generated, opioid-related social media big data may enable real-time monitoring of the opioid epidemic in the United States. To develop and validate an automatic text-processing pipeline for geospatial and temporal analysis of opioid-mentioning social media chatter. This cross-sectional, population-based study was conducted from December 1, 2017, to August 31, 2019, and used more than 3 years of publicly available social media posts on Twitter, dated from January 1, 2012, to October 31, 2015, that were geolocated in Pennsylvania. Opioid-mentioning tweets were extracted using prescription and illicit opioid names, including street names and misspellings. Social media posts (tweets) (n = 9006) were manually categorized into 4 classes, and training and evaluation of several machine learning algorithms were performed. Temporal and geospatial patterns were analyzed with the best-performing classifier on unlabeled data. Pearson and Spearman correlations of county- and substate-level abuse-indicating tweet rates with opioid overdose death rates from the Centers for Disease Control and Prevention WONDER database and with 4 metrics from the National Survey on Drug Use and Health for 3 years were calculated. Classifier performances were measured through microaveraged F1 scores (harmonic mean of precision and recall) or accuracies and 95% CIs. A total of 9006 social media posts were annotated, of which 1748 (19.4%) were related to abuse, 2001 (22.2%) were related to information, 4830 (53.6%) were unrelated, and 427 (4.7%) were not in the English language. Yearly rates of abuse-indicating social media post showed statistically significant correlation with county-level opioid-related overdose death rates (n = 75) for 3 years (Pearson r = 0.451, P < .001; Spearman r = 0.331, P = .004). Abuse-indicating tweet rates showed consistent correlations with 4 NSDUH metrics (n = 13) associated with nonmedical prescription opioid use (Pearson r = 0.683, P = .01; Spearman r = 0.346, P = .25), illicit drug use (Pearson r = 0.850, P < .001; Spearman r = 0.341, P = .25), illicit drug dependence (Pearson r = 0.937, P < .001; Spearman r = 0.495, P = .09), and illicit drug dependence or abuse (Pearson r = 0.935, P < .001; Spearman r = 0.401, P = .17) over the same 3-year period, although the tests lacked power to demonstrate statistical significance. A classification approach involving an ensemble of classifiers produced the best performance in accuracy or microaveraged F1 score (0.726; 95% CI, 0.708-0.743). The correlations obtained in this study suggest that a social media-based approach reliant on supervised machine learning may be suitable for geolocation-centric monitoring of the US opioid epidemic in near real time.

Data-driven method to enhance craniofacial and oral phenotype vocabularies

BackgroundA significant amount of clinical information captured as free-text narratives could be better used for several applications, such as clinical decision support, ontology development, evidence-based practice, and research. The Human Phenotype Ontology (HPO) is specifically used for semantic comparisons for diagnostic purposes. All these functions require quality coverage of the domain of interest. The authors used natural language processing to capture craniofacial and oral phenotype signatures from electronic health records and then used these signatures for evaluation of existing oral phenotype ontology coverage. MethodsThe authors applied a text-processing pipeline based on the clinical Text Analysis and Knowledge Extraction System to annotate the clinical notes with Unified Medical Language System codes. The authors extracted the disease or disorder phenotype terms, which were then compared with HPO terms and their synonyms. ResultsThe authors retrieved 2,153 deidentified clinical notes from 558 patients. Finally, 2,416 unique diseases or disorders phenotype terms were extracted, which included 210 craniofacial or oral phenotype terms. Twenty-six of these phenotypes were not found in the HPO. ConclusionsThe authors demonstrated that natural language processing tools could extract relevant phenotype terms from clinical narratives, which could help identify gaps in existing ontologies and enhance craniofacial and dental phenotyping vocabularies. Practical ImplicationsThe expansion of terms in the dental, oral, and craniofacial domains in the HPO is particularly important as the dental community moves toward electronic health records.

Automated extraction of ophthalmic surgery outcomes from the electronic health record

ObjectiveComprehensive analysis of ophthalmic surgical outcomes is often restricted by limited methodologies for efficiently and accurately extracting clinical information from electronic health record (EHR) systems because much is in free-text form. This study aims to utilize advanced methods to automate extraction of clinical concepts from the EHR free text to study visual acuity (VA), intraocular pressure (IOP), and medication outcomes of cataract and glaucoma surgeries. MethodsPatients who underwent cataract or glaucoma surgery at an academic medical center between 2009 and 2018 were identified by Current Procedural Terminology codes. Rule-based algorithms were developed and used on EHR clinical narrative text to extract intraocular lens (IOL) power and implant type, as well as to create a surgery laterality classifier. MedEx (version 1.3.7) was used on free-text clinical notes to extract information on eye medications and compared to information from medication orders. Random samples of free-text notes were reviewed by two independent masked annotators to assess inter-annotator agreement on outcome variable classification and accuracy of classifiers. VA and IOP were available from semi-structured fields. ResultsThis study cohort included 6347 unique patients, with 8550 stand-alone cataract surgeries, 451 combined cataract/glaucoma surgeries, and 961 glaucoma surgeries without concurrent cataract surgery. The rule-based laterality classifier achieved 100% accuracy compared to manual review of a sample of operative notes by independent masked annotators. For cataract surgery alone, glaucoma surgery alone, or combined cataract/glaucoma surgeries, our automated extraction algorithm achieved 99–100% accuracy compared to manual annotation of samples of notes from each group, including IOL model and IOL power for cataract surgeries, and glaucoma implant for glaucoma surgeries. For glaucoma medications, there was 90.7% inter-annotator agreement. After adjudication, 85.0% of medications identified by MedEx determined to be correct. Determination of surgical laterality enabled evaluation of pre- and postoperative VA and IOP for operative eyes. ConclusionThis text-processing pipeline can accurately capture surgical laterality and implant model usage from free-text operative notes of cataract and glaucoma surgeries, enabling extraction of clinical outcomes including visual acuities, intraocular pressure, and medications from the EHR system. Use of this approach with EHRs to assess ophthalmic surgical outcomes can benefit research groups interested in studying the safety and clinical efficacies of different surgical approaches.

Automatic Language Identification in Texts: A Survey

&#x0D; &#x0D; &#x0D; Language identification (“LI”) is the problem of determining the natural language that a document or part thereof is written in. Automatic LI has been extensively researched for over fifty years. Today, LI is a key part of many text processing pipelines, as text processing techniques generally assume that the language of the input text is known. Research in this area has recently been especially active. This article provides a brief history of LI research, and an extensive survey of the features and methods used in the LI literature. We describe the features and methods using a unified notation, to make the relationships between methods clearer. We discuss evaluation methods, applications of LI, as well as off-the-shelfLI systems that do not require training by the end user. Finally, we identify open issues, survey the work to date on each issue, and propose future directions for research in LI.&#x0D; &#x0D; &#x0D;

Automatic Processing of User-Generated Content for the Description of Energy-Consuming Activities at Individual and Group Level

Understanding and improving the energy consumption behavior of individuals is considered a powerful approach to improve energy conservation and stimulate energy efficiency. To motivate people to change their energy consumption behavior, we need to have a thorough understanding of which energy-consuming activities they perform and how these are performed. Traditional sources of information about energy consumption, such as smart sensor devices and surveys, can be costly to set up, may lack contextual information, have infrequent updates, or are not publicly accessible. In this paper, we propose to use social media as a complementary source of information for understanding energy-consuming activities. A huge amount of social media posts are generated by hundreds of millions of people every day, they are publicly available, and provide real-time data often tagged to space and time. We design an ontology to get a better understanding of the energy-consuming activities domain and develop a text and image processing pipeline to extract from social media the description of energy-consuming activities. We run a case study on Istanbul and Amsterdam. We highlight the strength and weakness of our approach, showing that social media data has the potential to be a complementary source of information for describing energy-consuming activities.

Beyond accuracy: creating interoperable and scalable text-mining web services.

The biomedical literature is a knowledge-rich resource and an important foundation for future research. With over 24 million articles in PubMed and an increasing growth rate, research in automated text processing is becoming increasingly important. We report here our recently developed web-based text mining services for biomedical concept recognition and normalization. Unlike most text-mining software tools, our web services integrate several state-of-the-art entity tagging systems (DNorm, GNormPlus, SR4GN, tmChem and tmVar) and offer a batch-processing mode able to process arbitrary text input (e.g. scholarly publications, patents and medical records) in multiple formats (e.g. BioC). We support multiple standards to make our service interoperable and allow simpler integration with other text-processing pipelines. To maximize scalability, we have preprocessed all PubMed articles, and use a computer cluster for processing large requests of arbitrary text. Our text-mining web service is freely available at http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/tmTools/#curl : Zhiyong.Lu@nih.gov.

ADT Linked to Increased Risk of Alzheimer's Disease

The use of androgen deprivation therapy for treatment of prostate cancer was associated with increased risk of Alzheimer's disease, and patients with greater duration of ADT use had higher risks, according to medical records data analysis. ADT use was significantly associated with Alzheimer's disease risk, with a hazard ratio (HR) of 1.88 by propensity score–matched Cox regression analysis (95% CI, 1.10–3.20; P = .021), and HR of 1.66 by traditional multivariable-adjusted Cox regression analysis (95% CI, 1.05–2.64; P = .031). Patients who used ADT for 12 months or more had the greatest risk observed (HR, 2.12; 95% CI, 1.11–4.03; P = .011), and the risk increased by category of ADT duration.Investigators used a novel text-processing pipeline to analyze clinical data, extracting disease and terminology codes, medication lists, and positive-present mentions of drug and disease concepts from clinical notes. “Use of the electronic medical record in this way allows rapid investigation of a rich data source to study a broad range of postmarketing outcomes, including those unlikely to be seen in smaller clinical trials,” wrote Kevin T. Nead, MD, of the University of Pennsylvania, Philadelphia, and his colleagues [J Clin Oncol 2015 Dec 7. doi: 10.1200/JCO.2015.63.6266]. The study evaluated 16,888 patients with prostate cancer; in total, 2,397 received ADT and 125 were diagnosed with Alzheimer's disease during a median follow-up of 2.7 years. The median time to Alzheimer's disease diagnosis was 4 years. The analysis replicated previously known associations between Alzheimer's disease and age (HR, 1.06; P < .001) and cardiovascular disease (HR, 1.60; P = .031), supporting the validity of the method, according to the researchers. Jennifer Shepphird is a Frontline Medical News freelance writer based in Hermosa Beach, CA.

Androgen Deprivation Therapy and Future Alzheimer's Disease Risk.

To test the association of androgen deprivation therapy (ADT) in the treatment of prostate cancer with subsequent Alzheimer's disease risk. We used a previously validated and implemented text-processing pipeline to analyze electronic medical record data in a retrospective cohort of patients at Stanford University and Mt. Sinai hospitals. Specifically, we extracted International Classification of Diseases-9th revision diagnosis and Current Procedural Terminology codes, medication lists, and positive-present mentions of drug and disease concepts from all clinical notes. We then tested the effect of ADT on risk of Alzheimer's disease using 1:5 propensity score-matched and traditional multivariable-adjusted Cox proportional hazards models. The duration of ADT use was also tested for association with Alzheimer's disease risk. There were 16,888 individuals with prostate cancer meeting all inclusion and exclusion criteria, with 2,397 (14.2%) receiving ADT during a median follow-up period of 2.7 years (interquartile range, 1.0-5.4 years). Propensity score-matched analysis (hazard ratio, 1.88; 95% CI, 1.10 to 3.20; P = .021) and traditional multivariable-adjusted Cox regression analysis (hazard ratio, 1.66; 95% CI, 1.05 to 2.64; P = .031) both supported a statistically significant association between ADT use and Alzheimer's disease risk. We also observed a statistically significant increased risk of Alzheimer's disease with increasing duration of ADT (P = .016). Our results support an association between the use of ADT in the treatment of prostate cancer and an increased risk of Alzheimer's disease in a general population cohort. This study demonstrates the utility of novel methods to analyze electronic medical record data to generate practice-based evidence.

Mining texts to efficiently generate global data on political regime types

We describe the design and results of an experiment in using text-mining and machine-learning techniques to generate annual measures of national political regime types. Valid and reliable measures of countries’ forms of national government are essential to cross-national and dynamic analysis of many phenomena of great interest to political scientists, including civil war, interstate war, democratization, and coups d’état. Unfortunately, traditional measures of regime type are very expensive to produce, and observations for ambiguous cases are often sharply contested. In this project, we train a series of support vector machine (SVM) classifiers to infer regime type from textual data sources. To train the classifiers, we used vectorized textual reports from Freedom House and the State Department as features for a training set of prelabeled regime type data. To validate our SVM classifiers, we compare their predictions in an out-of-sample context, and the performance results across a variety of metrics (accuracy, precision, recall) are very high. The results of this project highlight the ability of these techniques to contribute to producing real-time data sources for use in political science that can also be routinely updated at much lower cost than human-coded data. To this end, we set up a text-processing pipeline that pulls updated textual data from selected sources, conducts feature extraction, and applies supervised machine learning methods to produce measures of regime type. This pipeline, written in Python, can be pulled from the Github repository associated with this project and easily extended as more data becomes available.

Detection of sentence boundaries and abbreviations in clinical narratives.

BackgroundIn Western languages the period character is highly ambiguous, due to its double role as sentence delimiter and abbreviation marker. This is particularly relevant in clinical free-texts characterized by numerous anomalies in spelling, punctuation, vocabulary and with a high frequency of short forms.MethodsThe problem is addressed by two binary classifiers for abbreviation and sentence detection. A support vector machine exploiting a linear kernel is trained on different combinations of feature sets for each classification task. Feature relevance ranking is applied to investigate which features are important for the particular task. The methods are applied to German language texts from a medical record system, authored by specialized physicians.ResultsTwo collections of 3,024 text snippets were annotated regarding the role of period characters for training and testing. Cohen's kappa resulted in 0.98. For abbreviation and sentence boundary detection we can report an unweighted micro-averaged F-measure using a 10-fold cross validation of 0.97 for the training set. For test set based evaluation we obtained an unweighted micro-averaged F-measure of 0.95 for abbreviation detection and 0.94 for sentence delineation. Language-dependent resources and rules were found to have less impact on abbreviation detection than on sentence delineation.ConclusionsSentence detection is an important task, which should be performed at the beginning of a text processing pipeline. For the text genre under scrutiny we showed that support vector machines exploiting a linear kernel produce state of the art results for sentence boundary detection. The results are comparable with other sentence boundary detection methods applied to English clinical texts. We identified abbreviation detection as a supportive task for sentence delineation.

Generalising semantic category disambiguation with large lexical resources for fun and profit.

BackgroundSemantic Category Disambiguation (SCD) is the task of assigning the appropriate semantic category to given spans of text from a fixed set of candidate categories, for example Protein to “Fibrin”. SCD is relevant to Natural Language Processing tasks such as Named Entity Recognition, coreference resolution and coordination resolution. In this work, we study machine learning-based SCD methods using large lexical resources and approximate string matching, aiming to generalise these methods with regard to domains, lexical resources and the composition of data sets. We specifically consider the applicability of SCD for the purposes of supporting human annotators and acting as a pipeline component for other Natural Language Processing systems.ResultsWhile previous research has mostly cast SCD purely as a classification task, we consider a task setting that allows for multiple semantic categories to be suggested, aiming to minimise the number of suggestions while maintaining high recall. We argue that this setting reflects aspects which are essential for both a pipeline component and when supporting human annotators. We introduce an SCD method based on a recently introduced machine learning-based system and evaluate it on 15 corpora covering biomedical, clinical and newswire texts and ranging in the number of semantic categories from 2 to 91.With appropriate settings, our system maintains an average recall of 99% while reducing the number of candidate semantic categories on average by 65% over all data sets.ConclusionsMachine learning-based SCD using large lexical resources and approximate string matching is sensitive to the selection and granularity of lexical resources, but generalises well to a wide range of text domains and data sets given appropriate resources and parameter settings. By substantially reducing the number of candidate categories while only very rarely excluding the correct one, our method is shown to be applicable to manual annotation support tasks and use as a high-recall component in text processing pipelines. The introduced system and all related resources are freely available for research purposes at: https://github.com/ninjin/simsem.

Identifying phenotypic signatures of neuropsychiatric disorders from electronic medical records

Mental illness is the leading cause of disability in the USA, but boundaries between different mental illnesses are notoriously difficult to define. Electronic medical records (EMRs) have recently emerged as a powerful new source of information for defining the phenotypic signatures of specific diseases. We investigated how EMR-based text mining and statistical analysis could elucidate the phenotypic boundaries of three important neuropsychiatric illnesses-autism, bipolar disorder, and schizophrenia. We analyzed the medical records of over 7000 patients at two facilities using an automated text-processing pipeline to annotate the clinical notes with Unified Medical Language System codes and then searching for enriched codes, and associations among codes, that were representative of the three disorders. We used dimensionality-reduction techniques on individual patient records to understand individual-level phenotypic variation within each disorder, as well as the degree of overlap among disorders. We demonstrate that automated EMR mining can be used to extract relevant drugs and phenotypes associated with neuropsychiatric disorders and characteristic patterns of associations among them. Patient-level analyses suggest a clear separation between autism and the other disorders, while revealing significant overlap between schizophrenia and bipolar disorder. They also enable localization of individual patients within the phenotypic 'landscape' of each disorder. Because EMRs reflect the realities of patient care rather than idealized conceptualizations of disease states, we argue that automated EMR mining can help define the boundaries between different mental illnesses, facilitate cohort building for clinical and genomic studies, and reveal how clear expert-defined disease boundaries are in practice.

BeCAS: biomedical concept recognition services and visualization

The continuous growth of the biomedical scientific literature has been motivating the development of text-mining tools able to efficiently process all this information. Although numerous domain-specific solutions are available, there is no web-based concept-recognition system that combines the ability to select multiple concept types to annotate, to reference external databases and to automatically annotate nested and intercepted concepts. BeCAS, the Biomedical Concept Annotation System, is an API for biomedical concept identification and a web-based tool that addresses these limitations. MEDLINE abstracts or free text can be annotated directly in the web interface, where identified concepts are enriched with links to reference databases. Using its customizable widget, it can also be used to augment external web pages with concept highlighting features. Furthermore, all text-processing and annotation features are made available through an HTTP REST API, allowing integration in any text-processing pipeline. BeCAS is freely available for non-commercial use at http://bioinformatics.ua.pt/becas. tiago.nunes@ua.pt or jlo@ua.pt.