Rezarta Islamaj Doğan

DNorm: disease name normalization with pairwise learning to rank

Motivation: Despite the central role of diseases in biomedical research, there have been much fewer attempts to automatically determine which diseases are mentioned in a text—the task of disease name normalization (DNorm)—compared with other normalization tasks in biomedical text mining research. Methods: In this article we introduce the first machine learning approach for DNorm, using the NCBI disease corpus and the MEDIC vocabulary, which combines MeSH® and OMIM. Our method is a high-performing and mathematically principled framework for learning similarities between mentions and concept names directly from training data. The technique is based on pairwise learning to rank, which has not previously been applied to the normalization task but has proven successful in large optimization problems for information retrieval. Results: We compare our method with several techniques based on lexical normalization and matching, MetaMap and Lucene. Our algorithm achieves 0.782 micro-averaged F-measure and 0.809 macro-averaged F-measure, an increase over the highest performing baseline method of 0.121 and 0.098, respectively. Availability: The source code for DNorm is available at http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/DNorm, along with a web-based demonstration and links to the NCBI disease corpus. Results on PubMed abstracts are available in PubTator: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTator Contact: zhiyong.lu@nih.gov

SplicePort—An interactive splice-site analysis tool

SplicePort is a web-based tool for splice-site analysis that allows the user to make splice-site predictions for submitted sequences. In addition, the user can also browse the rich catalog of features that underlies these predictions, and which we have found capable of providing high classification accuracy on human splice sites. Feature selection is optimized for human splice sites, but the selected features are likely to be predictive for other mammals as well. With our interactive feature browsing and visualization tool, the user can view and explore subsets of features used in splice-site prediction (either the features that account for the classification of a specific input sequence or the complete collection of features). Selected feature sets can be searched, ranked or displayed easily. The user can group features into clusters and frequency plot WebLogos can be generated for each cluster. The user can browse the identified clusters and their contributing elements, looking for new interesting signals, or can validate previously observed signals. The SplicePort web server can be accessed at http://www.cs.umd.edu/projects/SplicePort and http://www.spliceport.org.

Understanding PubMed® user search behavior through log analysis

This article reports on a detailed investigation of PubMed users’ needs and behavior as a step toward improving biomedical information retrieval. PubMed is providing free service to researchers with access to more than 19 million citations for biomedical articles from MEDLINE and life science journals. It is accessed by millions of users each day. Efficient search tools are crucial for biomedical researchers to keep abreast of the biomedical literature relating to their own research. This study provides insight into PubMed users’ needs and their behavior. This investigation was conducted through the analysis of one month of log data, consisting of more than 23 million user sessions and more than 58 million user queries. Multiple aspects of users’ interactions with PubMed are characterized in detail with evidence from these logs. Despite having many features in common with general Web searches, biomedical information searches have unique characteristics that are made evident in this study. PubMed users are more persistent in seeking information and they reformulate queries often. The three most frequent types of search are search by author name, search by gene/protein, and search by disease. Use of abbreviation in queries is very frequent. Factors such as result set size influence users’ decisions. Analysis of characteristics such as these plays a critical role in identifying users’ information needs and their search habits. In turn, such an analysis also provides useful insight for improving biomedical information retrieval. Database URL: http://www.ncbi.nlm.nih.gov/PubMed

The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text

BackgroundDetermining usefulness of biomedical text mining systems requires realistic task definition and data selection criteria without artificial constraints, measuring performance aspects that go beyond traditional metrics. The BioCreative III Protein-Protein Interaction (PPI) tasks were motivated by such considerations, trying to address aspects including how the end user would oversee the generated output, for instance by providing ranked results, textual evidence for human interpretation or measuring time savings by using automated systems. Detecting articles describing complex biological events like PPIs was addressed in the Article Classification Task (ACT), where participants were asked to implement tools for detecting PPI-describing abstracts. Therefore the BCIII-ACT corpus was provided, which includes a training, development and test set of over 12,000 PPI relevant and non-relevant PubMed abstracts labeled manually by domain experts and recording also the human classification times. The Interaction Method Task (IMT) went beyond abstracts and required mining for associations between more than 3,500 full text articles and interaction detection method ontology concepts that had been applied to detect the PPIs reported in them.ResultsA total of 11 teams participated in at least one of the two PPI tasks (10 in ACT and 8 in the IMT) and a total of 62 persons were involved either as participants or in preparing data sets/evaluating these tasks. Per task, each team was allowed to submit five runs offline and another five online via the BioCreative Meta-Server. From the 52 runs submitted for the ACT, the highest Matthews Correlation Coefficient (MCC) score measured was 0.55 at an accuracy of 89% and the best AUC iP/R was 68%. Most ACT teams explored machine learning methods, some of them also used lexical resources like MeSH terms, PSI-MI concepts or particular lists of verbs and nouns, some integrated NER approaches. For the IMT, a total of 42 runs were evaluated by comparing systems against manually generated annotations done by curators from the BioGRID and MINT databases. The highest AUC iP/R achieved by any run was 53%, the best MCC score 0.55. In case of competitive systems with an acceptable recall (above 35%) the macro-averaged precision ranged between 50% and 80%, with a maximum F-Score of 55%.ConclusionsThe results of the ACT task of BioCreative III indicate that classification of large unbalanced article collections reflecting the real class imbalance is still challenging. Nevertheless, text-mining tools that report ranked lists of relevant articles for manual selection can potentially reduce the time needed to identify half of the relevant articles to less than 1/4 of the time when compared to unranked results. Detecting associations between full text articles and interaction detection method PSI-MI terms (IMT) is more difficult than might be anticipated. This is due to the variability of method term mentions, errors resulting from pre-processing of articles provided as PDF files, and the heterogeneity and different granularity of method term concepts encountered in the ontology. However, combining the sophisticated techniques developed by the participants with supporting evidence strings derived from the articles for human interpretation could result in practical modules for biological annotation workflows.

NCBI disease corpus: A resource for disease name recognition and concept normalization

Information encoded in natural language in biomedical literature publications is only useful if efficient and reliable ways of accessing and analyzing that information are available. Natural language processing and text mining tools are therefore essential for extracting valuable information, however, the development of powerful, highly effective tools to automatically detect central biomedical concepts such as diseases is conditional on the availability of annotated corpora. This paper presents the disease name and concept annotations of the NCBI disease corpus, a collection of 793 PubMed abstracts fully annotated at the mention and concept level to serve as a research resource for the biomedical natural language processing community. Each PubMed abstract was manually annotated by two annotators with disease mentions and their corresponding concepts in Medical Subject Headings (MeSH®) or Online Mendelian Inheritance in Man (OMIM®). Manual curation was performed using PubTator, which allowed the use of pre-annotations as a pre-step to manual annotations. Fourteen annotators were randomly paired and differing annotations were discussed for reaching a consensus in two annotation phases. In this setting, a high inter-annotator agreement was observed. Finally, all results were checked against annotations of the rest of the corpus to assure corpus-wide consistency. The public release of the NCBI disease corpus contains 6892 disease mentions, which are mapped to 790 unique disease concepts. Of these, 88% link to a MeSH identifier, while the rest contain an OMIM identifier. We were able to link 91% of the mentions to a single disease concept, while the rest are described as a combination of concepts. In order to help researchers use the corpus to design and test disease identification methods, we have prepared the corpus as training, testing and development sets. To demonstrate its utility, we conducted a benchmarking experiment where we compared three different knowledge-based disease normalization methods with a best performance in F-measure of 63.7%. These results show that the NCBI disease corpus has the potential to significantly improve the state-of-the-art in disease name recognition and normalization research, by providing a high-quality gold standard thus enabling the development of machine-learning based approaches for such tasks. The NCBI disease corpus, guidelines and other associated resources are available at: http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/DISEASE/.

BioC: a minimalist approach to interoperability for biomedical text processing

A vast amount of scientific information is encoded in natural language text, and the quantity of such text has become so great that it is no longer economically feasible to have a human as the first step in the search process. Natural language processing and text mining tools have become essential to facilitate the search for and extraction of information from text. This has led to vigorous research efforts to create useful tools and to create humanly labeled text corpora, which can be used to improve such tools. To encourage combining these efforts into larger, more powerful and more capable systems, a common interchange format to represent, store and exchange the data in a simple manner between different language processing systems and text mining tools is highly desirable. Here we propose a simple extensible mark-up language format to share text documents and annotations. The proposed annotation approach allows a large number of different annotations to be represented including sentences, tokens, parts of speech, named entities such as genes or diseases and relationships between named entities. In addition, we provide simple code to hold this data, read it from and write it back to extensible mark-up language files and perform some sample processing. We also describe completed as well as ongoing work to apply the approach in several directions. Code and data are available at http://bioc.sourceforge.net/. Database URL: http://bioc.sourceforge.net/

Semi-automatic semantic annotation of PubMed queries

Information processing algorithms require significant amounts of annotated data for training and testing. The availability of such data is often hindered by the complexity and high cost of production. In this paper, we investigate the benefits of a state-of-the-art tool to help with the semantic annotation of a large set of biomedical queries. Seven annotators were recruited to annotate a set of 10,000 PubMed® queries with 16 biomedical and bibliographic categories. About half of the queries were annotated from scratch, while the other half were automatically pre-annotated and manually corrected. The impact of the automatic pre-annotations was assessed on several aspects of the task: time, number of actions, annotator satisfaction, inter-annotator agreement, quality and number of the resulting annotations. The analysis of annotation results showed that the number of required hand annotations is 28.9% less when using pre-annotated results from automatic tools. As a result, the overall annotation time was substantially lower when pre-annotations were used, while inter-annotator agreement was significantly higher. In addition, there was no statistically significant difference in the semantic distribution or number of annotations produced when pre-annotations were used. The annotated query corpus is freely available to the research community. This study shows that automatic pre-annotations are found helpful by most annotators. Our experience suggests using an automatic tool to assist large-scale manual annotation projects. This helps speed-up the annotation time and improve annotation consistency while maintaining high quality of the final annotations.

Author name disambiguation for PubMed

Log analysis shows that PubMed users frequently use author names in queries for retrieving scientific literature. However, author name ambiguity may lead to irrelevant retrieval results. To improve the PubMed user experience with author name queries, we designed an author name disambiguation system consisting of similarity estimation and agglomerative clustering. A machine‐learning method was employed to score the features for disambiguating a pair of papers with ambiguous names. These features enable the computation of pairwise similarity scores to estimate the probability of a pair of papers belonging to the same author, which drives an agglomerative clustering algorithm regulated by 2 factors: name compatibility and probability level. With transitivity violation correction, high precision author clustering is achieved by focusing on minimizing false‐positive pairing. Disambiguation performance is evaluated with manual verification of random samples of pairs from clustering results. When compared with a state‐of‐the‐art system, our evaluation shows that among all the pairs the lumping error rate drops from 10.1% to 2.2% for our system, while the splitting error rises from 1.8% to 7.7%. This results in an overall error rate of 9.9%, compared with 11.9% for the state‐of‐the‐art method. Other evaluations based on gold standard data also show the increase in accuracy of our clustering. We attribute the performance improvement to the machine‐learning method driven by a large‐scale training set and the clustering algorithm regulated by a name compatibility scheme preferring precision. With integration of the author name disambiguation system into the PubMed search engine, the overall click‐through‐rate of PubMed users on author name query results improved from 34.9% to 36.9%.

Extracting Rx information from clinical narrative

OBJECTIVE The authors used the i2b2 Medication Extraction Challenge to evaluate their entity extraction methods, contribute to the generation of a publicly available collection of annotated clinical notes, and start developing methods for ontology-based reasoning using structured information generated from the unstructured clinical narrative. DESIGN Extraction of salient features of medication orders from the text of de-identified hospital discharge summaries was addressed with a knowledge-based approach using simple rules and lookup lists. The entity recognition tool, MetaMap, was combined with dose, frequency, and duration modules specifically developed for the Challenge as well as a prototype module for reason identification. MEASUREMENTS Evaluation metrics and corresponding results were provided by the Challenge organizers. RESULTS The results indicate that robust rule-based tools achieve satisfactory results in extraction of simple elements of medication orders, but more sophisticated methods are needed for identification of reasons for the orders and durations. LIMITATIONS Owing to the time constraints and nature of the Challenge, some obvious follow-on analysis has not been completed yet. CONCLUSIONS The authors plan to integrate the new modules with MetaMap to enhance its accuracy. This integration effort will provide guidance in retargeting existing tools for better processing of clinical text.

A context-blocks model for identifying clinical relationships in patient records

BackgroundPatient records contain valuable information regarding explanation of diagnosis, progression of disease, prescription and/or effectiveness of treatment, and more. Automatic recognition of clinically important concepts and the identification of relationships between those concepts in patient records are preliminary steps for many important applications in medical informatics, ranging from quality of care to hypothesis generation.MethodsIn this work we describe an approach that facilitates the automatic recognition of eight relationships defined between medical problems, treatments and tests. Unlike the traditional bag-of-words representation, in this work, we represent a relationship with a scheme of five distinct context-blocks determined by the position of concepts in the text. As a preliminary step to relationship recognition, and in order to provide an end-to-end system, we also addressed the automatic extraction of medical problems, treatments and tests. Our approach combined the outcome of a statistical model for concept recognition and simple natural language processing features in a conditional random fields model. A set of 826 patient records from the 4th i2b2 challenge was used for training and evaluating the system.ResultsResults show that our concept recognition system achieved an F-measure of 0.870 for exact span concept detection. Moreover the context-block representation of relationships was more successful (F-Measure = 0.775) at identifying relationships than bag-of-words (F-Measure = 0.402). Most importantly, the performance of the end-to-end system of relationship extraction using automatically extracted concepts (F-Measure = 0.704) was comparable to that obtained using manually annotated concepts (F-Measure = 0.711), and their difference was not statistically significant.ConclusionsWe extracted important clinical relationships from text in an automated manner, starting with concept recognition, and ending with relationship identification. The advantage of the context-blocks representation scheme was the correct management of word position information, which may be critical in identifying certain relationships. Our results may serve as benchmark for comparison to other systems developed on i2b2 challenge data. Finally, our system may serve as a preliminary step for other discovery tasks in medical informatics.