Automatic classification of free-text radiology reports to identify limb fractures using machine learning and the SNOMED CT ontology

Objective To develop and evaluate machine learning techniques that identify limb fractures and other abnormalities (e.g. dislocations) from radiology reports. Materials and Methods 99 free-text reports of limb radiology examinations were acquired from an Australian public hospital. Two clinicians were employed to identify fractures and abnormalities from the reports; a third senior clinician resolved disagreements. These assessors found that, of the 99 reports, 48 referred to fractures or abnormalities of limb structures. Automated methods were then used to extract features from these reports that could be useful for their automatic classification. The Naive Bayes classification algorithm and two implementations of the support vector machine algorithm were formally evaluated using cross-fold validation over the 99 reports. Result Results show that the Naive Bayes classifier accurately identifies fractures and other abnormalities from the radiology reports. These results were achieved when extracting stemmed token bigram and negation features, as well as using these features in combination with SNOMED CT concepts related to abnormalities and disorders. The latter feature has not been used in previous works that attempted classifying free-text radiology reports. Discussion Automated classification methods have proven effective at identifying fractures and other abnormalities from radiology reports (F-Measure up to 92.31%). Key to the success of these techniques are features such as stemmed token bigrams, negations, and SNOMED CT concepts associated with morphologic abnormalities and disorders. Conclusion This investigation shows early promising results and future work will further validate and strengthen the proposed approaches.

External knowledge and query strategies in active learning: A study in clinical information extraction

This paper presents a new active learning query strategy for information extraction, called Domain Knowledge Informativeness (DKI). Active learning is often used to reduce the amount of annotation effort required to obtain training data for machine learning algorithms. A key component of an active learning approach is the query strategy, which is used to iteratively select samples for annotation. Knowledge resources have been used in information extraction as a means to derive additional features for sample representation. DKI is, however, the first query strategy that exploits such resources to inform sample selection. To evaluate the merits of DKI, in particular with respect to the reduction in annotation effort that the new query strategy allows to achieve, we conduct a comprehensive empirical comparison of active learning query strategies for information extraction within the clinical domain. The clinical domain was chosen for this work because of the availability of extensive structured knowledge resources which have often been exploited for feature generation. In addition, the clinical domain offers a compelling use case for active learning because of the necessary high costs and hurdles associated with obtaining annotations in this domain. Our experimental findings demonstrated that 1) amongst existing query strategies, the ones based on the classification model’s confidence are a better choice for clinical data as they perform equally well with a much lighter computational load, and 2) significant reductions in annotation effort are achievable by exploiting knowledge resources within active learning query strategies, with up to 14% less tokens and concepts to manually annotate than with state-of-the-art query strategies.

Multi-state-choice automata model for expedient learning in random environment

A new automata model Mr,k, with a conceptually significant innovation in the form of multi-state alternatives at each instance, is proposed in this study. Computer simulations of the Mr,k, model in the context of feature selection in an unsupervised environment has demonstrated the superiority of the model over similar models without this multi-state-choice innovation.

R&D in clean technology: A project choice model with learning

In this study, we investigate the qualitative and quantitative effects of an R&D subsidy for a clean technology and a Pigouvian tax on a dirty technology on environmental R&D when it is uncertain how long the research takes to complete. The model is formulated as an optimal stopping problem, in which the number of successes required to complete the R&D project is finite and learning about the probability of success is incorporated. We show that the optimal R&D subsidy with the consideration of learning is higher than that without it. We also find that an R&D subsidy performs better than a Pigouvian tax unless suppliers have sufficient incentives to continue cost-reduction efforts after the new technology success-fully replaces the old one. Moreover, by using a two-project model, we show that a uniform subsidy is better than a selective subsidy.

Avoidant Learning Ability in Free Flying Housefly (Aldrichina grahami)by Electric Shock

下载PDF阅读器研究证实:蜜蜂和果蝇具有良好的学习记忆能力.利用自主改良的研究装置对另一种具有强大生存本能的双翅目昆虫--巨尾阿丽蝇(Aldrichina grahami)在自由状态下电击同避学习能力进行研究.结果表明,巨尾阿丽蝇具有良好的学习记忆能力,因为当刺激电压范围为5V到45V时,观察到巨尾阿丽蝇有显著的回避电刺激行为,而当电压达到60V时会受到明显伤害.由此推测,巨尾阿丽蝇适合作为神经系统研究的动物模型.该实验所采用的实验范例较以往有所改进,适合作为自由状态下研究昆虫的工具.

Learning, fatigue and preference formation in discrete choice experiments

While the repeated nature of Discrete Choice Experiments is advantageous from a sampling efficiency perspective, patterns of choice may differ across the tasks, due, in part, to learning and fatigue. Using probabilistic decision process models, we find in a field study that learning and fatigue behavior may only be exhibited by a small subset of respondents. Most respondents in our sample show preference and variance stability consistent with rational pre-existent and
well formed preferences. Nearly all of the remainder exhibit both learning and fatigue effects. An important aspect of our approach is that it enables learning and fatigue effects to be explored, even though they were not envisaged during survey design or data collection.

The grass-free lawn: management and species choice for optimum ground cover and plant diversity

In Britain, managed grass lawns provide the most traditional and widespread of garden and landscape practices in use today. Grass lawns are coming under increasing challenge as they tend to support a low level of biodiversity and can require substantial additional inputs to maintain. Here we apply a novel approach to the traditional monocultural lawnscape by replacing grasses entirely with clonal perennial forbs. We monitored changes in plant coverage and species composition over a two year period and here we report the results of a study comparing plant origin native, non-native and mixed) and mowing regime. This allows us to assess the viability of this construct as an alternative to traditional grass lawns. Grass-free lawns provided a similar level of plant cover to grass lawns. Both the mowing regime and the combination of species used affected this outcome, with native plant species seen to have the highest survival rates, and mowing at 4cm to produce the greatest amount of ground coverage and plant species diversity within grass-free lawns. Grass-free lawns required over 50% less mowing than a traditionally managed grass lawn. Observations suggest that plant forms that exhibited: a) a relatively fast growth rate, b) a relatively large individual leaf area, and c) an average leaf height substantially above the cut to be applied, were unsuitable for use in grass-free lawns. With an equivalent level of ground coverage to grass lawns, increased plant diversity and a reduced need for mowing, the grass-free lawn can be seen as a species diverse, lower input and potentially highly ornamental alternative to the traditional lawn format.