Chaotic genetic algorithm and Adaboost ensemble metamodeling approach for optimum resource planning in emergency departments.

Long length of stay and overcrowding in emergency departments (EDs) are two common problems in the healthcare industry. To decrease the average length of stay (ALOS) and tackle overcrowding, numerous resources, including the number of doctors, nurses and receptionists need to be adjusted, while a number of constraints are to be considered at the same time. In this study, an efficient method based on agent-based simulation, machine learning and the genetic algorithm (GA) is presented to determine optimum resource allocation in emergency departments. GA can effectively explore the entire domain of all 19 variables and identify the optimum resource allocation through evolution and mimicking the survival of the fittest concept. A chaotic mutation operator is used in this study to boost GA performance. A model of the system needs to be run several thousand times through the GA evolution process to evaluate each solution, hence the process is computationally expensive. To overcome this drawback, a robust metamodel is initially constructed based on an agent-based system simulation. The simulation exhibits ED performance with various resource allocations and trains the metamodel. The metamodel is created with an ensemble of the adaptive neuro-fuzzy inference system (ANFIS), feedforward neural network (FFNN) and recurrent neural network (RNN) using the adaptive boosting (AdaBoost) ensemble algorithm. The proposed GA-based optimization approach is tested in a public ED, and it is shown to decrease the ALOS in this ED case study by 14%. Additionally, the proposed metamodel shows a 26.6% improvement compared to the average results of ANFIS, FFNN and RNN in terms of mean absolute percentage error (MAPE).

Inclusion of social indicators in decision support tools for the selection of sustainable site remediation options.

Sustainable remediation requires a balanced decision-making process in which environmental, economic and social aspects of different remediation options are all considered together and the optimum remediation solution is selected. More attention has been paid to the evaluation of environmental and economic aspects, in particular to reduce the human and environmental risks and the remediation costs, to the exclusion of social aspects of remediation. This paper investigates how social aspects are currently considered in sustainability assessments of remediation projects. A selection of decision support tools (DSTs), used for the sustainability assessment of a remediation project, is analyzed to define how social aspects are considered in those tools. The social indicator categories of the Sustainable Remediation Forum - United Kingdom (SuRF-UK), are used as a basis for this evaluation. The consideration of social aspects in the investigated decision support tools is limited, but a clear increase is noticed in more recently developed tools. Among the five social indicator categories defined by SuRF-UK to facilitate a holistic consideration of social aspects of a remediation project only "Human health and safety" is systematically taken into account. "Neighbourhood and locality" is also often addressed, mostly emphasizing the potential disturbance caused by the remediation activities. However, the evaluation of 'Ethics and Equality', Communities and community involvement', and 'Uncertainty and evidence' is often neglected. Nevertheless, concrete examples can be found in some of the investigated tools. Specific legislation, standard procedures, and guidelines that have to be followed in a region or country are mainly been set up in the context of protecting human and ecosystem health, safety and prevention of nuisance. However, they sometimes already include some of the aspects addressed by the social indicators. In this perspective the use of DST to evaluate the sustainability of a site remediation project, should be tuned to the legislation, guidelines and procedures that are in force in a specific country or region.

Impact of an Atrial Fibrillation Decision Support Tool on thromboprophylaxis for atrial fibrillation.

BACKGROUND: Appropriate thromboprophylaxis for patients with atrial fibrillation (AF) remains a national challenge. METHODS: We hypothesized that provision of decision support in the form of an Atrial Fibrillation Decision Support Tool (AFDST) would improve thromboprophylaxis for AF patients. We conducted a cluster randomized trial involving 15 primary care practices and 1,493 adults with nonvalvular AF in an integrated health care system between April 2014 and February 2015. Physicians in the intervention group received patient-level treatment recommendations made by the AFDST. Our primary outcome was the proportion of patients with antithrombotic therapy that was discordant from AFDST recommendation. RESULTS: Treatment was discordant in 42% of 801 patients in the intervention group. Physicians reviewed reports for 240 patients. Among these patients, thromboprophylaxis was discordant in 63%, decreasing to 59% 1 year later (P = .02). In nonstratified analyses, changes in discordant care were not significantly different between the intervention group and control groups. In multivariate regression models, assignment to the intervention group resulted in a nonsignificant trend toward decreased discordance (P = .29), and being a patient of a resident physician (P = .02) and a higher HAS-BLED score predicted decreased discordance (P = .03), whereas female gender (P = .01) and a higher CHADSVASc score (P = .10) predicted increased discordance. CONCLUSIONS: Among patients whose physicians reviewed recommendations of the decision support tool discordant therapy decreased significantly over 1 year. However, in nonstratified analyses, the intervention did not result in significant improvements in discordant antithrombotic therapy.

Healthcare performance turned into decision support.

PURPOSE: The purpose of this study is to first create an overview of relevant factors directly influencing employee absence in the healthcare sector. The overview is used to further investigate the factors identified using employee satisfaction survey scores exclusively. The result of the overall objective is a management framework that allows managers to gain insight into the current status of risk factors with high influence on employee absence levels. DESIGN/METHODOLOGY/APPROACH: The research consists of a quantitative literature study supported by formal and semi-formal interviews conducted at the case organisations. Employee satisfaction surveys were applied to analyse the development over time of selected factors correlated with concurrent employee absence rates. Checking for causal results, comparisons with the included published literature findings were also carried out. FINDINGS: Four major clustered factors, three of which constitute the term "social capital", showed a high degree of connection with employee absence rates. The factors are general satisfaction, fairness, reliance and co-operation. Integrating the four elements in a management framework will provide valuable and holistic information about the determinants with regard to current levels of employee absence. The framework will be a valuable support for leaders with the authority to alter the determinants of employee absence. RESEARCH LIMITATIONS/IMPLICATIONS: Since a great part of the empirical material is supplied from the healthcare sector, the results obtained could be restricted to this sector. Inclusion of data from Arbejdsmarkedets Tillaegspension (ATP) showed no deviation from the results in the healthcare sector. PRACTICAL IMPLICATIONS: The product of the study is a decision support tool for leaders to cope with levels of employee absence. The framework is holistic and can prove to be a valuable tool to take a bearing of where to focus future initiatives. ORIGINALITY/VALUE: Gathering former observational studies in a complete overview embracing many relevant factors that influence sickness absence has not yet been attempted. Hospital management is provided with valuable information when given insight into the factors that control employee absence behaviour. Having this insight will enable the managers to promote a healthy working environment, thus lowering employee absence rates to a minimum.

How business intelligence can improve value.

Case studies of three healthcare organizations reinforce the premise that business intelligence--the ability to convert data into actionable information for decision making--is critical to demonstrating improved value.

Malaria elimination: moving forward with spatial decision support systems.

Operational challenges facing contemporary malaria elimination have distinct geospatial elements including the need for high-resolution location-based surveillance, targeted prevention and response interventions, and effective delivery of essential services at optimum levels of coverage. Although mapping and geographical reconnaissance (GR) has traditionally played an important role in supporting malaria control and eradication, its full potential as an applied health systems tool has not yet been fully realised. As accessibility to global positioning system (GPS), geographic information system (GIS) and mobile computing technology increases, the role of an integrated spatial decision support system (SDSS) framework for supporting the increased operational demands of malaria elimination requires further exploration, validation and application; particularly in the context of resource-poor settings.

The impact of integrated care on direct nursing home care.

BACKGROUND/AIM: The introduction of integrated nursing home care is an important policy goal in many countries and is expected to affect the type, frequency and duration of activities delivered to nursing home residents. The exact impact however is unknown. The aim of this paper is to reduce this information gap in order to provide decision supporting information to policy makers and managers. DESIGN/METHODS/ETHICAL ISSUES: At three measurement points between 1999 and 2003, caregivers belonging to 18 functions registered activities delivered to somatic and psycho-geriatric nursing home residents in The Netherlands. Residents either received traditional care, integrated care or care that contained elements of traditional and integrated care (hybrid care). Thirty-six thousand and seventy-one registration lists were used for data analysis. Data analysis included determining, comparing and linking the (total) average frequency and duration of each activity per care type, measurement point and type of resident. RESULTS: The (total) average frequency and total duration of most activities were higher for integrated care than for traditional and hybrid care. The average duration per activity was generally higher for traditional care. The (total) average frequency of most direct care activities at most measurement points and the total average duration per resident per day were higher for somatic care than for psycho-geriatric care. CONCLUSIONS: The introduction of integrated nursing home care affects the total average duration and frequency of direct care activities. However, there is no noticeable impact on individual activities or on differences in activities received by somatic and psycho-geriatric residents and the degree to which the occurrence of an activity is related to the duration of that activity. This is because a large proportion of care delivery represents patterned behaviour (routines). Because existing routines are difficult to get rid of, we should not have too high expectations about the effect of integrated care on service delivery.

An integrative health information systems approach for facilitating strategic planning in hospitals.

This article presents a framework for developing strategic information systems (SISs) for hospitals. It proposes a SIS formulation process which incorporates complexity theory, strategic/organizational analysis theory, and conventional MIS development concepts. Within the formulation process, four dimensions of SIS are proposed as well as an implementation plan. A major contribution of this article is the development of a hospital SIS framework which permits an organization to fluidly respond to external, interorganizational, and intraorganizational influences. In addition, this article offers a checklist which managers can utilize in developing an SIS in health care.

Integrated healthcare resource planning and management.

Management information systems (MIS) and decision support systems (DSS), used as part of broader healthcare technology management, are considered to be health technologies. As such, they should meet the criteria of affordability, appropriateness, cost-effectiveness, ease of use and sustainability if they are to be implementable and have a lasting impact on healthcare service delivery. They should also facilitate and support improved quality of healthcare. We have developed a suite of management-support tools around a concept of integrated healthcare resource planning and management (iHRPM). We believe that these tools meet the above-mentioned criteria and therefore lend themselves to widespread applicability in diverse healthcare and socio-economic contexts, not least in supporting performance monitoring and benchmarking.

Developing and implementing a patient-centered IT strategy.

The Army Medical Department (AMEDD), a comprehensive worldwide integrated healthcare system with an annual budget of more than $6 billion, more than 50,000 employees, and 2.4 million beneficiaries, developed and implemented a comprehensive patient-centered enterprise-wide information management and information technology strategy to facilitate information management systems and infrastructure decisions by leaders. This article describes a patient-centered model used to organize and link healthcare activities and activity leaders to portray patient care, administrative, business, financial, supply, and strategic support information systems. Activity and IT leaders applied a refined strategic alignment model to identify specific clinical, business, and IT goals and to detail the necessary infrastructure investments using a systems view. The use of patient and process outcome measures tied to the AMEDD's Balanced Score Card' helped leaders to manage IT strategy execution. Now, two years into the effort, a sample activity strategy--outpatient care--is used to illustrate the application of these tools to the development and implementation of a patient-centered IT strategy.

The STRATEGY project: decision tools to aid sustainable restoration and long-term management of contaminated agricultural ecosystems.

The STRATEGY project (Sustainable Restoration and Long-Term Management of Contaminated Rural, Urban and Industrial Ecosystems) aimed to provide a holistic decision framework for the selection of optimal restoration strategies for the long-term sustainable management of contaminated areas in Western Europe. A critical evaluation was carried out of countermeasures and waste disposal options, from which compendia of state-of-the-art restoration methods were compiled. A decision support system capable of optimising spatially varying restoration strategies, that considered the level of averted dose, costs (including those of waste disposal) and environmental side effects was developed. Appropriate methods of estimating indirect costs associated with side effects and of communicating with stakeholders were identified. The importance of stakeholder consultation at a local level and of ensuring that any response is site and scenario specific were emphasised. A value matrix approach was suggested as a method of addressing social and ethical issues within the decision-making process, and was designed to be compatible with both the countermeasure compendia and the decision support system. The applicability and usefulness of STRATEGY outputs for food production systems in the medium to long term is assessed.

A critical evaluation of the strategy project.

The STRATEGY project (sustainable restoration and long-term management of contaminated rural, urban and industrial ecosystems; www.strategy-ec.org.uk) addressed the need for a holistic decision framework for the selection of optimal remediation strategies for long-term sustainable management of contaminated areas in Western Europe. The project considered both technical and social aspects of implementing restoration strategies for urban and rural environments. The importance of considering socially relevant objectives in addition to the dose reduction was emphasised. A critical evaluation was carried out on 101 selected countermeasures, (including rural waste disposal options), a model was developed to aid optimising countermeasure strategies and a method of carrying out participatory decision-making suggested. The outputs of the project are described and critically evaluated.

Analysis of primary health care utilisation in south-western Finland--a tool for management.

Long-term health care planning is presently not based on the needs of the population at the local level in Finland but rather, it is based on retroactive economic values and already realised budget in hospital and primary health care. The existing health care structure and its health care practices continue to guide the supply of services. While we have the most extensive databases on primary health care and hospital services, such tools are not used in the broadest possible sense in the present health care planning at the local level. Simple and informative indicators available to health care planners and decision-makers from databases at the local level were used to appraise the use of health care services. Statistical profiles of health care clients were classified by age groups within the health authority area (population of 13,000) of Paimio-Sauvo in south-western Finland with the intent to explain utilisation of primary health care services, their coverage, and repeat visits as well as groups not using those services. Physicians recorded reasons for each patient visit with the ICD-10 categories. In the case municipalities, primary health care services provided 100% coverage to children of 0-6 years of age and more than 70% coverage to other groups. Most primary health care expenditures were assessed for people 65 years or older in 2000. As an example of a municipality, hospital and primary health care expenditures within Paimio varied from 24 to 30.4% of the total obligations for the last 10 years.

Integrated healthcare networks' performance: a growth curve modeling approach.

This study examines the effects of integration on the performance ratings of the top 100 integrated healthcare networks (IHNs) in the United States. A strategic-contingency theory is used to identify the relationship of IHNs' performance to their structural and operational characteristics and integration strategies. To create a database for the panel study, the top 100 IHNs selected by the SMG Marketing Group in 1998 were followed up in 1999 and 2000. The data were merged with the Dorenfest data on information system integration. A growth curve model was developed and validated by the Mplus statistical program. Factors influencing the top 100 IHNs' performance in 1998 and their subsequent rankings in the consecutive years were analyzed. IHNs' initial performance scores were positively influenced by network size, number of affiliated physicians and profit margin, and were negatively associated with average length of stay and technical efficiency. The continuing high performance, judged by maintaining higher performance scores, tended to be enhanced by the use of more managerial or executive decision-support systems. Future studies should include time-varying operational indicators to serve as predictors of network performance.