Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)

Electronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex - it contains temporal, mixed-type and multimodal data packed in irregular episodes. We present a computational framework to harness EMR with minimal human supervision via restricted Boltzmann machine (RBM). The framework derives a new representation of medical objects by embedding them in a low-dimensional vector space. This new representation facilitates algebraic and statistical manipulations such as projection onto 2D plane (thereby offering intuitive visualization), object grouping (hence enabling automated phenotyping), and risk stratification. To enhance model interpretability, we introduced two constraints into model parameters: (a) nonnegative coefficients, and (b) structural smoothness. These result in a novel model called eNRBM (EMR-driven nonnegative RBM). We demonstrate the capability of the eNRBM on a cohort of 7578 mental health patients under suicide risk assessment. The derived representation not only shows clinically meaningful feature grouping but also facilitates short-term risk stratification. The F-scores, 0.21 for moderate-risk and 0.36 for high-risk, are significantly higher than those obtained by clinicians and competitive with the results obtained by support vector machines.

Mixed-initiative decision support for care planning based on clinical practice guidelines

Care Plan On-Line (CPOL) is an intranet based system that supports a “Coordinated Care” model for chronic/complex disease management. CPOL combines provision of solicited and unsolicited advice features based on integration of the electronic medical record (EMR) with its decision support logic. The objective is to support General Practitioners (GPs) in formulating a 12-month care plan of services such that: (a) the plan is proactive and patient-centered; (b) the GP is kept in awareness of project- and diseasespecific clinical practice guidelines; and (c) the support integrates with GP workflow in a natural fashion. A key feature of our approach is to blur the distinction of EMR and decision support by presenting guidelines in layers with the top-most being a problem-oriented presentation of patient status, progressing on through to patient-independent supporting evidence. In conjunction with a degree of automated inclusion of care planning services, the system demonstrates mixed user and software initiative. We describe the CPOL deployment setting, the challenges of guideline-based clinical decision support, our approach to guideline delivery, and the CPOL architecture.

Immobilized enzyme technology for debittering citrus fruit juices

There has been increased interest in the use of immobilized enzymes in fruit juice industry for debittering of citrus fruit juices due to their high efficiency to remove bitter flavonoids. The structure of naringin, responsible for immediate bitterness, and of limonin, responsible for "delayed bitterness" has been discussed. This chapter also discusses various attempts that have been made to immobilize enzymes on an appropriate support so as to enable their use in debittering of citrus fruit juices. These include physicochemical and enzyme biotechnological approaches which makes the fruit juice more acceptable and cost effective to the consumer. Despite of high volume of production of citrus fruits and fruit juices, suitable processes to produce non-bitter citrus juice by immobilized enzymes technology has not yet commercialized globally.

Management perspective for TQM solution

Quality management is an important research topical in construction industry. The aim of this paper is to review and investigate, via extensive literature reviews, the management perspectives when construction organization implementing total quality management (TQM). If it is successfully operated, competitive advantage will be enhanced that may lead to eight beneficial areas [improve quality and environmental performance; broaden business opportunities; benefit the community; increase market share; improve finance situation; enhance organizational effectiveness; streamline response to legal issues and lessen insurance budget] which favour commercial viability. However, there are challenges in doing so which include inexperience, resources and administrative constraints, inadequate management skill, and cultural differences. Therefore, in order to foster quality culture, it needs four management directions, namely construction management (CM), knowledge management (KM), project management (PM) and human resources management (HRM). One can reasonably conclude that the quality improvements by TQM are going to create long term commercial advantages.

Australian quantity surveyors utilize ICT and ERP system improving efficiency

Despite Information Communication Technology (ICT) can help to improve efficiency and Enterprise Resource Planning (ERP) system has been widely perceives as an efficient mean, diffusion rate is slow in construction industry and amongst quantity surveying profession. Today, quantity surveyor must frequently communicate with other stakeholder throughout the design and construct process and using information technology is a must. The more technologies evolve, the more quantity surveying with change and evolve to utilize these technologies. This paper, through literature review, firstly identifies perceived benefits of using ICT/ERP system, secondly concludes the critical success factors that may affect decision of adopting ICT/ERP tool in practice, and thirdly to suggest three effective evaluation tools before/after implementing ICT/ERP strategy. The ultimate goal is to advise how Australian quantity surveyors (QS) can utilize ICT and ERP system to improve efficiency.

Stabilized sparse ordinal regression for medical risk stratification

The recent wide adoption of electronic medical records (EMRs) presents great opportunities and challenges for data mining. The EMR data are largely temporal, often noisy, irregular and high dimensional. This paper constructs a novel ordinal regression framework for predicting medical risk stratification from EMR. First, a conceptual view of EMR as a temporal image is constructed to extract a diverse set of features. Second, ordinal modeling is applied for predicting cumulative or progressive risk. The challenges are building a transparent predictive model that works with a large number of weakly predictive features, and at the same time, is stable against resampling variations. Our solution employs sparsity methods that are stabilized through domain-specific feature interaction networks. We introduces two indices that measure the model stability against data resampling. Feature networks are used to generate two multivariate Gaussian priors with sparse precision matrices (the Laplacian and Random Walk). We apply the framework on a large short-term suicide risk prediction problem and demonstrate that our methods outperform clinicians to a large margin, discover suicide risk factors that conform with mental health knowledge, and produce models with enhanced stability. © 2014 Springer-Verlag London.

Stable feature selection for clinical prediction: Exploiting ICD tree structure using Tree-Lasso

Modern healthcare is getting reshaped by growing Electronic Medical Records (EMR). Recently, these records have been shown of great value towards building clinical prediction models. In EMR data, patients' diseases and hospital interventions are captured through a set of diagnoses and procedures codes. These codes are usually represented in a tree form (e.g. ICD-10 tree) and the codes within a tree branch may be highly correlated. These codes can be used as features to build a prediction model and an appropriate feature selection can inform a clinician about important risk factors for a disease. Traditional feature selection methods (e.g. Information Gain, T-test, etc.) consider each variable independently and usually end up having a long feature list. Recently, Lasso and related l1-penalty based feature selection methods have become popular due to their joint feature selection property. However, Lasso is known to have problems of selecting one feature of many correlated features randomly. This hinders the clinicians to arrive at a stable feature set, which is crucial for clinical decision making process. In this paper, we solve this problem by using a recently proposed Tree-Lasso model. Since, the stability behavior of Tree-Lasso is not well understood, we study the stability behavior of Tree-Lasso and compare it with other feature selection methods. Using a synthetic and two real-world datasets (Cancer and Acute Myocardial Infarction), we show that Tree-Lasso based feature selection is significantly more stable than Lasso and comparable to other methods e.g. Information Gain, ReliefF and T-test. We further show that, using different types of classifiers such as logistic regression, naive Bayes, support vector machines, decision trees and Random Forest, the classification performance of Tree-Lasso is comparable to Lasso and better than other methods. Our result has implications in identifying stable risk factors for many healthcare problems and therefore can potentially assist clinical decision making for accurate medical prognosis.

An assessment of riparian restoration outcomes in two rural catchments in south-western Victoria: Focusing on tree and shrub species richness, structure and recruitment characteristics

Riparian ecosystems are among the most degraded systems in the landscape,and there has been substantial investment in their restoration. Consequently, monitoring restoration interventions offers opportunities to further develop the science of riparian restoration, particularly how to move from small-scale implementation to a broader landscape scale. Here, we report on a broad range of riparian revegetation projects in two regions of south-western Victoria, the Corangamite and Glenelg-Hopkins Catchment Management Areas. The objectives of restoration interventions in these regions have been stated quite broadly, for example, to reinstate terrestrial habitat and biodiversity, control erosion and improve water quality. This study reports on tree and shrub composition, structure and recruitment after restoration works compared with remnant vegetation found regionally. Within each catchment, a total of 57 sites from six subcatchments were identified, representing three age-classes: <4, 4–8 and >8–12 years after treatment, as well as untreated (control) sites. Treatments comprised fencing to exclude stock, spraying or slashing to reduce weed cover, followed by planting with tube stock. Across the six subcatchments, 12 reference (remnant) sites were used to provide a benchmark for species richness, structural and recruitment characteristics and to aid interpretation of the effects of the restoration intervention. Vegetation structure was well developed in the treated sites by 4–8 years after treatment. However, structural complexity was higher at remnant sites than at treated or untreated sites due to a higher richness of small shrubs. Tree and shrub recruitment occurred in all remnant sites and at 64% of sites treated >4 years ago. Most seedling recruitment at treatment sites was by Acacia spp. This assessment provides data on species richness, structure and recruitment characteristics following restoration interventions. Data from this study will contribute to longitudinal studies of vegetation processes in riparian landscapes of south-western Victoria.

Ecological connectivity or barrier fence? Critical choices on the agricultural margins of Western Australia

Western Australia's State Barrier Fence represents a continuation of colonial era attitudes that considered kangaroos, emus and dingoes as 'vermin'. Recent plans to upgrade and extend the Barrier Fence have shown little regard for ecological impacts or statutory environmental assessment processes.

Feeding wild birds in gardens: a test of water versus food

Bird feeding in residential gardens is an increasingly popular human-wildlife interaction. In Australia, the practice is discouraged by most government and nongovernment wildlife conservation agencies, although advice varies and the most common recommendation is to provide water and habitat for birds rather than supplementary food. This study compares bird abundance and diversity when residents in a Melbourne municipality provide water for birds versus food. Bird abundance was greater when food was provided compared with water, but avian assemblages did not differ.

Improved risk predictions via sparse imputation of patient conditions in electronic medical records

Electronic Medical Records (EMR) are increasingly used for risk prediction. EMR analysis is complicated by missing entries. There are two reasons - the “primary reason for admission” is included in EMR, but the co-morbidities (other chronic diseases) are left uncoded, and, many zero values in the data are accurate, reflecting that a patient has not accessed medical facilities. A key challenge is to deal with the peculiarities of this data - unlike many other datasets, EMR is sparse, reflecting the fact that patients have some, but not all diseases. We propose a novel model to fill-in these missing values, and use the new representation for prediction of key hospital events. To “fill-in” missing values, we represent the feature-patient matrix as a product of two low rank factors, preserving the sparsity property in the product. Intuitively, the product regularization allows sparse imputation of patient conditions reflecting common comorbidities across patients. We develop a scalable optimization algorithm based on Block coordinate descent method to find an optimal solution. We evaluate the proposed framework on two real world EMR cohorts: Cancer (7000 admissions) and Acute Myocardial Infarction (2652 admissions). Our result shows that the AUC for 3 months admission prediction is improved significantly from (0.741 to 0.786) for Cancer data and (0.678 to 0.724) for AMI data. We also extend the proposed method to a supervised model for predicting of multiple related risk outcomes (e.g. emergency presentations and admissions in hospital over 3, 6 and 12 months period) in an integrated framework. For this model, the AUC averaged over outcomes is improved significantly from (0.768 to 0.806) for Cancer data and (0.685 to 0.748) for AMI data.

Prediciton of emergency events: a multi-task multi-label learning approach

Prediction of patient outcomes is critical to plan resources in an hospital emergency department. We present a method to exploit longitudinal data from Electronic Medical Records (EMR), whilst exploiting multiple patient outcomes. We divide the EMR data into segments where each segment is a task, and all tasks are associated with multiple patient outcomes over a 3, 6 and 12 month period. We propose a model that learns a prediction function for each task-label pair, interacting through two subspaces: the first subspace is used to impose sharing across all tasks for a given label. The second subspace captures the task-specific variations and is shared across all the labels for a given task. The proposed model is formulated as an iterative optimization problems and solved using a scalable and efficient Block co-ordinate descent (BCD) method. We apply the proposed model on two hospital cohorts - Cancer and Acute Myocardial Infarction (AMI) patients collected over a two year period from a large hospital emergency department. We show that the predictive performance of our proposed models is significantly better than those of several state-of-the-art multi-task and multi-label learning methods.

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.

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.

Response of feral cats to a track-based baiting programme using Eradicat baits

Summary The feral Cat (Felis catus) is a significant threat to Australian fauna, and reducing their impacts is considered an essential action for threatened species conservation. Poison baiting is increasingly being used for the broad scale control of feral cats. In this study, we measured the population response of feral cats to a track-based baiting programme using Eradicat baits in the semi-arid northern wheatbelt region of Western Australia. Over two years, 1500 baits were laid once annually and the response of feral cats was measured using remote cameras in a before–after, control–impact design. There was a significant reduction in feral cat activity in the second year, but not the first. During bait uptake trials, corvids removed the most number of baits, followed by cats and varanids. The lack of a response to baiting in the first year may be due to existing low cat numbers in the baited area and/or the timing of the baiting. We provide a list of key recommendations to help inform future cat baiting programmes and research.