The objective of this thesis is to formalize, model, align and operationalize the evidence-based clinical algorithms of co-morbid chronic heart failure (CHF) and atrial fibrillation (AF) in order to provide clinical recommendations, care coordination and decision support to general practitioners (GPs). This thesis addresses following healthcare knowledge modeling issues: (a) modeling of healthcare knowledge, especially in terms of clinical guidelines and clinical pathways, to develop an ontology-based knowledge model for handling co-morbid diseases; (b) computerization of clinical pathways to offer point-of-care decision support; (c) alignment of ontologically-modeled disease-specific clinical pathways to handle co-morbid diseases; and (d) the provision of computerized decision support to GPs, based on modeled clinical guidelines and pathways, to assist them in handling co-morbid diseases. An elaborate OWL CP ontology for co-morbid CHF and AF was developed that can be executed to support the diagnosis and management of co-morbid CHF and AF in a general practice setting. / In this thesis we present an ontology based decision-support framework for handling co-morbidities by the alignment of ontologically modeled clinical practice guidelines (CPGs). The objective of this thesis is to formalize, model, align and operationalize the evidence-based clinical algorithms of co-morbid chronic heart failure (CHF) and atrial fibrillation (AF) in order to provide evidence-based clinical recommendations, care coordination and decision support to general practitioners (GPs) for effective management of CHF and AF. In this regard, the thesis addresses the following healthcare knowledge modeling issues: (a) modeling of healthcare knowledge, especially in terms of clinical guidelines and clinical pathways, to develop an ontology-based healthcare knowledge model for handling co-morbid diseases; (b) computerization of clinical pathways to offer point-of-care decision support; (c) alignment of ontologically-modeled disease-specific clinical pathways to handle co-morbid diseases; and (d) the provision of computerized decision support to general practitioners, based on modeled clinical guidelines and pathways, to assist them in handling chronic and co-morbid diseases. An elaborate OWL CP ontology for co-morbid CHF and AF—the CP ontology was developed that can be executed to support the diagnosis and management of co-morbid CHF and AF in a general practice setting. We have developed a decision support framework termed COMET (Co-morbidity Ontological Modeling & ExecuTion) that can handle three patient care scenarios, (i) patient has CHF; (ii) patient has AF; and (iii) patient develops a co-morbidity of both AF and CHF. COMET is accessible by web and is designed for GPs. COMET has been evaluated, both by simulated cases and by health professionals (GP and specialist), for its ability to handle single disease and comorbid care scenarios based on patient data and related constraints. The output at every phase is compared with the expected output as per single disease or comorbid management. Our results show that the resultant sequence of plans and their outcomes are comparable to the CP knowledge. Also, our ontology was able to handle any updates in the CP knowledge as advised by the domain experts

Constructing a Bayesian Network requires the conditional probabilities table (CPT) to be acquired, one for each variable or node in the network. When data mining is not available, CPTs must be acquired from the domain experts. The complexity of the direct elicitation is exponential on the number of parents of a variable, making direct elicitation from human experts impractical for a large number of causes. Causal models such as Noisy-OR, Noisy-AND, Noisy-MIN, Noisy-MAX and Recursive Noisy-OR have been developed that allow CPTs acquisition to be achieved with linear complexity on the number of causes. Their representation power is measured by their ability to encode the causal interactions. Causal interactions can be categorized into two types: reinforcing and undermining. The Non-Impeding Noisy-AND or NIN-AND tree causal model, developed by Xiang and Jia, is capable of modeling both types of interaction while retaining the linear complexity. The main challenge in utilizing the NIN-AND tree model to generate a CPT is that it requires its tree topology to be elicited. A NIN-AND tree topology is an encoding of the causal interactions between the causes. In this work we present two methods, Structure Elimination (SE) and Pairwise Causal Interaction (PCI), that allow indirect elicitations of the NIN-AND tree topology using some additional probabilities elicited from experts. We conduct human-based experiment to investigate the e ectiveness of the two methods in terms of accuracy by comparing them to the Direct Numerical (DN) elicitation method. We recruit participants from second year Computer Science students at the University of Guelph. The process involves training a participant into domain expert using a known NIN-AND tree model then acquire another NIN-AND tree model by applying the SE and PCI methods. The CPTs produced by the acquired NIN-AND tree models are then compared to the one obtained by using the DN method. Comparable CPT accuracies are obtained among models generated by di erent methods, even though SE and PCI requires a much smaller number of parameters in comparison to DN.

Background: Considerable amount of inappropriate antibiotic utilization has been observed in both acute and non-acute care hospitals. Literature has shown that strategies such as an order entry (OE) and computer decision support system (DSS) have improved prescribing practices in acute care settings. However, there is limited research on the effect of OE on antibiotic utilization in non-acute care settings. Objective: To determine the relationship between OE with DSS and antibiotic utilization in a complex continuing care and rehabilitation hospital. Methods: A retrospective analysis of OE and Pharmacy dispensing data, prospectively collected between July 1, 1999 and December 31, 2005, was conducted. Dispensing events for oral and intravenous antibiotics were merged with corresponding OE’s (when present) to form a final database of 4,739 dispensing events with 2,397 OE’s. The presence of OE and the proportion of OE to dispensing events formed the exposure variable while antibiotic utilization in defined daily dose (DDD) was calculated using dose and number of doses of an antibiotic. Antibiotic utilization was examined at the hospital and individual service in-patient unit levels (complex continuing care/CCC and rehabilitation medicine/REH). Statistical analysis consisting of multiple regression modeling was conducted to determine the association between use of OE and antibiotic utilization. Results: A best-fit model using multiple regression analysis at hospital level indicated a significant positive relationship between the presence of OE and antibiotic utilization when service, patient age, gender and antibiotic classes were accounted for. This model explained 11% of the variation in antibiotic utilization. No significant associations were found in the CCC in-patient unit while in the REH in-patient unit a significant positive relationship between the presence of OE and antibiotic utilization was observed. Similarly, antibiotic utilization increased significantly with increase in the proportion of OE to dispensing events at the hospital and REH in-patient unit levels but not in the CCC in-patient unit. Conclusion: The results of this study demonstrate that antibiotic utilization increased over the years following the inception of the OE system with DSS at the study hospital. Further research is required to examine the effect of OE with a rudimentary DSS on antibiotic utilization management in non-acute care. / Thesis (Master, Community Health & Epidemiology) -- Queen's University, 2007-07-13 10:47:38.035

<p>Diss. (sammanfattning) Umeå : Umeå universitet, 2003</p> / digitalisering@umu

This research addresses the design and development of a decision support tool to provide healthcare policy makers with insights and feedback when evaluating proposed patient flow and infection mitigation and control strategies in the emergency department (ED). An agent-based modeling (ABM) approach was used to simulate EDs, designed to be tuneable to specific parameters related to specification of topography, agent characteristics and behaviours, and the application in question. In this way, it allows for the user to simulate various ‘what-if’ scenarios related to infection spread and patient flow, where such policy questions may otherwise be left “best intent open loop” in practice. Infection spread modeling and patient flow modeling have been addressed by mathematical and queueing models in the past; however, the application of an ABM approach at the level of an institution is novel. A conjecture of this thesis is that such a tool should be augmented with Machine Learning (ML) technology to assist in performing optimization or search in which patient flow and infection spread are signals or variables of interest. Therefore this work seeks to design and demonstrate a decision support tool with ML capability for optimizing ED processes. The primary contribution of this thesis is the development of a novel, flexible, and tuneable framework for spatial, human-scale ABM in the context of a decision support tool for healthcare policy relating to infection spread and patient flow within EDs . The secondary contribution is the demonstration of the utility of ML for automatic policy generation with respect to the ABM tool. The application of ML to automatically generate healthcare policy in concert with an ABM is believed to be novel and of emerging practical importance. The tertiary contribution is the development and testing of a novel heuristic specific to the ML paradigm used: Genetic Programming (GP). This heuristic aids learning tasks performed in conjunction with ABMs for healthcare policy. The primary contribution is clearly demonstrated within this thesis. The others are of a more difficult nature; the groundwork has been laid for further work in these areas that are likely to remain open for the foreseeable future.

Bikes sharing systems have known a growing success all over the world. Several attempts have been made since the 1960s. The latest developments in ICT have enabled the system to become efficient. People can obtain real-time information about the position of the vehicles. More than 200 cities have already introduced the system and this trend keeps on with the launching of the NYC system in spring 2013. A new avatar of these means of transportation has arrived with the introduction of Autolib in Paris end of 2011.The objective of this thesis is to propose algorithms that may help to improve this system efficiency. Indeed, operating these systems induces several issues, one of which is the regulation problem. Regulation should ensures users that a right number of vehicles are present at any station anytime in order to fulfill the demand for both vehicles and parking racks. This regulation is often executed thanks to trucks that are travelling the city. This regulation issue is crucial since empty and full stations increase users' dissatisfaction. Finding the optimal strategy for regulating a network appears to be a difficult question. This thesis is divided into two parts. The first one deals with the "static" case. In this part, users' impact on the network is neglected. This is the case at night or when the system is closed. The operator faces a given repartition of the vehicles. He wants the repartition to match a target one that is known a priori. The one-truck and multiple-truck balancing problems are addressed in this thesis. For each one, an algorithm is proposed and tested on several instances. To deal with the "dynamic" case in which users interact with the system, a simulator has been developed. It is used to compare several strategies and to monitor redistribution by using trucks. Strategies not using trucks, but incentive policies are also tested: regularly updated prices are attached to stations to deter users from parking their vehicle at specified stations. At last, the question to find the best initial inventory is also addressed. It corresponds to the case when no truck are used within the day. Two local searches are presented and both aim at minimizing the total time lost by users in the system. The results obtained can be used as inputs for the target repartitions used in the first part. During my thesis, I participated to two EURO-ROADEF challenges, the 2010 edition proposed by EDF and the 2012 one by Google. In both case, my team reached the final phase. In 2010, our method was ranked fourth over all the participants and led to the publication of an article. In 2012, we ranked eighteenth over all the participants. Both works are added in the appendix

Due to the inherent hazardous characteristics associated with dolomite and development on dolomite, quantification of the stability attributes related to dolomite is essential. In large parts of South Africa, development on dolomite is inevitable due to the location thereof. The purpose of this study is to define an implementation framework for decision-making with regards to development on dolomite. The decision-making process is based on a dolomite stability investigation conducted by AGES North West (AGES, 2012) within Sarafina, Ikageng. The results from this study are interpreted by means of a decision support system that is based on the geo-environmental setting of the study area and the geotechnical properties related to the subsurface profile. This includes but is not limited to: Geo-environmental site conditions: • Drainage • Topography • Geophysical conditions • Regional geological conditions • Local geological conditions • Regional groundwater conditions • Local groundwater conditions Geotechnical stability of the dolomite based on the hazard characterisation and evaluation procedures: • Percussion drilling data • Receptacle development • Mobilisation agencies • Potential surface manifestation development space • Nature and mobilisation potential of the blanketing layer • The bedrock morphology These parameters are all inter-related and affect each other in various ways. During the study the importance of site specific observations and interpretations are emphasized. / Thesis (MSc (Environmental Sciences))--North-West University, Potchefstroom Campus, 2013

Due to the inherent hazardous characteristics associated with dolomite and development on dolomite, quantification of the stability attributes related to dolomite is essential. In large parts of South Africa, development on dolomite is inevitable due to the location thereof. The purpose of this study is to define an implementation framework for decision-making with regards to development on dolomite. The decision-making process is based on a dolomite stability investigation conducted by AGES North West (AGES, 2012) within Sarafina, Ikageng. The results from this study are interpreted by means of a decision support system that is based on the geo-environmental setting of the study area and the geotechnical properties related to the subsurface profile. This includes but is not limited to: Geo-environmental site conditions: • Drainage • Topography • Geophysical conditions • Regional geological conditions • Local geological conditions • Regional groundwater conditions • Local groundwater conditions Geotechnical stability of the dolomite based on the hazard characterisation and evaluation procedures: • Percussion drilling data • Receptacle development • Mobilisation agencies • Potential surface manifestation development space • Nature and mobilisation potential of the blanketing layer • The bedrock morphology These parameters are all inter-related and affect each other in various ways. During the study the importance of site specific observations and interpretations are emphasized. / Thesis (MSc (Environmental Sciences))--North-West University, Potchefstroom Campus, 2013

The world we live in today demands systems that make our lives easier and help us make the right choices on time. There exists a growing need for quality products that help us in our day to day activities. Easy-to-use computer-based decision support systems apply all available and applicable data with the correct model, knowledge and skill of decision makers to support the user to choose the best solution. It is therefore important to develop decision support systems correctly to be of value to the user. Looking at other information system developments, the author tries to suggest ways to develop decision support systems. System development methodologies are investigated to determine if they are able to address the development of the very important decision support system components. Five methodologies were discussed and researched for their theoretical suitability to address the development of decision support systems. The author performed qualitative research using case studies and semi-structured interviews to assess the use or non-use of system development methodologies in the development of decision support systems in a South African context. Content and cross-case analyses were used to achieve results that are discussed to broaden the knowledge on the development of decision support systems. The author provides some explanations to why system development methodologies were not used in the development of the case studies. This research not only contributes to the academic body of knowledge about using system development methodologies in the development of decision support systems, but could also be useful to developers embarking on a new decision support system development. / Thesis (MSc (Computer Science))--North-West University, Potchefstroom Campus, 2011.

This research addresses the design and development of a decision support tool to provide healthcare policy makers with insights and feedback when evaluating proposed patient flow and infection mitigation and control strategies in the emergency department (ED). An agent-based modeling (ABM) approach was used to simulate EDs, designed to be tuneable to specific parameters related to specification of topography, agent characteristics and behaviours, and the application in question. In this way, it allows for the user to simulate various ‘what-if’ scenarios related to infection spread and patient flow, where such policy questions may otherwise be left “best intent open loop” in practice. Infection spread modeling and patient flow modeling have been addressed by mathematical and queueing models in the past; however, the application of an ABM approach at the level of an institution is novel. A conjecture of this thesis is that such a tool should be augmented with Machine Learning (ML) technology to assist in performing optimization or search in which patient flow and infection spread are signals or variables of interest. Therefore this work seeks to design and demonstrate a decision support tool with ML capability for optimizing ED processes. The primary contribution of this thesis is the development of a novel, flexible, and tuneable framework for spatial, human-scale ABM in the context of a decision support tool for healthcare policy relating to infection spread and patient flow within EDs . The secondary contribution is the demonstration of the utility of ML for automatic policy generation with respect to the ABM tool. The application of ML to automatically generate healthcare policy in concert with an ABM is believed to be novel and of emerging practical importance. The tertiary contribution is the development and testing of a novel heuristic specific to the ML paradigm used: Genetic Programming (GP). This heuristic aids learning tasks performed in conjunction with ABMs for healthcare policy. The primary contribution is clearly demonstrated within this thesis. The others are of a more difficult nature; the groundwork has been laid for further work in these areas that are likely to remain open for the foreseeable future.