Automatic de-identification of electronic health records : an Australian perspective

We present an approach to automatically de-identify health records. In our approach, personal health information is identified using a Conditional Random Fields machine learning classifier, a large set of linguistic and lexical features, and pattern matching techniques. Identified personal information is then removed from the reports. The de-identification of personal health information is fundamental for the sharing and secondary use of electronic health records, for example for data mining and disease monitoring. The effectiveness of our approach is first evaluated on the 2007 i2b2 Shared Task dataset, a widely adopted dataset for evaluating de-identification techniques. Subsequently, we investigate the robustness of the approach to limited training data; we study its effectiveness on different type and quality of data by evaluating the approach on scanned pathology reports from an Australian institution. This data contains optical character recognition errors, as well as linguistic conventions that differ from those contained in the i2b2 dataset, for example different date formats. The findings suggest that our approach compares to the best approach from the 2007 i2b2 Shared Task; in addition, the approach is found to be robust to variations of training size, data type and quality in presence of sufficient training data.

De-Identification of health records using Anonym: Effectiveness and robustness across datasets

Objective Evaluate the effectiveness and robustness of Anonym, a tool for de-identifying free-text health records based on conditional random fields classifiers informed by linguistic and lexical features, as well as features extracted by pattern matching techniques. De-identification of personal health information in electronic health records is essential for the sharing and secondary usage of clinical data. De-identification tools that adapt to different sources of clinical data are attractive as they would require minimal intervention to guarantee high effectiveness. Methods and Materials The effectiveness and robustness of Anonym are evaluated across multiple datasets, including the widely adopted Integrating Biology and the Bedside (i2b2) dataset, used for evaluation in a de-identification challenge. The datasets used here vary in type of health records, source of data, and their quality, with one of the datasets containing optical character recognition errors. Results Anonym identifies and removes up to 96.6% of personal health identifiers (recall) with a precision of up to 98.2% on the i2b2 dataset, outperforming the best system proposed in the i2b2 challenge. The effectiveness of Anonym across datasets is found to depend on the amount of information available for training. Conclusion Findings show that Anonym compares to the best approach from the 2006 i2b2 shared task. It is easy to retrain Anonym with new datasets; if retrained, the system is robust to variations of training size, data type and quality in presence of sufficient training data.

Semantic interference in object naming : an fMRI study of the postcue naming paradigm

It is well established that the time to name target objects can be influenced by the presence of categorically related versus unrelated distractor items. A variety of paradigms have been developed to determine the level at which this semantic interference effect occurs in the speech production system. In this study, we investigated one of these tasks, the postcue naming paradigm, for the first time with fMRI. Previous behavioural studies using this paradigm have produced conflicting interpretations of the processing level at which the semantic interference effect takes place, ranging from pre- to post-lexical. Here we used fMRI with a sparse, event-related design to adjudicate between these competing explanations. We replicated the behavioural postcue naming effect for categorically related target/distractor pairs, and observed a corresponding increase in neuronal activation in the right lingual and fusiform gyri-regions previously associated with visual object processing and colour-form integration. We interpret these findings as being consistent with an account that places the semantic interference effect in the postcue paradigm at a processing level involving integration of object attributes in short-term memory.

Semantic context and visual feature effects in object naming : an fMRI study using arterial spin labeling

Previous behavioral studies reported a robust effect of increased naming latencies when objects to be named were blocked within semantic category, compared to items blocked between category. This semantic context effect has been attributed to various mechanisms including inhibition or excitation of lexico-semantic representations and incremental learning of associations between semantic features and names, and is hypothesized to increase demands on verbal self-monitoring during speech production. Objects within categories also share many visual structural features, introducing a potential confound when interpreting the level at which the context effect might occur. Consistent with previous findings, we report a significant increase in response latencies when naming categorically related objects within blocks, an effect associated with increased perfusion fMRI signal bilaterally in the hippocampus and in the left middle to posterior superior temporal cortex. No perfusion changes were observed in the middle section of the left middle temporal cortex, a region associated with retrieval of lexical-semantic information in previous object naming studies. Although a manipulation of visual feature similarity did not influence naming latencies, we observed perfusion increases in the perirhinal cortex for naming objects with similar visual features that interacted with the semantic context in which objects were named. These results provide support for the view that the semantic context effect in object naming occurs due to an incremental learning mechanism, and involves increased demands on verbal self-monitoring.

Using textual analysis with Concept Inventories to identify root causes of misconceptions

Engineers must have deep and accurate conceptual understanding of their field and Concept inventories (CIs) are one method of assessing conceptual understanding and providing formative feedback. Current CI tests use Multiple Choice Questions (MCQ) to identify misconceptions and have undergone reliability and validity testing to assess conceptual understanding. However, they do not readily provide the diagnostic information about students’ reasoning and therefore do not effectively point to specific actions that can be taken to improve student learning. We piloted the textual component of our diagnostic CI on electrical engineering students using items from the signals and systems CI. We then analysed the textual responses using automated lexical analysis software to test the effectiveness of these types of software and interviewed the students regarding their experience using the textual component. Results from the automated text analysis revealed that students held both incorrect and correct ideas for certain conceptual areas and provided indications of student misconceptions. User feedback also revealed that the inclusion of the textual component is helpful to students in assessing and reflecting on their own understanding.

Text mining with semantic annotation : using enriched text representation for entity-oriented retrieval, semantic relation identification and text clustering

This project is a step forward in the study of text mining where enhanced text representation with semantic information plays a significant role. It develops effective methods of entity-oriented retrieval, semantic relation identification and text clustering utilizing semantically annotated data. These methods are based on enriched text representation generated by introducing semantic information extracted from Wikipedia into the input text data. The proposed methods are evaluated against several start-of-art benchmarking methods on real-life data-sets. In particular, this thesis improves the performance of entity-oriented retrieval, identifies different lexical forms for an entity relation and handles clustering documents with multiple feature spaces.

Using automated text analysis to evaluate students’ conceptual understanding

Background: A major challenge for assessing students’ conceptual understanding of STEM subjects is the capacity of assessment tools to reliably and robustly evaluate student thinking and reasoning. Multiple-choice tests are typically used to assess student learning and are designed to include distractors that can indicate students’ incomplete understanding of a topic or concept based on which distractor the student selects. However, these tests fail to provide the critical information uncovering the how and why of students’ reasoning for their multiple-choice selections. Open-ended or structured response questions are one method for capturing higher level thinking, but are often costly in terms of time and attention to properly assess student responses. Purpose: The goal of this study is to evaluate methods for automatically assessing open-ended responses, e.g. students’ written explanations and reasoning for multiple-choice selections. Design/Method: We incorporated an open response component for an online signals and systems multiple-choice test to capture written explanations of students’ selections. The effectiveness of an automated approach for identifying and assessing student conceptual understanding was evaluated by comparing results of lexical analysis software packages (Leximancer and NVivo) to expert human analysis of student responses. In order to understand and delineate the process for effectively analysing text provided by students, the researchers evaluated strengths and weakness for both the human and automated approaches. Results: Human and automated analyses revealed both correct and incorrect associations for certain conceptual areas. For some questions, that were not anticipated or included in the distractor selections, showing how multiple-choice questions alone fail to capture the comprehensive picture of student understanding. The comparison of textual analysis methods revealed the capability of automated lexical analysis software to assist in the identification of concepts and their relationships for large textual data sets. We also identified several challenges to using automated analysis as well as the manual and computer-assisted analysis. Conclusions: This study highlighted the usefulness incorporating and analysing students’ reasoning or explanations in understanding how students think about certain conceptual ideas. The ultimate value of automating the evaluation of written explanations is that it can be applied more frequently and at various stages of instruction to formatively evaluate conceptual understanding and engage students in reflective

Individual differences in the processing of punishment and reward cues : an application to road safety messages

This thesis examined the extent to which individual differences, as conceptualised by the revised Reinforcement Sensitivity Theory, influenced young drivers' information processing and subsequent acceptance of anti-speeding messages. Using a multi-method approach, the findings highlighted the utility of combining objective measures (a cognitive response time task and electroencephalography) with self-report measures to assess message processing and message acceptance, respectively. This body of research indicated that responses to anti-speeding messages may differ depending on an individual's personality disposition. Overall, the research provided further insight into the development of message strategies to target high risk drivers.

Estimating second language productive vocabulary size: A Capture-Recapture approach

This study provides validity evidence for the Capture-Recapture (CR) method, borrowed from ecology, as a measure of second language (L2) productive vocabulary size (PVS). Two separate “captures” of productive vocabulary were taken using written word association tasks (WAT). At Time 1, 47 bilinguals provided at least 4 associates to each of 30 high-frequency stimulus words in English, their first language (L1), and in French, their L2. A few days later (Time 2), this procedure was repeated with a different set of stimulus words in each language. Since the WAT was used, both Lex30 and CR PVS scores were calculated in each language. Participants also completed an animacy judgment task assessing the speed and efficiency of lexical access. Results indicated that, in both languages, CR and Lex30 scores were significantly positively correlated (evidence of convergent validity). CR scores were also significantly larger in the L1, and correlated significantly with the speed of lexical access in the L2 (evidence of construct validity). These results point to the validity of the technique for estimating relative L2 PVS. However, CR scores are not a direct indication of absolute vocabulary size. A discussion of the method’s underlying assumptions and their implications for interpretation are provided.

Probabilistic orthographic cues to grammatical category in the brain

What helps us determine whether a word is a noun or a verb, without conscious awareness? We report on cues in the way individual English words are spelled, and, for the first time, identify their neural correlates via functional magnetic resonance imaging (fMRI). We used a lexical decision task with trisyllabic nouns and verbs containing orthographic cues that are either consistent or inconsistent with the spelling patterns of words from that grammatical category. Significant linear increases in response times and error rates were observed as orthography became less consistent, paralleled by significant linear decreases in blood oxygen level dependent (BOLD) signal in the left supramarginal gyrus of the left inferior parietal lobule, a brain region implicated in visual word recognition. A similar pattern was observed in the left superior parietal lobule. These findings align with an emergentist view of grammatical category processing which results from sensitivity to multiple probabilistic cues.

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 activity during automatic semantic priming revealed by event-related functional magnetic resonance imaging

Semantic priming occurs when a subject is faster in recognising a target word when it is preceded by a related word compared to an unrelated word. The effect is attributed to automatic or controlled processing mechanisms elicited by short or long interstimulus intervals (ISIs) between primes and targets. We employed event-related functional magnetic resonance imaging (fMRI) to investigate blood oxygen level dependent (BOLD) responses associated with automatic semantic priming using an experimental design identical to that used in standard behavioural priming tasks. Prime-target semantic strength was manipulated by using lexical ambiguity primes (e.g., bank) and target words related to dominant or subordinate meaning of the ambiguity. Subjects made speeded lexical decisions (word/nonword) on dominant related, subordinate related, and unrelated word pairs presented randomly with a short ISI. The major finding was a pattern of reduced activity in middle temporal and inferior prefrontal regions for dominant versus unrelated and subordinate versus unrelated comparisons, respectively. These findings are consistent with both a dual process model of semantic priming and recent repetition priming data that suggest that reductions in BOLD responses represent neural priming associated with automatic semantic activation and implicate the left middle temporal cortex and inferior prefrontal cortex in more automatic aspects of semantic processing.

Dopaminergic neuromodulation of semantic processing: A 4-T fMRI study with levodopa

There is emerging evidence that alterations in dopaminergic transmission can influence semantic processing, yet the neural mechanisms involved are unknown. The influence of levodopa (L-DOPA) on semantic priming was investigated in healthy individuals (n=20) using event-related functional magnetic resonance imaging with a randomized, double-blind crossover design. Critical prime-target pairs consisted of a lexical ambiguity prime and 1) a target related to the dominant meaning of the prime (e.g., bank-money), 2) a target related to the subordinate meaning (e.g., fence-sword), or 3) an unrelated target (e.g., ball-desk). Behavioral data showed that both dominant and subordinate meanings were primed on placebo. In contrast, there was preserved priming of dominant meanings and no significant priming of subordinate meanings on L-DOPA, the latter associated with decreased anterior cingulate and dorsal prefrontal cortex activity. Dominant meaning activation on L-DOPA was associated with increased activity in the left rolandic operculum and left middle temporal gyrus. These findings suggest that L-DOPA enhances frequency-based semantic focus via prefrontal and temporal modulation of automatic semantic priming and through engagement of anterior cingulate mechanisms supporting attentional/controlled priming.

A perfusion fMRI investigation of thematic and categorical context effects in the spoken production of object names

The context in which objects are presented influences the speed at which they are named. We employed the blocked cyclic naming paradigm and perfusion functional magnetic resonance imaging (fMRI) to investigate the mechanisms responsible for interference effects reported for thematicallyand categorically related compared to unrelated contexts. Naming objects in categorically homogeneous contexts induced a significant interference effect that accumulated from the second cycle onwards. This interference effect was associated with significant perfusion signal decreases in left middle and posterior lateral temporal cortex and the hippocampus. By contrast, thematically homogeneous contexts facilitated naming latencies significantly in the first cycle and did not differ from heterogeneous contexts thereafter, nor were they associated with any perfusion signal changes compared to heterogeneous contexts. These results are interpreted as being consistent with an account in which the interference effect both originates and has its locus at the lexical level, with an incremental learning mechanism adapting the activation levels of target lexical representations following access. We discuss the implications of these findings for accounts that assume thematic relations can be active lexical competitors or assume mandatory involvement of top-down control mechanisms in interference effects during naming.

Differential processing of thematic and categorical conceptual relations in spoken word production

Studies of semantic context effects in spoken word production have typically distinguished between categorical (or taxonomic) and associative relations. However, associates tend to confound semantic features or morphological representations, such as whole-part relations and compounds (e.g., BOAT-anchor, BEE-hive). Using a picture-word interference paradigm and functional magnetic resonance imaging (fMRI), we manipulated categorical (COW-rat) and thematic (COW-pasture) TARGET-distractor relations in a balanced design, finding interference and facilitation effects on naming latencies, respectively, as well as differential patterns of brain activation compared with an unrelated distractor condition. While both types of distractor relation activated the middle portion of the left middle temporal gyrus (MTG) consistent with retrieval of conceptual or lexical representations, categorical relations involved additional activation of posterior left MTG, consistent with retrieval of a lexical cohort. Thematic relations involved additional activation of the left angular gyrus. These results converge with recent lesion evidence implicating the left inferior parietal lobe in processing thematic relations and may indicate a potential role for this region during spoken word production.