Ann Gledson

Using Web-Search Results to Measure Word-Group Similarity

Semantic relatedness between words is important to many NLP tasks, and numerous measures exist which use a variety of resources. Thus far, such work is confined to measuring similarity between two words (or two texts), and only a handful utilize the web as a corpus. This paper introduces a distributional similarity measure which uses internet search counts and also extends to calculating the similarity within word-groups. The evaluation results are encouraging: for word-pairs, the correlations with human judgments are comparable with state-of-the-art web-search page-count heuristics. When used to measure similarities within sets of 10 words, the results correlate highly (up to 0.8) with those expected. Relatively little comparison has been made between the results of different search-engines. Here, we compare experimental results from Google, Windows Live Search and Yahoo and find noticeable differences.

Decision support systems for clinical radiological practice — towards the next generation

The huge amount of information that needs to be assimilated in order to keep pace with the continued advances in modern medical practice can form an insurmountable obstacle to the individual clinician. Within radiology, the recent development of quantitative imaging techniques, such as perfusion imaging, and the development of imaging-based biomarkers in modern therapeutic assessment has highlighted the need for computer systems to provide the radiological community with support for academic as well as clinical/translational applications. This article provides an overview of the underlying design and functionality of radiological decision support systems with examples tracing the development and evolution of such systems over the past 40 years. More importantly, we discuss the specific design, performance and usage characteristics that previous systems have highlighted as being necessary for clinical uptake and routine use. Additionally, we have identified particular failings in our current methodologies for data dissemination within the medical domain that must be overcome if the next generation of decision support systems is to be implemented successfully.

Which computer-use behaviours are most indicative of cognitive decline? Insights from an expert reference group

Computer use is becoming ubiquitous among older adults. As computer use depends on complex cognitive functions, measuring individuals’ computer-use behaviours over time may provide a way to detect changes in their cognitive functioning. However, it is uncertain which computer-use behaviour changes are most likely to be associated with declines of particular cognitive functions. To address this, we convened six experts from clinical and cognitive neurosciences to take part in two workshops and a follow-up survey to gain consensus on which computer-use behaviours would likely be the strongest indicators of cognitive decline. This resulted in a list of 21 computer-use behaviours that the majority of experts agreed would offer a ‘strong indication’ of decline in a specific cognitive function, across Memory, Executive function, Language and Perception and Action domains. This list enables a hypothesis-driven approach to analysing computer-use behaviours predicted to be markers of cognitive decline.

Quantification of structural changes in the corpus callosumin children with profound hypoxic–ischaemic brain injury

BackgroundBirth-related acute profound hypoxic–ischaemic brain injury has specific patterns of damage including the paracentral lobules.ObjectiveTo test the hypothesis that there is anatomically coherent regional volume loss of the corpus callosum as a result of this hemispheric abnormality.Materials and methodsStudy subjects included 13 children with proven acute profound hypoxic–ischaemic brain injury and 13 children with developmental delay but no brain abnormalities. A computerised system divided the corpus callosum into 100 segments, measuring each width. Principal component analysis grouped the widths into contiguous anatomical regions. We conducted analysis of variance of corpus callosum widths as well as support vector machine stratification into patient groups.ResultsThere was statistically significant narrowing of the mid–posterior body and genu of the corpus callosum in children with hypoxic–ischaemic brain injury. Support vector machine analysis yielded over 95% accuracy in patient group stratification using the corpus callosum centile widths.ConclusionFocal volume loss is seen in the corpus callosum of children with hypoxic–ischaemic brain injury secondary to loss of commissural fibres arising in the paracentral lobules. Support vector machine stratification into the hypoxic–ischaemic brain injury group or the control group on the basis of corpus callosum width is highly accurate and points towards rapid clinical translation of this technique as a potential biomarker of hypoxic–ischaemic brain injury.

Measuring Topic Homogeneity and its Application to Dictionary-Based Word Sense Disambiguation

The use of topical features is abundant in Natural Language Processing (NLP), a major example being in dictionary-based Word Sense Disambiguation (WSD). Yet previous research does not attempt to measure the level of topic cohesion in documents, despite assertions of its effects. This paper introduces a quantitative measure of Topic Homogeneity using a range of NLP resources and not requiring prior knowledge of correct senses. Evaluation is performed firstly by using the WordNet::Domains package to create word-sets with varying levels of homogeneity and comparing our results with those expected. Additionally, to evaluate each measures potential value, the homogeneity results are correlated against those of 3 co-occurrence/dictionary-based WSD techniques, tested on 1040 Semcor and SENSEVAL sub-documents. Many low-moderate correlations are found to exist with several in the moderate range (above .40). These correlations surpass polysemy and senseentropy, the 2 most cited factors affecting WSD. Finally, a combined homogeneity measure achieves correlations of up to .52.

Can you detect early dementia from an email? : A proof of principle study of daily computer use to detect cognitive and functional decline

To determine whether multiple computer use behaviours can distinguish between cognitively healthy older adults and those in the early stages of cognitive decline, and to investigate whether these behaviours are associated with cognitive and functional ability.

A Bayesian Association Rule Mining Algorithm

This paper proposes a Bayesian association rule mining algorithm (BAR) which combines the Apriori association rule mining algorithm with Bayesian networks. Two interesting-ness measures of association rules: Bayesian confidence (BC) and Bayesian lift (BL) which measure conditional dependence and independence relationships between items are defined based on the joint probabilities represented by the Bayesian networks of association rules. BAR outputs best rules according to BC and BL. BAR is evaluated for its performance using two anonymized clinical phenotype datasets from the UCI Repository: Thyroid disease and Diabetes. The results show that BAR is capable of finding the best rules which have the highest BC, BL and very high support, confidence and lift.

Known and unknown requirements in healthcare

We report experience in requirements elicitation of domain knowledge from experts in clinical and cognitive neurosciences. The elicitation target was a causal model for early signs of dementia indicated by changes in user behaviour and errors apparent in logs of computer activity. A Delphi-style process consisting of workshops with experts followed by a questionnaire was adopted. The paper describes how the elicitation process had to be adapted to deal with problems encountered in terminology and limited consensus among the experts. In spite of the difficulties encountered, a partial causal model of user behavioural pathologies and errors was elicited. This informed requirements for configuring data- and text-mining tools to search for the specific data patterns. Lessons learned for elicitation from experts are presented, and the implications for requirements are discussed as “unknown unknowns”, as well as configuration requirements for directing data-/text-mining tools towards refining awareness requirements in healthcare applications.