Exploiting medical hierarchies for concept-based information retrieval

Search technologies are critical to enable clinical sta to rapidly and e ectively access patient information contained in free-text medical records. Medical search is challenging as terms in the query are often general but those in rel- evant documents are very speci c, leading to granularity mismatch. In this paper we propose to tackle granularity mismatch by exploiting subsumption relationships de ned in formal medical domain knowledge resources. In symbolic reasoning, a subsumption (or `is-a') relationship is a parent-child rela- tionship where one concept is a subset of another concept. Subsumed concepts are included in the retrieval function. In addition, we investigate a number of initial methods for combining weights of query concepts and those of subsumed concepts. Subsumption relationships were found to provide strong indication of relevant information; their inclusion in retrieval functions yields performance improvements. This result motivates the development of formal models of rela- tionships between medical concepts for retrieval purposes.

Exploiting SNOMED CT concepts and relationships for clinical information retrieval : Australian e-Health Research Centre and Queensland University of Technology at the TREC 2012 Medical Track

The Australian e-Health Research Centre and Queensland University of Technology recently participated in the TREC 2012 Medical Records Track. This paper reports on our methods, results and experience using an approach that exploits the concept and inter-concept relationships defined in the SNOMED CT medical ontology. Our concept-based approach is intended to overcome specific challenges in searching medical records, namely vocabulary mismatch and granularity mismatch. Queries and documents are transformed from their term-based originals into medical concepts as defined by the SNOMED CT ontology, this is done to tackle vocabulary mismatch. In addition, we make use of the SNOMED CT parent-child `is-a' relationships between concepts to weight documents that contained concept subsumed by the query concepts; this is done to tackle the problem of granularity mismatch. Finally, we experiment with other SNOMED CT relationships besides the is-a relationship to weight concepts related to query concepts. Results show our concept-based approach performed significantly above the median in all four performance metrics. Further improvements are achieved by the incorporation of weighting subsumed concepts, overall leading to improvement above the median of 28% infAP, 10% infNDCG, 12% R-prec and 7% Prec@10. The incorporation of other relations besides is-a demonstrated mixed results, more research is required to determined which SNOMED CT relationships are best employed when weighting related concepts.

Graph-based concept weighting for medical information retrieval

This paper presents a graph-based method to weight medical concepts in documents for the purposes of information retrieval. Medical concepts are extracted from free-text documents using a state-of-the-art technique that maps n-grams to concepts from the SNOMED CT medical ontology. In our graph-based concept representation, concepts are vertices in a graph built from a document, edges represent associations between concepts. This representation naturally captures dependencies between concepts, an important requirement for interpreting medical text, and a feature lacking in bag-of-words representations. We apply existing graph-based term weighting methods to weight medical concepts. Using concepts rather than terms addresses vocabulary mismatch as well as encapsulates terms belonging to a single medical entity into a single concept. In addition, we further extend previous graph-based approaches by injecting domain knowledge that estimates the importance of a concept within the global medical domain. Retrieval experiments on the TREC Medical Records collection show our method outperforms both term and concept baselines. More generally, this work provides a means of integrating background knowledge contained in medical ontologies into data-driven information retrieval approaches.

A tensor encoding model of word meaning : theory and application to information retrieval

This project was a step forward in developing and evaluating a novel, mathematical model that can deduce the meaning of words based on their use in language. This model can be applied to a wide range of natural language applications, including the information seeking process most of us undertake on a daily basis.

Combining word semantics within complex Hilbert space for information retrieval

Complex numbers are a fundamental aspect of the mathematical formalism of quantum physics. Quantum-like models developed outside physics often overlooked the role of complex numbers. Specifically, previous models in Information Retrieval (IR) ignored complex numbers. We argue that to advance the use of quantum models of IR, one has to lift the constraint of real-valued representations of the information space, and package more information within the representation by means of complex numbers. As a first attempt, we propose a complex-valued representation for IR, which explicitly uses complex valued Hilbert spaces, and thus where terms, documents and queries are represented as complex-valued vectors. The proposal consists of integrating distributional semantics evidence within the real component of a term vector; whereas, ontological information is encoded in the imaginary component. Our proposal has the merit of lifting the role of complex numbers from a computational byproduct of the model to the very mathematical texture that unifies different levels of semantic information. An empirical instantiation of our proposal is tested in the TREC Medical Record task of retrieving cohorts for clinical studies.

Understanding negation and family history to improve clinical information retrieval

We present a study to understand the effect that negated terms (e.g., "no fever") and family history (e.g., "family history of diabetes") have on searching clinical records. Our analysis is aimed at devising the most effective means of handling negation and family history. In doing so, we explicitly represent a clinical record according to its different content types: negated, family history and normal content; the retrieval model weights each of these separately. Empirical evaluation shows that overall the presence of negation harms retrieval effectiveness while family history has little effect. We show negation is best handled by weighting negated content (rather than the common practise of removing or replacing it). However, we also show that many queries benefit from the inclusion of negated content and that negation is optimally handled on a per-query basis. Additional evaluation shows that adaptive handing of negated and family history content can have significant benefits.

Document clustering algorithms, representations and evaluation for information retrieval

This thesis presents new methods for classification and thematic grouping of billions of web pages, at scales previously not achievable. This process is also known as document clustering, where similar documents are automatically associated with clusters that represent various distinct topic. These automatically discovered topics are in turn used to improve search engine performance by only searching the topics that are deemed relevant to particular user queries.

Migrants, refugees and mobility : how useful are information communication technologies in the first phase of resettlement?

The rate at which people move and resettle around the world is unprecedented. Mobility and resettlement is now greatly assisted by the use of inexpensive internet communication technologies (ICTs) for a wide variety of functions: to communicate locally and across territories, for localised information seeking, geo – locational mapping and for forging new social connections in host countries and cities. This article is based on a qualitative study of newly arrived migrants and mobile people from non English speaking backgrounds (NESB) to the city of Brisbane, Australia and investigates how the internet is used to assist the initial period of settling into the city. As increasing amounts of essential information is placed online, the study asks how people from NESB communities manage to negotiate the types of information they require during the early stages of resettlement, given varying levels of access to ICTs, digital and language literacy. The study finds that the internet is widely used for specific location information seeking (such as accommodation and job-seeking), but this is often supplemented with other non-mediated sources of information. The study identified implications for social policy in regard to the resourcing and access of information. While findings are specific to the study location, it is feasible that the patterns of internet use for resettlement have relevance in a broader context.

How everyday language can and will boost effective information retrieval

Typing 2 or 3 keywords into a browser has become an easy and efficient way to find information. Yet, typing even short queries becomes tedious on ever shrinking (virtual) keyboards. Meanwhile, speech processing is maturing rapidly, facilitating everyday language input. Also, wearable technology can inform users proactively by listening in on their conversations or processing their social media interactions. Given these developments, everyday language may soon become the new input of choice. We present an information retrieval (IR) algorithm specifically designed to accept everyday language. It integrates two paradigms of information retrieval, previously studied in isolation; one directed mainly at the surface structure of language, the other primarily at the underlying meaning. The integration was achieved by a Markov machine that encodes meaning by its transition graph, and surface structure by the language it generates. A rigorous evaluation of the approach showed, first, that it can compete with the quality of existing language models, second, that it is more effective the more verbose the input, and third, as a consequence, that it is promising for an imminent transition from keyword input, where the onus is on the user to formulate concise queries, to a modality where users can express more freely, more informal, and more natural their need for information in everyday language.

Integrating and evaluating neural word embeddings in information retrieval

Recent advances in neural language models have contributed new methods for learning distributed vector representations of words (also called word embeddings). Two such methods are the continuous bag-of-words model and the skipgram model. These methods have been shown to produce embeddings that capture higher order relationships between words that are highly effective in natural language processing tasks involving the use of word similarity and word analogy. Despite these promising results, there has been little analysis of the use of these word embeddings for retrieval. Motivated by these observations, in this paper, we set out to determine how these word embeddings can be used within a retrieval model and what the benefit might be. To this aim, we use neural word embeddings within the well known translation language model for information retrieval. This language model captures implicit semantic relations between the words in queries and those in relevant documents, thus producing more accurate estimations of document relevance. The word embeddings used to estimate neural language models produce translations that differ from previous translation language model approaches; differences that deliver improvements in retrieval effectiveness. The models are robust to choices made in building word embeddings and, even more so, our results show that embeddings do not even need to be produced from the same corpus being used for retrieval.