Browsing by Subject "Decision support"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Developing a decision support tool for improved aquatic invasive species management
    (2013-03) Sharpe, Leah M.
    Aquatic invasive species (AIS) are a serious problem with adverse ecological, economic, and social impacts. These wide-ranging impacts mean similarly wide ranges of affected and interested parties (stakeholders) and of knowledge and data types being involved in AIS decisions. Decision support tools (DST) can be powerfully effective methods for helping to simplify complex decisions, incorporating different types of knowledge, and assisting in clear communication between involved parties. Developing a useful DST, however, requires understanding the needs, priorities, and concerns of broader stakeholders as well as the managers responsible for making the decisions. It also requires understanding the legal and policy context for these decisions. This dissertation reports the results of research conducted to understand stakeholders’ attitudes and concerns about genetic biocontrol (a new AIS control technology currently under development), understand the strengths and weaknesses of the current decision-making process used by AIS managers, and examine the effectiveness of the National Invasive Species Act, the key piece of federal AIS legislation regarding management of AIS. Together, these results form building blocks for developing a DST for improved management of AIS. Information on stakeholder perspectives on development of new AIS control technologies, involving genetic manipulations, was gathered in a series of focus groups in the United States Great Lakes and Lake Champlain regions. Stakeholders were enthusiastic about the potential inherent in these new technologies but remained deeply concerned about potential unintended consequences. Key concerns related to ecological impacts, the cost of development, and the possibility that this research will detract from other, ongoing control work. Stakeholders also had a number of recommendations for development of these new technologies that have implications for broader AIS management. These recommendations included engaging stakeholders throughout the development process, employing clear go/no-go reasoning, and using a transparent decision-making process. A series of interviews with natural resource managers was undertaken to improve understanding of the current decision-making environment and identify its strengths and weakness. These interviews illuminated the priorities and concerns underlying managers’ decision-making processes, their perceptions of existing strengths and weaknesses of these processes, and the issues that a decision support tool could help them to better address. In their work, managers must balance a wide range of priorities competing with one another for limited resources (e.g., prevention and containment efforts, research into new control tools, control and eradication efforts). The existing decision-making environment succeeds at facilitating coordination between agencies and communication with the broader public. This process, however, currently lacks several principles of robust decision-making including sufficient scientific basis, structure, documentation, and an adaptive element. The results indicate that AIS decisions could be strengthened by explicitly incorporating these principles into the decision-making process and that use of a decision support tool would be an effective way of carrying out such incorporation. Finally, I analyzed the National Invasive Species Act, arguably the most important federal policy dealing with AIS, using peer-reviewed and grey literature, as well as natural resource manager interviews to assess whether or not the Act had met its stated goals. The results indicate the Act has had limited success in achieving its objectives, especially in preventing introductions of new invasive species and limiting the spread of invasive species already present, but has been effective in organizing national and regional coordination via the Aquatic Nuisance Species Task Force and its regional panels. Results suggest that reauthorizations of the Act should grant additional authority to regulate introductions via pathways other than ballast water to a federal agency and that the Aquatic Nuisance Species Task Force should be granted additional authority and resources to allow it to further increase regional coordination of control and containment efforts. Together, these results allowed me to design a blueprint for a DST responsive to the needs of stakeholders, managers, and federal level policy. I developed a simplified sample of the DST to illustrate how it combines spatial data with manager experience and stakeholder priorities to determine key areas for management actions (i.e. monitoring, quarantines, and control efforts).
  • Thumbnail Image
    Item
    Enhancing Data-Driven Decision Support with Multi-Perspective Solutions
    (2020-08) Wang, Yaqiong
    As digital systems become ubiquitous, providing all-around support for decision makers has become a significant part of contemporary information systems. To this end, numerous data-driven analytics techniques have been widely adopted by various platforms to facilitate decision making in a wide variety of application domains, e.g., product choice, employee recruitment, and medical diagnosis. The appropriate application of various data-driven methodologies for decision support in complex real-world contexts is crucial to gain benefits and to avoid unexpected consequences and, thus, the ability take into account multiple perspectives for better decision support represents an important challenge. In order to provide insights into this question, this thesis focuses on investigating some of the problems existing in decision support applications and attempts to provide various solutions and empirical evidence of the effectiveness of these solutions. Specifically, my thesis proposes to provide more nuanced decision support in different application domains by balancing different aspects of decision support models or by providing complementary sources of information for decision makers, e.g., balancing accuracy and long-tailness to address popularity bias in recommender systems; using individual prediction reliability to complement outcome prediction to support decision making in highly risk-sensitive domains like medical diagnosis or financial markets; providing complementary channels to fulfill online consumption decision support in the retailing industry. Solutions and findings provided by my thesis advance the understanding of decision support problems in multifaceted contexts, and have practical implications for information systems that adopt data-driven methods.
  • Thumbnail Image
    Item
    Personalized surgical risk assessment using population-based data analysis
    (2013-02) AbuSalah, Ahmad Mohammad
    The volume of information generated by healthcare providers is growing at a relatively high speed. This tremendous growth has created a gap between knowledge and clinical practice that experts say could be narrowed with the proper use of healthcare data to guide clinical decisions and tools that support rapid information availability at the clinical setting. In this thesis, we utilized population surgical procedure data from the Nationwide Inpatient Sample database, a nationally representative surgical outcome database, to answer the question of how can we use population data to guide the personalized surgical risk assessment process. Specifically, we provided a risk model development approach to construct a model-driven clinical decision support system utilizing outcome predictive modeling techniques and applied the approach on a spinal fusion surgery which was selected as a use case. We have also created The Procedure Outcome Evaluation Tool (POET); which is a data-driven system that provides clinicians with a method to access NIS population data and submit ad hoc multi-attribute queries to generate average and personalized data-driven surgical risks. Both systems use patient demographics and comorbidities, hospital characteristics, and admission information data elements provided by NIS data to inform clinicians about inpatient mortality, length of stay, and discharge disposition status.