Medical semantic similarity with a neural language model

Advances in neural network language models have demonstrated that these models can effectively learn representations of words meaning. In this paper, we explore a variation of neural language models that can learn on concepts taken from structured ontologies and extracted from free-text, rather than directly from terms in free-text. This model is employed for the task of measuring semantic similarity between medical concepts, a task that is central to a number of techniques in medical informatics and information retrieval. The model is built with two medical corpora (journal abstracts and patient records) and empirically validated on two ground-truth datasets of human-judged concept pairs assessed by medical professionals. Empirically, our approach correlates closely with expert human assessors ($\approx$ 0.9) and outperforms a number of state-of-the-art benchmarks for medical semantic similarity. The demonstrated superiority of this model for providing an effective semantic similarity measure is promising in that this may translate into effectiveness gains for techniques in medical information retrieval and medical informatics (e.g., query expansion and literature-based discovery).

The ghost in the machine: Legal challenges of neural interface devices

Neural interface devices and the melding of mind and machine, challenge the law in determining where civil liability for injury, damage or loss should lie. The ability of the human mind to instruct and control these devices means that in a negligence action against a person with a neural interface device, determining the standard of care owed by him or her will be of paramount importance. This article considers some of the factors that may influence the court’s determination of the appropriate standard of care to be applied in this situation, leading to the conclusion that a new standard of care might evolve.

Investigating the impact of project definition clarity on project performance: Structural equation modeling study

Having a clear project definition is crucial for successful construction projects. It affects design quality, project communication between stakeholders and final project performance in terms of cost, schedule and quality. This study examines the relationship between project definition and final project performance through a structural equation model comprising 4 latent constructs and 6 path hypotheses using data from a questionnaire survey of 120 general contractors in the Malaysian construction industry. The results show that in the study population, all three items impact the project performance, but the link between design quality and project performance is indirect. Instead, the clarity of project definition affects project performance indirectly through design quality and project communication and design quality affects project performance indirectly through project communication. The primary contribution is to provide quantitative confirmation of the more general statements made in the literature from around the world and therefore adds to and consolidates existing knowledge. Practical implications derived from the finding are also proposed for various project stakeholders. Furthermore, as lack of the clarity of project definition is a very common occurrence in construction projects globally, these findings have important ramifications for all construction projects in expanding and clarifying existing knowledge on what is needed for the successful delivery of construction projects.

Numerical modeling of thin steel roof battens under wind uplift loads

Extreme wind events such as tropical cyclones, tornadoes and storms are more likely to impact the Australian coastal regions due to possible climate changes. Such events can be extremely destructive to building structures, in particular, low-rise buildings with lightweight roofing systems that are commonly made of thin steel roofing sheets and battens. Large wind uplift loads that act on the roofs during high wind events often cause premature roof connection failures. Recent wind damage investigations have shown that roof failures have mostly occurred at the batten to rafter or truss screw connections. In most of these cases, the screw fastener heads pulled through the bottom flanges of thin steel roof battens. This roof connection failure is very critical as both roofing sheets and battens will be lost during the high wind events. Hence, a research study was conducted to investigate this critical pull-through failure using both experimental and numerical methods. This paper presents the details of numerical modeling and the results.

Quantitative genetic modeling of lateral ventricular shape and volume using multi-atlas fluid image alignment in twins

Despite substantial progress in measuring the 3D profile of anatomical variations in the human brain, their genetic and environmental causes remain enigmatic. We developed an automated system to identify and map genetic and environmental effects on brain structure in large brain MRI databases . We applied our multi-template segmentation approach ("Multi-Atlas Fluid Image Alignment") to fluidly propagate hand-labeled parameterized surface meshes into 116 scans of twins (60 identical, 56 fraternal), labeling the lateral ventricles. Mesh surfaces were averaged within subjects to minimize segmentation error. We fitted quantitative genetic models at each of 30,000 surface points to measure the proportion of shape variance attributable to (1) genetic differences among subjects, (2) environmental influences unique to each individual, and (3) shared environmental effects. Surface-based statistical maps revealed 3D heritability patterns, and their significance, with and without adjustments for global brain scale. These maps visualized detailed profiles of environmental versus genetic influences on the brain, extending genetic models to spatially detailed, automatically computed, 3D maps.

Neural correlates of semantic priming for ambiguous words: An event-related fMRI study

We investigated the neural correlates of semantic priming by using event-related fMRI to record blood oxygen level dependent (BOLD) responses while participants performed speeded lexical decisions (word/nonword) on visually presented related versus unrelated prime-target pairs. A long stimulus onset asynchrony of 1000 ms was employed, which allowed for increased controlled processing and selective frequency-based ambiguity priming. Conditions included an ambiguous word prime (e.g. bank) and a target related to its dominant (e.g. money) or subordinate meaning (e.g. river). Compared to an unrelated condition, primed dominant targets were associated with increased activity in the LIFG, the right anterior cingulate and superior temporal gyrus, suggesting postlexical semantic integrative mechanisms, while increased right supramarginal activity for the unrelated condition was consistent with expectancy based priming. Subordinate targets were not primed and were associated with reduced activity primarily in occipitotemporal regions associated with word recognition, which may be consistent with frequency-based meaning suppression. These findings provide new insights into the neural substrates of semantic priming and the functional-anatomic correlates of lexical ambiguity suppression mechanisms.

Brain structure in healthy adults is related to serum transferrin and the H63D polymorphism in the HFE gene

Control of iron homeostasis is essential for healthy central nervous system function: iron deficiency is associated with cognitive impairment, yet iron overload is thought to promote neurodegenerative diseases. Specific genetic markers have been previously identified that influence levels of transferrin, the protein that transports iron throughout the body, in the blood and brain. Here, we discovered that transferrin levels are related to detectable differences in the macro- and microstructure of the living brain. We collected brain MRI scans from 615 healthy young adult twins and siblings, of whom 574 were also scanned with diffusion tensor imaging at 4 Tesla. Fiber integrity was assessed by using the diffusion tensor imaging-based measure of fractional anisotropy. In bivariate genetic models based on monozygotic and dizygotic twins, we discovered that partially overlapping additive genetic factors influenced transferrin levels and brain microstructure. We also examined common variants in genes associated with transferrin levels, TF and HFE, and found that a commonly carried polymorphism (H63D at rs1799945) in the hemochromatotic HFE gene was associated with white matter fiber integrity. This gene has a well documented association with iron overload. Our statistical maps reveal previously unknown influences of the same gene on brain microstructure and transferrin levels. This discovery may shed light on the neural mechanisms by which iron affects cognition, neurodevelopment, and neurodegeneration.

4D deformation modeling of cortical disease progression in Alzheimer's dementia

This work describes the development of a model of cerebral atrophic changes associated with the progression of Alzheimer's disease (AD). Linear registration, region-of-interest analysis, and voxel-based morphometry methods have all been employed to elucidate the changes observed at discrete intervals during a disease process. In addition to describing the nature of the changes, modeling disease-related changes via deformations can also provide information on temporal characteristics. In order to continuously model changes associated with AD, deformation maps from 21 patients were averaged across a novel z-score disease progression dimension based on Mini Mental State Examination (MMSE) scores. The resulting deformation maps are presented via three metrics: local volume loss (atrophy), volume (CSF) increase, and translation (interpreted as representing collapse of cortical structures). Inspection of the maps revealed significant perturbations in the deformation fields corresponding to the entorhinal cortex (EC) and hippocampus, orbitofrontal and parietal cortex, and regions surrounding the sulci and ventricular spaces, with earlier changes predominantly lateralized to the left hemisphere. These changes are consistent with results from post-mortem studies of AD.

Modeling of the hemodynamic responses in block design fMRI studies

The hemodynamic response function (HRF) describes the local response of brain vasculature to functional activation. Accurate HRF modeling enables the investigation of cerebral blood flow regulation and improves our ability to interpret fMRI results. Block designs have been used extensively as fMRI paradigms because detection power is maximized; however, block designs are not optimal for HRF parameter estimation. Here we assessed the utility of block design fMRI data for HRF modeling. The trueness (relative deviation), precision (relative uncertainty), and identifiability (goodness-of-fit) of different HRF models were examined and test-retest reproducibility of HRF parameter estimates was assessed using computer simulations and fMRI data from 82 healthy young adult twins acquired on two occasions 3 to 4 months apart. The effects of systematically varying attributes of the block design paradigm were also examined. In our comparison of five HRF models, the model comprising the sum of two gamma functions with six free parameters had greatest parameter accuracy and identifiability. Hemodynamic response function height and time to peak were highly reproducible between studies and width was moderately reproducible but the reproducibility of onset time was low. This study established the feasibility and test-retest reliability of estimating HRF parameters using data from block design fMRI studies.

Neural activity associated with semantic versus phonological anomia treatments in aphasia

Naming impairments in aphasia are typically targeted using semantic and/or phonologically based tasks. However, it is not known whether these treatments have different neural mechanisms. Eight participants with aphasia received twelve treatment sessions using an alternating treatment design, with fMRI scans pre- and post-treatment. Half the sessions employed Phonological Components Analysis (PCA), and half the sessions employed Semantic Feature Analysis (SFA). Pre-treatment activity in the left caudate correlated with greater immediate treatment success for items treated with SFA, whereas recruitment of the left supramarginal gyrus and right precuneus post-treatment correlated with greater immediate treatment success for items treated with PCA. The results support previous studies that have found greater treatment outcome to be associated with activity in predominantly left hemisphere regions, and suggest that different mechanisms may be engaged dependent on the type of treatment employed.

Linking business goals to process models in semantic business process modeling

Broad knowledge is required when a business process is modeled by a business analyst. We argue that existing Business Process Management methodologies do not consider business goals at the appropriate level. In this paper we present an approach to integrate business goals and business process models. We design a Business Goal Ontology for modeling business goals. Furthermore, we devise a modeling pattern for linking the goals to process models and show how the ontology can be used in query answering. In this way, we integrate the intentional perspective into our business process ontology framework, enriching the process description and enabling new types of business process analysis. © 2008 IEEE.

Improving deep convultional neural networks with unsupervised feature learning

The latest generation of Deep Convolutional Neural Networks (DCNN) have dramatically advanced challenging computer vision tasks, especially in object detection and object classification, achieving state-of-the-art performance in several computer vision tasks including text recognition, sign recognition, face recognition and scene understanding. The depth of these supervised networks has enabled learning deeper and hierarchical representation of features. In parallel, unsupervised deep learning such as Convolutional Deep Belief Network (CDBN) has also achieved state-of-the-art in many computer vision tasks. However, there is very limited research on jointly exploiting the strength of these two approaches. In this paper, we investigate the learning capability of both methods. We compare the output of individual layers and show that many learnt filters and outputs of the corresponding level layer are almost similar for both approaches. Stacking the DCNN on top of unsupervised layers or replacing layers in the DCNN with the corresponding learnt layers in the CDBN can improve the recognition/classification accuracy and training computational expense. We demonstrate the validity of the proposal on ImageNet dataset.

A framework for freeway incident modeling and traffic re-routing

This paper proposes an analytical Incident Traffic Management framework for freeway incident modeling and traffic re-routing. The proposed framework incorporates an econometric incident duration model and a traffic re-routing optimization module. The incident duration model is used to estimate the expected duration of the incident and thus determine the planning horizon for the re-routing module. The re-routing module is a CTM-based Single Destination System Optimal Dynamic Traffic Assignment model that generates optimal real-time strategies of re-routing freeway traffic to its adjacent arterial network during incidents. The proposed framework has been applied to a case study network including a freeway and its adjacent arterial network in South East Queensland, Australia. The results from different scenarios of freeway demand and incident blockage extent have been analyzed and advantages of the proposed framework are demonstrated.

Conformational epitopes on the diabetes autoantigen GAD65 identified by peptide phage display and molecular modeling

The major diabetes autoantigen, glutamic acid decarboxylase (GAD65), contains a region of sequence similarity, including six identical residues PEVKEK, to the P2C protein of coxsackie B virus, suggesting that cross-reactivity between coxsackie B virus and GAD65 can initiate autoimmune diabetes. We used the human islet cell mAbs MICA3 and MICA4 to identify the Ab epitopes of GAD65 by screening phage-displayed random peptide libraries. The identified peptide sequences could be mapped to a homology model of the pyridoxal phosphate (PLP) binding domain of GAD65. For MICA3, a surface loop containing the sequence PEVKEK and two adjacent exposed helixes were identified in the PLP binding domain as well as a region of the C terminus of GAD65 that has previously been identified as critical for MICA3 binding. To confirm that the loop containing tile PEVKEK sequence contributes to the MICA3 epitope, this loop was deleted by mutagenesis. This reduced binding of MICA3 by 70%. Peptide sequences selected using MICA4 were rich in basic or hydroxyl-containing amino acids, and the surface of the GAD65 PLP-binding domain surrounding Lys358, which is known to be critical for MICA4 binding, was likewise rich in these amino acids. Also, the two phage most reactive width MICA4 encoded the motif VALxG, and the reverse of this sequence, LAV, was located in this same region. Thus, we have defined the MICA3 and MICA4 epitopes on GAD65 using the combination of phage display, molecular modeling, and mutagenesis and have provided compelling evidence for the involvement of the PEVKEK loop in the MICA3 epitope.