Harnessing information from injury narrative in the 'big data' era: Understanding and applying machine learning for injury surveillance

Objective Vast amounts of injury narratives are collected daily and are available electronically in real time and have great potential for use in injury surveillance and evaluation. Machine learning algorithms have been developed to assist in identifying cases and classifying mechanisms leading to injury in a much timelier manner than is possible when relying on manual coding of narratives. The aim of this paper is to describe the background, growth, value, challenges and future directions of machine learning as applied to injury surveillance. Methods This paper reviews key aspects of machine learning using injury narratives, providing a case study to demonstrate an application to an established human-machine learning approach. Results The range of applications and utility of narrative text has increased greatly with advancements in computing techniques over time. Practical and feasible methods exist for semi-automatic classification of injury narratives which are accurate, efficient and meaningful. The human-machine learning approach described in the case study achieved high sensitivity and positive predictive value and reduced the need for human coding to less than one-third of cases in one large occupational injury database. Conclusion The last 20 years have seen a dramatic change in the potential for technological advancements in injury surveillance. Machine learning of ‘big injury narrative data’ opens up many possibilities for expanded sources of data which can provide more comprehensive, ongoing and timely surveillance to inform future injury prevention policy and practice.

Systematic review of the psychological consequences of false-positive screening mammograms

- Background In the UK, women aged 50–73 years are invited for screening by mammography every 3 years. In 2009–10, more than 2.24 million women in this age group in England were invited to take part in the programme, of whom 73% attended a screening clinic. Of these, 64,104 women were recalled for assessment. Of those recalled, 81% did not have breast cancer; these women are described as having a false-positive mammogram. - Objective The aim of this systematic review was to identify the psychological impact on women of false-positive screening mammograms and any evidence for the effectiveness of interventions designed to reduce this impact. We were also looking for evidence of effects in subgroups of women. - Data sources MEDLINE, MEDLINE In-Process & Other Non-Indexed Citations, EMBASE, Health Management Information Consortium, Cochrane Central Register for Controlled Trials, Cochrane Database of Systematic Reviews, Centre for Reviews and Dissemination (CRD) Database of Abstracts of Reviews of Effects, CRD Health Technology Assessment (HTA), Cochrane Methodology, Web of Science, Science Citation Index, Social Sciences Citation Index, Conference Proceedings Citation Index-Science, Conference Proceeding Citation Index-Social Science and Humanities, PsycINFO, Cumulative Index to Nursing and Allied Health Literature, Sociological Abstracts, the International Bibliography of the Social Sciences, the British Library's Electronic Table of Contents and others. Initial searches were carried out between 8 October 2010 and 25 January 2011. Update searches were carried out on 26 October 2011 and 23 March 2012. - Review methods Based on the inclusion criteria, titles and abstracts were screened independently by two reviewers. Retrieved papers were reviewed and selected using the same independent process. Data were extracted by one reviewer and checked by another. Each included study was assessed for risk of bias. - Results Eleven studies were found from 4423 titles and abstracts. Studies that used disease-specific measures found a negative psychological impact lasting up to 3 years. Distress increased with the level of invasiveness of the assessment procedure. Studies using instruments designed to detect clinical levels of morbidity did not find this effect. Women with false-positive mammograms were less likely to return for the next round of screening [relative risk (RR) 0.97; 95% confidence interval (CI) 0.96 to 0.98] than those with normal mammograms, were more likely to have interval cancer [odds ratio (OR) 3.19 (95% CI 2.34 to 4.35)] and were more likely to have cancer detected at the next screening round [OR 2.15 (95% CI 1.55 to 2.98)]. - Limitations This study was limited to UK research and by the robustness of the included studies, which frequently failed to report quality indicators, for example failure to consider the risk of bias or confounding, or failure to report participants' demographic characteristics. - Conclusions We conclude that the experience of having a false-positive screening mammogram can cause breast cancer-specific psychological distress that may endure for up to 3 years, and reduce the likelihood that women will return for their next round of mammography screening. These results should be treated cautiously owing to inherent weakness of observational designs and weaknesses in reporting. Future research should include a qualitative interview study and observational studies that compare generic and disease-specific measures, collect demographic data and include women from different social and ethnic groups.

Information flow, trading activity and commodity futures volatility

Based on unique news data relating to gold and crude oil, we investigate how news volume and sentiment, shocks in trading activity, market depth and trader positions unrelated to information flow covary with realized volatility. Positive shocks to the rate of news arrival, and negative shocks to news sentiment exhibit the largest effects. After controlling for the level of news flow and cross-correlations, net trader positions play only a minor role. These findings are at odds with those of [Wang (2002a). The Journal of Futures Markets, 22, 427–450; Wang (2002b). The Financial Review, 37, 295–316], but are consistent with the previous literature which doesn't find a strong link between volatility and trader positions.

Organizational competencies and dynamic Accounting Information System capability: Impact on AIS processes and firm performance

Accounting information systems (AIS) capture and process accounting data and provide valuable information for decision-makers. However, in a rapidly changing environment, continual management of the AIS is necessary for organizations to optimise performance outcomes. We suggest that building a dynamic AIS capability enables accounting process and organizational performance. Using the dynamic capabilities framework (Teece 2007) we propose that a dynamic AIS capability can be developed through the synergy of three competencies: a flexible AIS, having a complementary business intelligence system and accounting professionals with IT technical competency. Using survey data, we find evidence of a positive association between a dynamic AIS capability, accounting process performance, and overall firm performance. The results suggest that developing a dynamic AIS resource can add value to an organization. This study provides guidance for organizations looking to leverage the performance outcomes of their AIS environment.

On information technology competencies for collaborative organizational structures

There is an uptake of organizations involvement in collaborative organizational structures (COS). As the nature and level of information technology (IT) investment in COS will be similar, the COS IT competencies will leverage the IT investments to create the collaborative rent generating potential of the COS, which would then improve the business value of the COS members. Consistent with the resource-centric views of the firm, we suggest that the COS members need to contribute their managed IT competencies to their COS, whose synergies would create COS IT competencies. We suggest three key IT competencies for COS; proactive top management decision synergy, collaborative and agile IT infrastructure, and cross-functional tactical management synergy. Using survey data, we find evidence of a positive association between these COS IT competencies and the collaborative rent generating potential of the COS. We also find a positive association between the collaborative rent generating potential of the COS and the business value of the COS members. The results suggest that developing COS IT competencies add value to a COS and its members. This study provides guidance for organizations looking to leverage their involvement in a COS.

How Do Different Types of Investors React to New Financial Statement Information?

The study contributes to our understanding of the forces that drive the stock market by investigating how different types of investors react to new financial statement information. Using the extremely comprehensive official register of share holdings in Finland, we find that the majority of investors are more probable to sell (buy) stocks in a company after a positive (negative) earnings surprise, and show a bias towards buying after the disclosure of new financial statement information. Large investors, on the other hand, show behavior opposite to that of the majority of investors in the market. Further, foreign investors show behavior similar to that of domestic investors. We suggest investor overconfidence and asymmetric information as possible explanations for the documented behavior.

Positive Relationships between Association Strength and Phenotypic Similarity Characterize the Assembly of Mixed-Species Bird Flocks Worldwide

Competition theory predicts that local communities should consist of species that are more dissimilar than expected by chance. We find a strikingly different pattern in a multicontinent data set (55 presence-absence matrices from 24 locations) on the composition of mixed-species bird flocks, which are important sub-units of local bird communities the world over. By using null models and randomization tests followed by meta-analysis, we find the association strengths of species in flocks to be strongly related to similarity in body size and foraging behavior and higher for congeneric compared with noncongeneric species pairs. Given the local spatial scales of our individual analyses, differences in the habitat preferences of species are unlikely to have caused these association patterns; the patterns observed are most likely the outcome of species interactions. Extending group-living and social-information-use theory to a heterospecific context, we discuss potential behavioral mechanisms that lead to positive interactions among similar species in flocks, as well as ways in which competition costs are reduced. Our findings highlight the need to consider positive interactions along with competition when seeking to explain community assembly.

Learning from positive and unlabelled examples using maximum margin clustering

Learning from Positive and Unlabelled examples (LPU) has emerged as an important problem in data mining and information retrieval applications. Existing techniques are not ideally suited for real world scenarios where the datasets are linearly inseparable, as they either build linear classifiers or the non-linear classifiers fail to achieve the desired performance. In this work, we propose to extend maximum margin clustering ideas and present an iterative procedure to design a non-linear classifier for LPU. In particular, we build a least squares support vector classifier, suitable for handling this problem due to symmetry of its loss function. Further, we present techniques for appropriately initializing the labels of unlabelled examples and for enforcing the ratio of positive to negative examples while obtaining these labels. Experiments on real-world datasets demonstrate that the non-linear classifier designed using the proposed approach gives significantly better generalization performance than the existing relevant approaches for LPU.

Value of information in product recovery decisions: A Bayesian approach

There is a widespread recognition of the need for better information sharing and provision to improve the viability of end-of-life (EOL) product recovery operations. The emergence of automated data capture and sharing technologies such as RFID, sensors and networked databases has enhanced the ability to make product information; available to recoverers, which will help them make better decisions regarding the choice of recovery option for EOL products. However, these technologies come with a cost attached to it, and hence the question 'what is its value?' is critical. This paper presents a probabilistic approach to model product recovery decisions and extends the concept of Bayes' factor for quantifying the impact of product information on the effectiveness of these decisions. Further, we provide a quantitative examination of the factors that influence the value of product information, this value depends on three factors: (i) penalties for Type I and Type II errors of judgement regarding product quality; (ii) prevalent uncertainty regarding product quality and (iii) the strength of the information to support/contradict the belief. Furthermore, we show that information is not valuable under all circumstances and derive conditions for achieving a positive value of information. © 2010 Taylor & Francis.

Positive selection on multiple antique allelic lineages of transferrin in the polyploid Carassius auratus

Transferrin polymorphism has been studied in the polyploid Carassius auratus by cloning and sequence analysis of cDNAs from its three subspecies C. auratus gibelio, C. auratus auratus, and C. auratus cuvieri. DNA polymorphism of extremely high extent was shown for the transferrin gene by the 248 segregation sites among coding region sequences of its alleles. The deduced amino acid sequences of the transferrin alleles showed variable theoretical physicochemical parameters, which might constitute molecular basis for their electrophoretic heterogeneity. Positive selection was inferred by the replacement/synonymous ratios larger than 1 in partial allelic lineages which was subsequently confirmed by likelihood simulation under neutral or selection models. Furthermore, the correspondent sites to these selected codons were collectively located at two planes in the crystallographic structure of rabbit transferrin, which suggested that the rapid evolution of C. auratus transferrin might correlate to its adaptation to variable environmental elements such as oxygen pressure. The minimal 26 recombination events were detected among coding sequences of C. auratus transferrin, with partial mosaic sequences and breakpoints identified by identity scanning and information site analyses. Phylogenetic analyses revealed multiple antique allelic lineages of transferrin, which was estimated to diverge fifteen to twenty MYA. All these features strongly suggested the role of balancing selection in long persistence of high transferrin polymorphism in C. auratus. Furthermore, owing to its particular evolutionary backgrounds, the silver crucian carp might possess a distinctive balancing selection mechanism.

A study of information literacy initiatives between secondary schools and universities in the UK

Lonsdale, R. E. & Armstrong, C. (2006). A study of information literacy initiatives between secondary schools and universities in the UK. In A.B. Martins, A.P. Falcao, E. Conde, I. Andrade, M.B. Nunes, M.J. Vitorino (Eds.), Proceedings of 35th Annual conference of the International Association of School Librarianship, Lisboa (Portugal). The Multiple Faces of Literacy: Reading, Knowing, Doing: Selected papers from the 35th Annual Conference of IASL [CD-ROM: PDF version] Lisbon, Portugal 2006 Sponsorship: JISC

Integration of relational and hierarchical network information for protein function prediction

BACKGROUND:In the current climate of high-throughput computational biology, the inference of a protein's function from related measurements, such as protein-protein interaction relations, has become a canonical task. Most existing technologies pursue this task as a classification problem, on a term-by-term basis, for each term in a database, such as the Gene Ontology (GO) database, a popular rigorous vocabulary for biological functions. However, ontology structures are essentially hierarchies, with certain top to bottom annotation rules which protein function predictions should in principle follow. Currently, the most common approach to imposing these hierarchical constraints on network-based classifiers is through the use of transitive closure to predictions.RESULTS:We propose a probabilistic framework to integrate information in relational data, in the form of a protein-protein interaction network, and a hierarchically structured database of terms, in the form of the GO database, for the purpose of protein function prediction. At the heart of our framework is a factorization of local neighborhood information in the protein-protein interaction network across successive ancestral terms in the GO hierarchy. We introduce a classifier within this framework, with computationally efficient implementation, that produces GO-term predictions that naturally obey a hierarchical 'true-path' consistency from root to leaves, without the need for further post-processing.CONCLUSION:A cross-validation study, using data from the yeast Saccharomyces cerevisiae, shows our method offers substantial improvements over both standard 'guilt-by-association' (i.e., Nearest-Neighbor) and more refined Markov random field methods, whether in their original form or when post-processed to artificially impose 'true-path' consistency. Further analysis of the results indicates that these improvements are associated with increased predictive capabilities (i.e., increased positive predictive value), and that this increase is consistent uniformly with GO-term depth. Additional in silico validation on a collection of new annotations recently added to GO confirms the advantages suggested by the cross-validation study. Taken as a whole, our results show that a hierarchical approach to network-based protein function prediction, that exploits the ontological structure of protein annotation databases in a principled manner, can offer substantial advantages over the successive application of 'flat' network-based methods.

Hospital clinicians information behaviour and attitudes towards the 'Clinical Informationist': an Irish survey

Background: Hospital clinicians are increasingly expected to practice evidence-based medicine (EBM) in order to minimize medical errors and ensure quality patient care, but experience obstacles to information-seeking. The introduction of a Clinical Informationist (CI) is explored as a possible solution. Aims:  This paper investigates the self-perceived information needs, behaviour and skill levels of clinicians in two Irish public hospitals. It also explores clinicians perceptions and attitudes to the introduction of a CI into their clinical teams. Methods: A questionnaire survey approach was utilised for this study, with 22 clinicians in two hospitals. Data analysis was conducted using descriptive statistics. Results: Analysis showed that clinicians experience diverse information needs for patient care, and that barriers such as time constraints and insufficient access to resources hinder their information-seeking. Findings also showed that clinicians struggle to fit information-seeking into their working day, regularly seeking to answer patient-related queries outside of working hours. Attitudes towards the concept of a CI were predominantly positive. Conclusion: This paper highlights the factors that characterise and limit hospital clinicians information-seeking, and suggests the CI as a potentially useful addition to the clinical team, to help them to resolve their information needs for patient care.

Shipping information pipeline: initial design principles

This paper presents a design science approach to solving persistent problems in the international shipping eco system by creating the missing common information infrastructures. Specifically, this paper reports on an ongoing dialogue between stakeholders in the shipping industry and information systems researchers engaged in the design and development of a prototype for an innovative IT-artifact called Shipping Information Pipeline which is a kind of “an internet” for shipping information. The instrumental aim is to enable information seamlessly to cross the organizational boundaries and national borders within international shipping which is a rather complex domain. The intellectual objective is to generate and evaluate the efficacy and effectiveness of design principles for inter-organizational information infrastructures in the international shipping domain that can have positive impacts on global trade and local economies.