Regularizing topic discovery in emrs with side information by using hierarchical bayesian models

We propose a novel hierarchical Bayesian framework, word-distance-dependent Chinese restaurant franchise (wd-dCRF) for topic discovery from a document corpus regularized by side information in the form of word-to-word relations, with an application on Electronic Medical Records (EMRs). Typically, a EMRs dataset consists of several patients (documents) and each patient contains many diagnosis codes (words). We exploit the side information available in the form of a semantic tree structure among the diagnosis codes for semantically-coherent disease topic discovery. We introduce novel functions to compute word-to-word distances when side information is available in the form of tree structures. We derive an efficient inference method for the wddCRF using MCMC technique. We evaluate on a real world medical dataset consisting of about 1000 patients with PolyVascular disease. Compared with the popular topic analysis tool, hierarchical Dirichlet process (HDP), our model discovers topics which are superior in terms of both qualitative and quantitative measures.

Transition from paper to electronic nursing documentation in residential aged care: an actor network theory analysis

Objectives: To examine the role of technology when introduced into the specific setting of residential aged care and then analyse the associated changes to this complex socio-technical network of human and technology actors on the introduction of this technology using the rich lens of Actor Network Theory. Methods: An exploratory qualitative single case study was conducted. The specific focus being the implementation of a nursing information system in an aged care context, i.e. the transition from paper-based nursing documentation to electronic nursing documentation. A series of 19 semi structured interviews with facility managers, nursing coordinators, and the nursing and care staff were conducted. The collected data were analysed using standard qualitative techniques such as thematic analysis and a priori themes were developed from the application of Actor Network Theory. Results: A priori themes coupled with emergent themes served to highlight the impact of a disruptive technology solution into a complex context. Conclusion: An Actor Network Theory analysis enables a rich theoretical lens to be used to examine the introduction of a disruptive technology into a complex context. On such examination critical success factors were identified as well as key barriers. Moreover, people issues were found to be central to the success of such a solution.

Australian government budget balance numbers: the hybrid nature of public sector accrual accounting

Purpose - The purpose of this paper is to analyse the nature and comparability of budget balance (surplus/deficit) numbers headlined by the Australian Commonwealth Government and the governments of the six Australian States and the two Australian Territories. It does this in the context of the transition to Australian accounting standard AASB 1049 Whole of Government and General Government Sector Financial Reporting. Design/methodology/approach - A case study research method is adopted, based on a content/documentary analysis of the headline budget balance numbers in the general government sector budget statements of each of the nine governments for the eight financial years from 2004-2005 to 2011-2012. Findings - Findings indicate some variation in the measurement bases adopted and a number of departures from the measurement bases prescribed in the reporting frameworks, including AASB 1049. Findings also reveal that none of the nine governments have headlined a full accrual based budget balance number since the implementation of AASB 1049 in 2008. Research limitations/implications - While the study focuses on the Australian general government sector environment, it has significant implications in highlighting the ambiguity in the government budget balance numbers presented and the monitoring and information asymmetry problems that can arise. Research findings have wider relevance internationally in highlighting issues arising with the public sector adoption of accrual accounting. Practical implications - The paper highlights the manner in which governments have been selective in the manner in which they present important budget aggregates. This has important practical and social implications, as the budget balance number is one of the most important measures used to evaluate a government's fiscal management and responsibility. Originality/value - The paper represents the first detailed examination of aspects of the effect of the transition to AASB 1049.

Health literacy and the Internet: a study on the readability of Australian online health information

OBJECTIVE: Almost 80% of Australian Internet users seek out health information online so the readability of this information is important. This study aimed to evaluate the readability of Australian online health information and determine if it matches the average reading level of Australians. METHODS: Two hundred and fifty-one web pages with information on 12 common health conditions were identified across sectors. Readability was assessed by the Flesch-Kincaid (F-K), Simple Measure of Gobbledygook (SMOG) and Flesch Reading Ease (FRE) formulas, with grade 8 adopted as the average Australian reading level. RESULTS: The average reading grade measured by F-K and SMOG was 10.54 and 12.12 respectively. The mean FRE was 47.54, a 'difficult-to-read' score. Only 0.4% of web pages were written at or below grade 8 according to SMOG. Information on dementia was the most difficult to read overall, while obesity was the most difficult among government websites. CONCLUSIONS AND IMPLICATIONS: The findings suggest that the readability of Australian health websites is above the average Australian levels of reading. A quantifiable guideline is needed to ensure online health information accommodates the reading needs of the general public to effectively use the Internet as an enabler of health literacy.

Framing ICT policies to facilitate participatory e-government

This paper examines the role of information and communication technology (ICT) policies in shaping the participatory nature of local e-government. It suggests that civic involvement through e-government practices requires a combination of direct and indirect ICT policies (Cohen, van Geenhuizen and Nijkamp, 2005). Direct policies focus on ICT infrastructure development and enhance civic adoption and use of ICTs. ICTs also support policies indirectly through data organisation, information dissemination and the provision of spaces for discourse, deliberation and contributions to decision-making processes. Drawing from policy examples from Australia and the United Kingdom (UK), this paper suggests the need to combine federal guidance with local knowledge, while using policies to support ICTs and using ICTs to support policies. Such a cohesive and integrated policy relationship between federal and local government bodies is needed if local e-government is to advance to facilitate civic engagement.

Cost-effectiveness analysis of a hospital electronic medication management system

OBJECTIVE: To conduct a cost-effectiveness analysis of a hospital electronic medication management system (eMMS). METHODS: We compared costs and benefits of paper-based prescribing with a commercial eMMS (CSC MedChart) on one cardiology ward in a major 326-bed teaching hospital, assuming a 15-year time horizon and a health system perspective. The eMMS implementation and operating costs were obtained from the study site. We used data on eMMS effectiveness in reducing potential adverse drug events (ADEs), and potential ADEs intercepted, based on review of 1 202 patient charts before (n = 801) and after (n = 401) eMMS. These were combined with published estimates of actual ADEs and their costs. RESULTS: The rate of potential ADEs following eMMS fell from 0.17 per admission to 0.05; a reduction of 71%. The annualized eMMS implementation, maintenance, and operating costs for the cardiology ward were A$61 741 (US$55 296). The estimated reduction in ADEs post eMMS was approximately 80 actual ADEs per year. The reduced costs associated with these ADEs were more than sufficient to offset the costs of the eMMS. Estimated savings resulting from eMMS implementation were A$63-66 (US$56-59) per admission (A$97 740-$102 000 per annum for this ward). Sensitivity analyses demonstrated results were robust when both eMMS effectiveness and costs of actual ADEs were varied substantially. CONCLUSION: The eMMS within this setting was more effective and less expensive than paper-based prescribing. Comparison with the few previous full economic evaluations available suggests a marked improvement in the cost-effectiveness of eMMS, largely driven by increased effectiveness of contemporary eMMs in reducing medication errors.

Trials and tribulations with electronic medication adherence monitoring in kidney transplantation

Medication adherence in kidney transplantation is critical to prevent graft rejection. Testing interventions designed to support patients to take their prescribed medications following a kidney transplant require an accurate measure of medication adherence. In research, the available methods for measuring medication adherence include self-report, pill counts, prescription refill records, surrogate measures of medication adherence and medication bottles with a microchip-embedded cap to record bottle openings. Medication bottles with a microchip-embedded cap are currently regarded as the gold standard measure. This commentary outlines the challenges in measuring medication adherence using electronic medication monitoring of kidney transplant patients recruited from five sites. The challenges included obtaining unanimous stakeholder support for using this method, agreement on an index medication to measure, adequate preparation of the patient and training of pharmacy staff, and how to analyze data when periods of time were not recorded using the electronic adherence measure. Provision of this information will enable hospital and community pharmacists to implement approaches that promote the effective use of this adherence measure for optimal patient outcomes.

A sword with two edges: propagation studies on both positive and negative information in online social networks

Online social networks (OSN) have become one of the major platforms for people to exchange information. Both positive information (e.g., ideas, news and opinions) and negative information (e.g., rumors and gossips) spreading in social media can greatly influence our lives. Previously, researchers have proposed models to understand their propagation dynamics. However, those were merely simulations in nature and only focused on the spread of one type of information. Due to the human-related factors involved, simultaneous spread of negative and positive information cannot be thought of the superposition of two independent propagations. In order to fix these deficiencies, we propose an analytical model which is built stochastically from a node level up. It can present the temporal dynamics of spread such as the time people check newly arrived messages or forward them. Moreover, it is capable of capturing people's behavioral differences in preferring what to believe or disbelieve. We studied the social parameters impact on propagation using this model. We found that some factors such as people's preference and the injection time of the opposing information are critical to the propagation but some others such as the hearsay forwarding intention have little impact on it. The extensive simulations conducted on the real topologies confirm the high accuracy of our model.

The driving force of government in promoting BIM implementation

The adoption of Building Information Modelling (BIM) is one of the greatest technological innovations in the construction industry to date. However, the implementation of BIM lags far behind its potential due to the existence of various barriers. Strong government support is critical for the successful development and deployment of complex technology systems. BIM could seek government support to drive its implementation process and overcome the barriers. Through a survey, this paper aims to discover stakeholders’ expectations of the government role in BIM implementation and explores specific ways for governments to promote BIM implementation. The research findings are expected to assist related departments to accelerate BIM implementation.

Correlated differential privacy: hiding information in non-IID data set

Privacy preserving on data mining and data release has attracted an increasing research interest over a number of decades. Differential privacy is one influential privacy notion that offers a rigorous and provable privacy guarantee for data mining and data release. Existing studies on differential privacy assume that in a data set, records are sampled independently. However, in real-world applications, records in a data set are rarely independent. The relationships among records are referred to as correlated information and the data set is defined as correlated data set. A differential privacy technique performed on a correlated data set will disclose more information than expected, and this is a serious privacy violation. Although recent research was concerned with this new privacy violation, it still calls for a solid solution for the correlated data set. Moreover, how to decrease the large amount of noise incurred via differential privacy in correlated data set is yet to be explored. To fill the gap, this paper proposes an effective correlated differential privacy solution by defining the correlated sensitivity and designing a correlated data releasing mechanism. With consideration of the correlated levels between records, the proposed correlated sensitivity can significantly decrease the noise compared with traditional global sensitivity. The correlated data releasing mechanism correlated iteration mechanism is designed based on an iterative method to answer a large number of queries. Compared with the traditional method, the proposed correlated differential privacy solution enhances the privacy guarantee for a correlated data set with less accuracy cost. Experimental results show that the proposed solution outperforms traditional differential privacy in terms of mean square error on large group of queries. This also suggests the correlated differential privacy can successfully retain the utility while preserving the privacy.

Stabilizing sparse cox model using statistic and semantic structures in electronic medical records

Stability in clinical prediction models is crucial for transferability between studies, yet has received little attention. The problem is paramount in high dimensional data, which invites sparse models with feature selection capability. We introduce an effective method to stabilize sparse Cox model of time-to-events using statistical and semantic structures inherent in Electronic Medical Records (EMR). Model estimation is stabilized using three feature graphs built from (i) Jaccard similarity among features (ii) aggregation of Jaccard similarity graph and a recently introduced semantic EMR graph (iii) Jaccard similarity among features transferred from a related cohort. Our experiments are conducted on two real world hospital datasets: a heart failure cohort and a diabetes cohort. On two stability measures – the Consistency index and signal-to-noise ratio (SNR) – the use of our proposed methods significantly increased feature stability when compared with the baselines.

Systematic examination of publicly-available information reveals the diverse and extensive corporate political activity of the food industry in Australia

BACKGROUND: The political influence of the food industry, referred to as corporate political activity (CPA), represents a potential barrier to the development and implementation of effective public health policies for non-communicable diseases prevention. This paper reports on the feasibility and limitations of using publicly-available information to identify and monitor the CPA of the food industry in Australia. METHODS: A systematic search was conducted for information from food industry, government and other publicly-available data sources in Australia. Data was collected in relation to five key food industry actors: the Australian Food and Grocery Council; Coca Cola; McDonald's; Nestle; and Woolworths, for the period January 2012 to February 2015. Data analysis was guided by an existing framework for classifying CPA strategies of the food industry. RESULTS: The selected food industry actors used multiple CPA strategies, with 'information and messaging' and 'constituency building' strategies most prominent. CONCLUSIONS: The systematic analysis of publicly-available information over a limited period was able to identify diverse and extensive CPA strategies of the food industry in Australia. This approach can contribute to accountability mechanisms for NCD prevention.

Hierarchical Bayesian nonparametric models for knowledge discovery from electronic medical records

Electronic Medical Record (EMR) has established itself as a valuable resource for large scale analysis of health data. A hospital EMR dataset typically consists of medical records of hospitalized patients. A medical record contains diagnostic information (diagnosis codes), procedures performed (procedure codes) and admission details. Traditional topic models, such as latent Dirichlet allocation (LDA) and hierarchical Dirichlet process (HDP), can be employed to discover disease topics from EMR data by treating patients as documents and diagnosis codes as words. This topic modeling helps to understand the constitution of patient diseases and offers a tool for better planning of treatment. In this paper, we propose a novel and flexible hierarchical Bayesian nonparametric model, the word distance dependent Chinese restaurant franchise (wddCRF), which incorporates word-to-word distances to discover semantically-coherent disease topics. We are motivated by the fact that diagnosis codes are connected in the form of ICD-10 tree structure which presents semantic relationships between codes. We exploit a decay function to incorporate distances between words at the bottom level of wddCRF. Efficient inference is derived for the wddCRF by using MCMC technique. Furthermore, since procedure codes are often correlated with diagnosis codes, we develop the correspondence wddCRF (Corr-wddCRF) to explore conditional relationships of procedure codes for a given disease pattern. Efficient collapsed Gibbs sampling is derived for the Corr-wddCRF. We evaluate the proposed models on two real-world medical datasets - PolyVascular disease and Acute Myocardial Infarction disease. We demonstrate that the Corr-wddCRF model discovers more coherent topics than the Corr-HDP. We also use disease topic proportions as new features and show that using features from the Corr-wddCRF outperforms the baselines on 14-days readmission prediction. Beside these, the prediction for procedure codes based on the Corr-wddCRF also shows considerable accuracy.

Networking for big data

Big data is an emerging hot research topic due to its pervasive application in human society, such as government, climate, finance, and science. Currently, most research work on big data falls in data mining, machine learning, and data analysis. However, these amazing top-level killer applications would not be possible without the underneath support of networking due to their extremely large volume and computing complexity, especially when real-time or near-real-time applications are demanded.

The Nine Circles of Surveillance Hell: An Institutional View of Information Flows and Information Threats in Libraries

In the past few years, libraries have started to design public programs that educate patrons about different tools and techniques to protect personal privacy. But do end user solutions provide adequate safeguards against surveillance by corporate and government actors? What does a comprehensive plan for privacy entail in order that libraries live up to their privacy values? In this paper, the authors discuss the complexity of surveillance architecture that the library institution might confront when seeking to defend the privacy rights of patrons. This architecture consists of three main parts: physical or material aspects, logical characteristics, and social factors of information and communication flows in the library setting. For each category, the authors will present short case studies that are culled from practitioner experience, research, and public discourse. The case studies probe the challenges faced by the library—not only when making hardware and software choices, but also choices related to staffing and program design. The paper shows that privacy choices intersect not only with free speech and chilling effects, but also with questions that concern intellectual property, organizational development, civic engagement, technological innovation, public infrastructure, and more. The paper ends with discussion of what libraries will require in order to sustain and improve efforts to serve as stewards of privacy in the 21st century.