Delroy H. Cameron

PREDOSE: A semantic web platform for drug abuse epidemiology using social media

OBJECTIVES The role of social media in biomedical knowledge mining, including clinical, medical and healthcare informatics, prescription drug abuse epidemiology and drug pharmacology, has become increasingly significant in recent years. Social media offers opportunities for people to share opinions and experiences freely in online communities, which may contribute information beyond the knowledge of domain professionals. This paper describes the development of a novel semantic web platform called PREDOSE (PREscription Drug abuse Online Surveillance and Epidemiology), which is designed to facilitate the epidemiologic study of prescription (and related) drug abuse practices using social media. PREDOSE uses web forum posts and domain knowledge, modeled in a manually created Drug Abuse Ontology (DAO--pronounced dow), to facilitate the extraction of semantic information from User Generated Content (UGC), through combination of lexical, pattern-based and semantics-based techniques. In a previous study, PREDOSE was used to obtain the datasets from which new knowledge in drug abuse research was derived. Here, we report on various platform enhancements, including an updated DAO, new components for relationship and triple extraction, and tools for content analysis, trend detection and emerging patterns exploration, which enhance the capabilities of the PREDOSE platform. Given these enhancements, PREDOSE is now more equipped to impact drug abuse research by alleviating traditional labor-intensive content analysis tasks. METHODS Using custom web crawlers that scrape UGC from publicly available web forums, PREDOSE first automates the collection of web-based social media content for subsequent semantic annotation. The annotation scheme is modeled in the DAO, and includes domain specific knowledge such as prescription (and related) drugs, methods of preparation, side effects, and routes of administration. The DAO is also used to help recognize three types of data, namely: (1) entities, (2) relationships and (3) triples. PREDOSE then uses a combination of lexical and semantic-based techniques to extract entities and relationships from the scraped content, and a top-down approach for triple extraction that uses patterns expressed in the DAO. In addition, PREDOSE uses publicly available lexicons to identify initial sentiment expressions in text, and then a probabilistic optimization algorithm (from related research) to extract the final sentiment expressions. Together, these techniques enable the capture of fine-grained semantic information, which facilitate search, trend analysis and overall content analysis using social media on prescription drug abuse. Moreover, extracted data are also made available to domain experts for the creation of training and test sets for use in evaluation and refinements in information extraction techniques. RESULTS A recent evaluation of the information extraction techniques applied in the PREDOSE platform indicates 85% precision and 72% recall in entity identification, on a manually created gold standard dataset. In another study, PREDOSE achieved 36% precision in relationship identification and 33% precision in triple extraction, through manual evaluation by domain experts. Given the complexity of the relationship and triple extraction tasks and the abstruse nature of social media texts, we interpret these as favorable initial results. Extracted semantic information is currently in use in an online discovery support system, by prescription drug abuse researchers at the Center for Interventions, Treatment and Addictions Research (CITAR) at Wright State University. CONCLUSION A comprehensive platform for entity, relationship, triple and sentiment extraction from such abstruse texts has never been developed for drug abuse research. PREDOSE has already demonstrated the importance of mining social media by providing data from which new findings in drug abuse research were uncovered. Given the recent platform enhancements, including the refined DAO, components for relationship and triple extraction, and tools for content, trend and emerging pattern analysis, it is expected that PREDOSE will play a significant role in advancing drug abuse epidemiology in future.

A graph-based recovery and decomposition of Swanson's hypothesis using semantic predications

OBJECTIVES This paper presents a methodology for recovering and decomposing Swansons Raynaud Syndrome-Fish Oil hypothesis semi-automatically. The methodology leverages the semantics of assertions extracted from biomedical literature (called semantic predications) along with structured background knowledge and graph-based algorithms to semi-automatically capture the informative associations originally discovered manually by Swanson. Demonstrating that Swansons manually intensive techniques can be undertaken semi-automatically, paves the way for fully automatic semantics-based hypothesis generation from scientific literature. METHODS Semantic predications obtained from biomedical literature allow the construction of labeled directed graphs which contain various associations among concepts from the literature. By aggregating such associations into informative subgraphs, some of the relevant details originally articulated by Swanson have been uncovered. However, by leveraging background knowledge to bridge important knowledge gaps in the literature, a methodology for semi-automatically capturing the detailed associations originally explicated in natural language by Swanson, has been developed. RESULTS Our methodology not only recovered the three associations commonly recognized as Swansons hypothesis, but also decomposed them into an additional 16 detailed associations, formulated as chains of semantic predications. Altogether, 14 out of the 19 associations that can be attributed to Swanson were retrieved using our approach. To the best of our knowledge, such an in-depth recovery and decomposition of Swansons hypothesis has never been attempted. CONCLUSION In this work therefore, we presented a methodology to semi-automatically recover and decompose Swansons RS-DFO hypothesis using semantic representations and graph algorithms. Our methodology provides new insights into potential prerequisites for semantics-driven Literature-Based Discovery (LBD). Based on our observations, three critical aspects of LBD include: (1) the need for more expressive representations beyond Swansons ABC model; (2) an ability to accurately extract semantic information from text; and (3) the semantic integration of scientific literature and structured background knowledge.

Context-driven automatic subgraph creation for literature-based discovery

Background Literature-based discovery (LBD) is characterized by uncovering hidden associations in non-interacting scientific literature. Prior approaches to LBD include use of: 1) domain expertise and structured background knowledge to manually filter and explore the literature, 2) distributional statistics and graph-theoretic measures to rank interesting connections, and 3) heuristics to help eliminate spurious connections. However, manual approaches to LBD are not scalable and purely distributional approaches may not be sufficient to obtain insights into the meaning of poorly understood associations. While several graph-based approaches have the potential to elucidate associations, their effectiveness has not been fully demonstrated. A considerable degree of a priori knowledge, heuristics, and manual filtering is still required. Objectives In this paper we implement and evaluate a context-driven, automatic subgraph creation method that captures multifaceted complex associations between biomedical concepts to facilitate LBD. Given a pair of concepts, our method automatically generates a ranked list of subgraphs, which provide informative and potentially unknown associations between such concepts. Methods To generate subgraphs, the set of all MEDLINE articles that contain either of the two specified concepts (A, C) are first collected. Then binary relationships or assertions, which are automatically extracted from the MEDLINE articles, called semantic predications, are used to create a labeled directed predications graph. In this predications graph, a path is represented as a sequence of semantic predications. The hierarchical agglomerative clustering (HAC) algorithm is then applied to cluster paths that are bounded by the two concepts (A, C). HAC relies on implicit semantics captured through Medical Subject Heading (MeSH) descriptors, and explicit semantics from the MeSH hierarchy, for clustering. Paths that exceed a threshold of semantic relatedness are clustered into subgraphs based on their shared context. Finally, the automatically generated clusters are provided as a ranked list of subgraphs. Results The subgraphs generated using this approach facilitated the rediscovery of 8 out of 9 existing scientific discoveries. In particular, they directly (or indirectly) led to the recovery of several intermediates (or B-concepts) between A- and C-terms, while also providing insights into the meaning of the associations. Such meaning is derived from predicates between the concepts, as well as the provenance of the semantic predications in MEDLINE. Additionally, by generating subgraphs on different thematic dimensions (such as Cellular Activity, Pharmaceutical Treatment and Tissue Function), the approach may enable a broader understanding of the nature of complex associations between concepts. Finally, in a statistical evaluation to determine the interestingness of the subgraphs, it was observed that an arbitrary association is mentioned in only approximately 4 articles in MEDLINE on average. Conclusion These results suggest that leveraging the implicit and explicit semantics provided by manually assigned MeSH descriptors is an effective representation for capturing the underlying context of complex associations, along multiple thematic dimensions in LBD situations.

Semantics-empowered text exploration for knowledge discovery

The interaction paradigm offered by most contemporary Web Information Systems is a search-and-sift paradigm in which users manually seek information using hyperlinked documents. This paradigm is derived from a document-centric model that gives users minimal support for scanning through high volumes of text. We present a novel information exploration paradigm based on a data-centric view of corpora, along with a prototype implementation that demonstrates the value in content-driven navigation. We leverage semantic metadata to link data in documents by exploiting named relationships between entities. We also present utilities for gathering user generated navigation trails, critical for knowledge discovery. We discuss the impact of our approach in the context of knowledge exploration.

Towards comprehensive longitudinal healthcare data capture

The ability to connect the dots in structured background knowledge and also across scientific literature has been demonstrated as a critical aspect of knowledge discovery. It is not unreasonable therefore to expect that connecting-the-dots across massive amounts of healthcare data may also lead to new insights that could impact diagnosis, treatment and overall patient care. Of critical importance is the observation that while structured Electronic Medical Records (EMR) are useful sources of health information, it is often the unstructured clinical texts such as progress notes and discharge summaries that contain rich, updated and granular information. Hence, by coupling structured EMR data with data from unstructured clinical texts, more holistic patient records, needed for connecting the dots, can be obtained. Unfortunately, free-text progress notes are fraught with a lack of proper grammatical structure, and contain liberal use of jargon and abbreviations, together with frequent misspellings. While these notes still serve their intended purpose for medical care, automatically extracting semantic information from them is a complex task. Overcoming this complexity could mean that evidence-based support for structured EMR data using unstructured clinical texts, can be provided. In this work therefore, we explore a pattern-based approach for extracting Smoker Semantic Types (SST) from unstructured clinical notes, in order to enable evidence-based resolution of SSTs asserted in structured EMRs using SSTs extracted from unstructured clinical notes. Our findings support the notion that information present in unstructured clinical text can be used to complement structured healthcare data. This is a crucial observation towards creating comprehensive longitudinal patient models for connecting-the-dots and providing better overall patient care.

Semantic Predications for Complex Information Needs in Biomedical Literature

Many complex information needs that arise in biomedical disciplines require exploring multiple documents in order to obtain information. While traditional information retrieval techniques that return a single ranked list of documents are quite common for such tasks, they may not always be adequate. The main issue is that ranked lists typically impose a significant burden on users to filter out irrelevant documents. Additionally, users must intuitively reformulate their search query when relevant documents have not been not highly ranked. Furthermore, even after interesting documents have been selected, very few mechanisms exist that enable document-to-document transitions. In this paper, we demonstrate the utility of assertions extracted from biomedical text (called semantic predications) to facilitate retrieving relevant documents for complex information needs. Our approach offers an alternative to query reformulation by establishing a framework for transitioning from one document to another. We evaluate this novel knowledge-driven approach using precision and recall metrics on the 2006 TREC Genomics Track.

A Taxonomy-Based Model for Expertise Extrapolation

While many Expert Finder applications succeed in finding experts, their techniques are not always designed to capture the various levels at which expertise can be expressed. Indeed, expertise can be inferred from relationships between topics and subtopics in a taxonomy. The conventional wisdom is that expertise in subtopics is also indicative of expertise in higher level topics as well. The enrichment of Expertise Profiles for finding experts can therefore be facilitated by taking domain hierarchies into account. We present a novel semantics-based model for finding experts, expertise levels and collaboration levels in a peer review context, such as composing a Program Committee (PC) for a conference. The implicit coauthorship network encompassed by bibliographic data enables the possibility of discovering unknown experts within various degrees of separation in the coauthorship graph. Our results show an average of 85% recall in finding experts, when evaluated against three WWW Conference PCs and close to 80 additional comparable experts outside the immediate collaboration network of the PC Chairs.

A context-driven subgraph model for literature-based discovery by Delroy Cameron with Prateek Jain as coordinator

Literature-Based Discovery (LBD) refers to the process of uncovering hidden connections that are implicit in scientific literature. Numerous hypotheses have been generated from scientific literature using the LBD paradigm, which influenced innovations in diagnosis, treatment, preventions and overall public health. However, much of the existing research on discovering hidden connections among concepts have used distributional statistics and graph-theoretic measures to capture implicit associations. Such metrics do not explicitly capture the semantics of hidden connections. Rather, they only allude to the existence of meaningful underlying associations. To gain in-depth insights into the meaning of hidden (and other) connections, complementary methods have often been employed. Some of these methods include: 1) the use of domain expertise for concept filtering and knowledge exploration, 2) leveraging structured background knowledge for context and to supplement concept filtering, and 3) developing heuristics a priori to help eliminate spurious connections.