Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

Background and aims: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.

Materials and methods: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: ‘semi-structured’ and ‘unstructured’. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.

Results: The best result of 99.4% accuracy – which included only one semi-structured report predicted as unstructured – was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.

Conclusions: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.

Virtual Reality as a tool to Assist Learning in Aerospace Assembly

This study examines whether virtual reality (VR) is more superior to paper-based instructions in increasing the speed at which individuals learn a new assembly task. Specifically, the work seeks to quantify any learning benefits when individuals have been given the opportunity and compares the performance of two groups using virtual and hardcopy media types to pre-learn the task. A build experiment based on multiple builds of an aircraft panel showed that a group of people who pre-learned the assembly task using a VR environment completed their builds faster (average build time 29.5% lower). The VR group also made fewer references to instructional materials (average number of references 38% lower) and made fewer errors than a group using more traditional, hard copy instructions. These outcomes were more pronounced during build one with differences in build time and number of references showing limited statistical differences.

Joint Analysis of Multiple Algorithms and Performance Measures

There has been an increasing interest in the development of new methods using Pareto optimality to deal with multi-objective criteria (for example, accuracy and time complexity). Once one has developed an approach to a problem of interest, the problem is then how to compare it with the state of art. In machine learning, algorithms are typically evaluated by comparing their performance on different data sets by means of statistical tests. Standard tests used for this purpose are able to consider jointly neither performance measures nor multiple competitors at once. The aim of this paper is to resolve these issues by developing statistical procedures that are able to account for multiple competing measures at the same time and to compare multiple algorithms altogether. In particular, we develop two tests: a frequentist procedure based on the generalized likelihood-ratio test and a Bayesian procedure based on a multinomial-Dirichlet conjugate model. We further extend them by discovering conditional independences among measures to reduce the number of parameters of such models, as usually the number of studied cases is very reduced in such comparisons. Data from a comparison among general purpose classifiers is used to show a practical application of our tests.

Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 

Bespoke Radiology e-Learning

Introduction: Foundation doctors are expected to assess and interpret plain x-ray studies of the chest/abdomen before a definitive report is issued by senior staff. The Royal College of Radiologists have published guidelines (RCR curriculum) on the scope of plain film findings medical students should be familiar with.1 Studies have shown that the x-ray interpretation without feedback does not significantly improve diagnostic ability. 2 Queen’s University, Belfast Trust Radiology and Experior Medical developed an online system to assess individual student ability to interpret X-ray findings. Over a series of assessments each student’s profile is built up, identifying strengths and weakness. The system can then create bespoke individual assessments re-evaluating previously identified weak areas and quantifying interpretative skill improvement. Aim: To determine how readily an online system is adopted by senior medical students, investigating if increasing exposure to x-ray interpretation combined with cyclical formative feedback enhances performance. Methods: The system was offered to all 270 final year medical students as an online resource. The system comprised a series of 20 weekly 30 minute assessments, containing normal and abnormal x-rays within the RCR curriculum. After each assessment students were given formative feedback, including their own result, annotated answers, peer group comparison and a breakdown of areas of strength and weakness. Focus groups of 4-5 students addressed student perspectives of the system, including ease of use, image resolution, system performance across different operating platforms, perceived value of formative feedback loops, breakdown of performance and the value of bespoke personalised assessments. Research Ethics Approval was granted for the study. Data analysis was via two-sided one-sample t-test; initial minimal recruitment was estimated as 60 students, to detect a mean 10% change in performance, with a standard deviation of 20%. Results and Discussion: Over 80% (n = XXX/270) of the student cohort engaged with the study. Student baseline average was 39%, increasing to 62% by the exit test. The steadily sustained improvement (57% relative performance in interpretative diagnostic accuracy) was despite increasing test difficulty. Student feedback via focus groups was universally positive throughout the examined domains. Conclusion: The online resource proved to be valuable, with high levels of student engagement, improving performance despite increasingly difficulty testing and positive learner experience with the system. References: 1. Undergraduate Radiology Curriculum, The Royal College of Ra, April 2012. Ref No. BFCR(12)4 The Royal College of Radiologists, April 2012 2. I Satia, S Bashagha, A Bibi, R Ahmed, S Mellor, F Zaman. Assessing the accuracy and certainty in interpretating chest x-rays in the medical division. Clin Med August 2013 Vol.13 no. 4 349-352

Seeing How it Sounds: Observation, Imitation and Improved Learning in Piano Playing

Research in various fields has shown that students benefit from teacher action demonstrations during instruction, establishing the need to better understand the effectiveness of different demonstration types across student proficiency levels. This study centres upon a piano learning and teaching environment in which beginners and intermediate piano students (N=48) learning to perform a specific type of staccato were submitted to three different (group exclusive) teaching conditions: audio-only demonstration of the musical task; observation of the teacher's action demonstration followed by student imitation (blockedobservation); and observation of the teacher's action demonstration whilst alternating imitation of the task with the teacher's performance (interleaved-observation). Learning was measured in relation to students' range of wrist amplitude (RWA) and ratio of sound and inter-sound duration (SIDR) before, during and after training. Observation and imitation of the teacher’s action demonstrations had a beneficial effect on students' staccato knowledge retention at different times after training: students submitted to interleaved-observation presented significantly shorter note duration and larger wrist rotation, and as such, were more proficient at the learned technique in each of the lesson and retention tests than students in the other learning conditions. There were no significant differences in performance or retention for students of different proficiency levels. These findings have relevant implications for instrumental music pedagogy and other contexts where embodied action is an essential aspect of the learning process.