Healthcare information systems: data mining methods in the creation of a clinical recommender system

Recommender systems have been extensively studied to present items, such as movies, music and books that are likely of interest to the user. Researchers have indicated that integrated medical information systems are becoming an essential part of the modern healthcare systems. Such systems have evolved to an integrated enterprise-wide system. In particular, such systems are considered as a type of enterprise information systems or ERP system addressing healthcare industry sector needs. As part of efforts, nursing care plan recommender systems can provide clinical decision support, nursing education, clinical quality control, and serve as a complement to existing practice guidelines. We propose to use correlations among nursing diagnoses, outcomes and interventions to create a recommender system for constructing nursing care plans. In the current study, we used nursing diagnosis data to develop the methodology. Our system utilises a prefix-tree structure common in itemset mining to construct a ranked list of suggested care plan items based on previously-entered items. Unlike common commercial systems, our system makes sequential recommendations based on user interaction, modifying a ranked list of suggested items at each step in care plan construction. We rank items based on traditional association-rule measures such as support and confidence, as well as a novel measure that anticipates which selections might improve the quality of future rankings. Since the multi-step nature of our recommendations presents problems for traditional evaluation measures, we also present a new evaluation method based on average ranking position and use it to test the effectiveness of different recommendation strategies.     

Machine learning advances for time series forecasting

In this paper, we survey the most recent advances in supervised machine learning (ML) and high-dimensional models for time-series forecasting. We consider both linear and nonlinear alternatives. Among the linear methods, we pay special attention to penalized regressions and ensemble of models. The nonlinear methods considered in the paper include shallow and deep neural networks, in their feedforward and recurrent versions, and tree-based methods, such as random forests and boosted trees. We also consider ensemble and hybrid models by combining ingredients from different alternatives. Tests for superior predictive ability are briefly reviewed. Finally, we discuss application of ML in economics and finance and provide an illustration with high-frequency financial data.     

Material flow,material information,and the analytics of integrative enterprise information systems

Enterprise information systems (EIS) process highly abstracted information. They, nevertheless, are concerned with material systems. Information science has become increasingly analytic. This article draws attention back to the deeply embedded motive forces of ‘exchange’ and ‘money-information’ in the empiric systems that attend its analytics. The article further points to a danger that excessive abstraction can disconnect decision information from that in the processes of concern to EIS.     

Pre-defined and optional staging for the deployment of enterprise systems: a case study and a framework

The effective deployment of enterprise systems has been a major challenge for many organisations. Customising the new system, changing business processes, and integrating multiple information sources are all difficult tasks. As such, they are typically done in carefully planned stages in a process known as phased implementation. Using ideas from Option Theory, this article critiques aspects of phased implementation. One customer relationship management (CRM) project and its phased implementation are described in detail and ten other enterprise system deployments are summarised as a basis for the observation that almost all deployment stages are pre-defined operational steps rather than decision points. However, Option Theory suggests that optional stages, to be used only when risk materialises, should be integral parts of project plans. Although such optional stages are often more valuable than pre-defined stages, the evidence presented in this article shows that they are only rarely utilised. Therefore, a simple framework is presented; it first identifies risks related to the deployment of enterprise systems, then identifies optional stages that can mitigate these risks, and finally compares the costs and benefits of both pre-defined and optional stages.     

The impact of enterprise systems on process flexibility and organisational flexibility

In light of the current dynamic business environment, companies nowadays need to respond rapidly to changes. Companies often invest heavily in enterprise systems in the hope that these can improve their flexibility in coping with such changes. However, previous studies have shown that the impact of enterprise systems on flexibility can be either positive or negative. To resolve this inconsistency in the existing research, this paper suggests that a company's flexibility should be distinguished between process level and organisational level. Specifically, this paper proposes that enterprise systems will affect process flexibility negatively but affect organisational flexibility positively. The analysis results show that enterprise systems have different effects on process and organisational flexibility. Furthermore, industry clockspeed sets a boundary for the effect on process flexibility but not for that on organisational flexibility. Research and practical implications of this study are discussed.     

Configurations of New Public Management reforms and the efficiency,effectiveness and equity of public healthcare systems: a fuzzy-set Qualitative Comparative Analysis

ABSTRACT

Fuzzy-set Qualitative Comparative Analysis identifies configurations of New Public Management (NPM) reforms (privatization, consumerism, performance management, and corporatization) associated with perceptions of improvements in healthcare efficiency, effectiveness and equity in 14 European countries. Although these outcomes are pursued concurrently, no combination of the considered reforms appears to support success or failure across the board and the inter-relations between reforms shape their effects. Three NPM reform profiles are evident in Europe; (1) strong reformers, adopting a comprehensive package of reforms that are perceived to perform better than (2) partial reformers, with (3) limited reformers also doing better than partial reformers.     

Integration of hybrid wireless networks in cloud services oriented enterprise information systems

This article presents a hybrid wireless network integration scheme in cloud services-based enterprise information systems (EISs). With the emerging hybrid wireless networks and cloud computing technologies, it is necessary to develop a scheme that can seamlessly integrate these new technologies into existing EISs. By combining the hybrid wireless networks and computing in EIS, a new framework is proposed, which includes frontend layer, middle layer and backend layers connected to IP EISs. Based on a collaborative architecture, cloud services management framework and process diagram are presented. As a key feature, the proposed approach integrates access control functionalities within the hybrid framework that provide users with filtered views on available cloud services based on cloud service access requirements and user security credentials. In future work, we will implement the proposed framework over SwanMesh platform by integrating the UPnP standard into an enterprise information system.     

企业微型学习的设计研究

随着计算机网络技术和移动通信技术的飞速发展,越来越多的企业机构期望更高效地组织员工学习新的技能和专业知识,以此提升企业的竞争力。而此时移动学习和娱乐学习的理念出现并广为流行,企业的学习者也越来越关注学习方式和知识管理的便捷性和实时性,企业微型学习的发展正是顺应了这一理念的需求,它是继数字化学习之后出现的一个新型的学习模式。     

Collaborator or competitor: assessing the evidence supporting the role of social enterprise in health and social care

In many countries, social enterprise has been introduced into a competitive market-oriented environment as a substitute for publicly owned services, particularly in healthcare. In the United Kingdom, evidence for this move seems to derive from case studies where social enterprise operates in collaboration – as opposed to competition – with publicly owned services. Our systematic review demonstrates that there is no evidence to support the role of social enterprise as a substitute for publicly owned services. However, there is evidence to show that where social enterprise operates in a collaborative environment, enhanced outcomes can be achieved, such as connectedness, well-being and self-confidence.     

The impact of using kiosk on enterprise systems in service industry

The hospitality industry services many types of travellers. Each of them needs to be analysed differently in order to accurately determine their respective service quality attributes and customer delight. The effective and efficient enterprise information systems (EISs) play a significant role in traveller’s experience and in the competitive advantages that hotels can gain. For this study, self-service kiosks and guest service agents as part of hotel’s EISs are used to investigate the impact each has on the experience of business and leisure travellers. This study provides empirical results that further investigate how to improve the service quality for both types of travellers during the registration process. This process is the first physical interaction between the travellers and the hotel. Any problem in registering would generate a long-lasting negative first impression on the travellers, thus diminishing the customer delight. In the light of our findings, this study will contribute to the effective and efficient design of self-service kiosk systems, hotel’s EISs, and improved front office management to better accommodate the specific needs of both types of travellers.     

企业人力资本开发的体制和政策环境研究

文章讨论了如何创造人力资本开发的体制和政策环境,以培育和提高企业的核心能力,并且就人力资本开发的体制和政策环境的问题,向政府和企业,尤其是西部的政府和企业提出了一些建议。     

Market drivers of sustainability and sustainability learning capabilities: The moderating role of sustainability control systems

This study examines (i) the impact of market drivers of sustainability on the adoption of sustainability learning capabilities and (ii) the moderating role of sustainability control systems (SCS) on the relationship between market drivers of sustainability and sustainability learning capabilities. Drawing on the levers of control framework, stakeholder theory and organisational learning literature, survey data were collected from 175 large scale local and multinational companies operating in Sri Lanka. Findings reveal that market drivers of sustainability have a significant positive impact on sustainability learning capabilities. Whereas the interactive use of SCS shows a positive moderating impact, the diagnostic use of SCS shows a negative impact. The study enhances our understanding of (i) the influence of market drivers of sustainability on the adoption of sustainability learning capabilities and (ii) the use of SCS in enabling sustainability learning capabilities. The study reveals novel insights for managers responding to changing market drivers of sustainability, on how to (re)align different uses of SCS to enable sustainability learning capabilities.     

Machine learning algorithms for forecasting and backcasting blood demand data with missing values and outliers: A study of Tema General Hospital of Ghana

The major challenge in managing blood products lies in the uncertainty of blood demand and supply, with a trade-off between shortage and wastage, especially in most developing countries. Thus, reliable demand predictions can be imperative in planning voluntary blood donation campaigns and improving blood availability within Ghana hospitals. However, most historical datasets on blood demand in Ghana are predominantly contaminated with missing values and outliers due to improper database management systems. Consequently, time-series prediction can be challenging since data cleaning can affect models’ predictive power. Also, machine learning (ML) models’ predictive power for backcasting past years’ lost data is understudied compared to their forecasting abilities. This study thus aims to compare K-Nearest Neighbour regression (KNN), Generalised Regression Neural Network (GRNN), Neural Network Auto-regressive (NNAR), Multi-Layer Perceptron (MLP), Extreme Learning Machine (ELM) and Long Short-Term Memory (LSTM) models via a rolling-origin strategy, for forecasting and backcasting a blood demand data with missing values and outliers from a government hospital in Ghana. KNN performed well in forecasting blood demand (12.55% error); whereas, ELM achieved the highest backcasting power (19.36% error). Future studies can also employ ML algorithms as a good alternative for backcasting past values of time-series data that are time-reversible.     

Why HR policies fail to support workplace learning: the complexities of policy implementation in healthcare

An appropriate human resource policy infrastructure to support workplace learning has been advocated both within the literature on workplace learning and in official British Government guidance for healthcare organizations. Yet minimal empirical evidence exists to support the view that HR policies are able to promote greater use of workplace learning methods within organizations. This proposition was tested through collecting both quantitative and qualitative data from staff in British hospices. The findings demonstrated the limited effects of HR policies in this respect and five key factors were identified that appeared to influence HR policy implementation in this instance. These findings have wider significance for our understanding of the complex interrelationships that potentially exist between HR policies, their outcomes and the mediating factors associated with policy implementation.     

Examining the motivators of training transfer in an enterprise systems context

Enterprise systems (ES) are large software packages that have been widely adopted, but are complex to deploy. One way to obtain more value from them is to train end-users. However, little is known about the effectiveness of ES training. This study examines post-training behaviour in the ES environment through the concept of training transfer and the theoretical framework of self-determination theory. It proposes that end-users’ computer self-efficacy (CSE) and mastery orientation (MO), as well as the perceived ease-of-use (PEOU) of a system, influence their motivation to transfer the skills they have gained during training to their work environment and to use the system. Data was collected from 170 ES end-users, who had previously attended ES training, through a survey. Partial least squares modelling was used to analyse the data, and all of the hypotheses were supported. This study is among the first few studies that investigate the more distal impact of information systems training.     

On domain modelling of the service system with its application to enterprise information systems

Information systems are a kind of service systems and they are throughout every element of a modern industrial and business system, much like blood in our body. Types of information systems are heterogeneous because of extreme uncertainty in changes in modern industrial and business systems. To effectively manage information systems, modelling of the work domain (or domain) of information systems is necessary. In this paper, a domain modelling framework for the service system is proposed and its application to the enterprise information system is outlined. The framework is defined based on application of a general domain modelling tool called function-context-behaviour-principle-state-structure (FCBPSS). The FCBPSS is based on a set of core concepts, namely: function, context, behaviour, principle, state and structure and system decomposition. Different from many other applications of FCBPSS in systems engineering, the FCBPSS is applied to both infrastructure and substance systems, which is novel and effective to modelling of service systems including enterprise information systems. It is to be noted that domain modelling of systems (e.g. enterprise information systems) is a key to integration of heterogeneous systems and to coping with unanticipated situations facing to systems.     

A combined machine learning algorithms and DEA method for measuring and predicting the efficiency of Chinese manufacturing listed companies

Data Envelopment Analysis (DEA) is a linear programming methodology for measuring the efficiency of Decision Making Units (DMUs) to improve organizational performance in the private and public sectors. However, if a new DMU needs to be known its efficiency score, the DEA analysis would have to be re-conducted, especially nowadays, datasets from many fields have been growing rapidly in the real world, which will need a huge amount of computation. Following the previous studies, this paper aims to establish a linkage between the DEA method and machine learning (ML) algorithms, and proposes an alternative way that combines DEA with ML (ML-DEA) algorithms to measure and predict the DEA efficiency of DMUs. Four ML-DEA algorithms are discussed, namely DEA-CCR model combined with back-propagation neural network (BPNN-DEA), with genetic algorithm (GA) integrated with back-propagation neural network (GANN-DEA), with support vector machines (SVM-DEA), and with improved support vector machines (ISVM-DEA), respectively. To illustrate the applicability of above models, the performance of Chinese manufacturing listed companies in 2016 is measured, predicted and compared with the DEA efficiency scores obtained by the DEA-CCR model. The empirical results show that the average accuracy of the predicted efficiency of DMUs is about 94%, and the comprehensive performance order of four ML-DEA algorithms ranked from good to poor is GANN-DEA, BPNN-DEA, ISVM-DEA, and SVM-DEA.     

An exploratory review of the relationship between enterprise training and technology upgrading: evidence from South African manufacturing firms

The study examines the extent to which disaggregated training variables are related to technological upgrading, in the context of a middle-income developing country trying to manage its integration into the global economy. For a developing country, successful integration into the global economy requires that local manufacturing firms are able to competitively restructure, as a precondition for survival and long-term growth. Consequently, skills and technological upgrading are crucial in raising the international competitive advantage of local firms. Enterprise-provided training is one means that can be used by local firms to continuously upgrade their knowledge bases, increase their international competitiveness, and enhance employment growth over time. This paper uses South Africa as a case study, to demonstrate how economic reform measures can expose skills deficiencies in the manufacturing sector and lead to an increase in capital intensity of the sector. Exposure of skills deficiencies, in turn, raises the importance of skill-upgrading through schooling and training of existing workforce. Despite a couple of studies on the evolution of the labour market in South Africa, no previous research has explicitly examined the relationship between technological upgrading and disaggregated training/learning variables at the firm level. This paper aims to fill that gap by focusing on disaggregated enterprise-based training efforts. The study uses the Human Capital theoretical framework to answer the main research question: Which disaggregated learning variables (i.e., on-the-job or off-the-job training offered to different occupational groups) are significantly associated with technological upgrading? The study raises possible issues of heterogeneity in returns to training offered to different occupational groups in the context of technological-upgrading. On the other hand, technological upgrading may not necessarily always disadvantage all unskilled workers. Possible policy implications of research findings are outlined.     

Influence of high performance work systems on employee subjective well-being and job burnout: empirical evidence from the Chinese healthcare sector

Over the last two decades, high performance work systems (HPWSs) research has been dominated by examining the effects of these systems on firm performance. Research on the impact of HPWSs on employees has been marginalised. This study examines the impact of HPWSs on two psychological outcomes for employees, namely, subjective well-being (SWB) and workplace burnout, by utilising data collected from 1488 physicians and nurses in 25 Chinese hospitals. It also examines the moderating effects of employees' organisational based self-esteem (OBSE), as an individual intervention and physician–nurse relationships, as an organisational intervention, on the relationship between HPWSs and employee outcomes. HPWS is found to increase employees' SWB and decrease burnout. Such well-being-enhancing and burnout-relieving effects are stronger when employees have high OBSE. The positive effect of HPWS on SWB is also stronger when there is a collaborative relationship among employees in an organisation. The major contribution of this study is to unpack the ‘black box’ of how HPWS influences employee well-being in the Chinese healthcare sector context.     

Narrowing the scope of failure prediction using targeted fault load injection

As society becomes more dependent upon computer systems to perform increasingly critical tasks, ensuring that those systems do not fail becomes increasingly important. Many organizations depend heavily on desktop computers for day-to-day operations. Unfortunately, the software that runs on these computers is written by humans and, as such, is still subject to human error and consequent failure. A natural solution is to use statistical machine learning to predict failure. However, since failure is still a relatively rare event, obtaining labelled training data to train these models is not a trivial task. This work presents new simulated fault-inducing loads that extend the focus of traditional fault injection techniques to predict failure in the Microsoft enterprise authentication service and Apache web server. These new fault loads were successful in creating failure conditions that were identifiable using statistical learning methods, with fewer irrelevant faults being created.