Timely and appropriate clinical decisions can be lifesaving, and decision support systems could help facilitate this. However, user adoption of clinical decision support systems (CDSS) and their impact on patient care have been disappointing. Contemporary theories in information systems and several evaluation studies have failed to explain or predict the adoption of CDSS. To find out why I conducted a qualitative inquiry using the constructivist grounded theory method. Guided by the theory of planned behaviour, I designed a functional clinical decision support system called DermML. Then, I used it as a stimulus to elicit responses through semi-structured interviews with doctors, a community to which I also belong. Besides the interview data, I also collected demographic data from the participants and anonymous clickstream data from DermML. I found that the clinical community is diverse, and their knowledge needs are varied yet predictable. Using theoretical sampling, constant comparison and iterative conceptualization, I scaled my findings to a substantive theory that explains the difference in practitioners' knowledge needs and predicts adoption based on CDSS type and use context. Having designed DermML myself, the data provided me with design insights that I have articulated as prescriptive design theory. I posit that GT can generate explanatory and predictive theories and prescriptive design theories to guide action. This study eliminates the boundaries between the developers of CDSS, study participants, future users and knowledge mobilization partners. I hope the rich data I collected and the insights I derived help improve the adoption of CDSS and save lives. / Thesis / Doctor of Philosophy (PhD)

Aim: To examine the adoption of CCDS by paramedics, including the impact of CCDS on paramedic role and practice. Methods: Systematic review of CCDS in emergency care followed by a cluster-randomised controlled trial (C-RCT) of CCDS with a qualitative component involving 42 paramedics at two study sites. Results: 19/20 studies identified for inclusion in the systematic review were from the Emergency Department setting, with no studies from prehospital care. The focus of the studies was on process of care (19/20) rather than patient outcomes (5/20). Positive impacts were reported in 15/19 (79%) process of care studies. Only two patient outcome studies were able to report findings (one positive, one negative). Results relating to CCDS implementation were reported as an ad hoc response to problems encountered. In this C-RCT paramedics used CCDS with 12% of eligible patients (site one: 2%; site two: 24%). Intervention paramedics were twice as likely to refer patients to a falls service as those in the control group (usual care) (relative risk = 2.0; 95% Cl 1.1 to 3.7) although conveyance rates were unaltered (relative risk = 1.1; 95% Cl 0.8 to 1.5) and episode of care was unchanged (-5.7 minutes; 95% Cl -38.5 to 27.2). When CCDS was used patient referral to falls services was three times as likely (relative risk = 3.1; 95% Cl 1.4 to 6.9), and non-conveyance was twice as likely (risk = 2.1; 95% Cl 1.1 to 3.9) and overall episode of care fell by 114 minutes (95% Cl from 77.2 to 150.3). Reasons given for not using CCDS included technical problems, lack of integration, it was not sophisticated enough to influence decision making. Paramedics adapted when and how they used CCDS to suit context and patient condition. Conclusion: There is little existing evidence in relation to CCDS use in the emergency care setting, and the prehospital emergency care setting in particular. Studies of CCDS undertaken in emergency departments have shown benefit, particularly in relation to process of care. The C-RCT found that CCDS use by paramedics was low, particularly at site one, but use was associated with higher rates of patient referral and non-conveyance, and shorter episodes of care. There were encouraging signs that CCDS can support a new decision making role for paramedics. The study provides useful lessons for policy makers, practitioners and researchers about the potential benefits of CCDS and the challenges to adoption of new technology in emergency prehospital care.

Telenursing is a highly specialized area of nursing practice that has evolved in response to the advent of new technologies within the delivery of health care. Telenursing has been defined as “the use of communications and information technology [ICT’s] to deliver health and health care services and information over large and small distances (CRNBC, 2016). Telenurses use health information systems (HIS) in the form of a Clinical Decision Support System (CDSS) to assist callers with their health related concerns on a 24/7 basis. As decision making is an integral part of telenurse practice, particularly because they are using a CDSS while assessing the caller over the phone, it was important to understand the factors that influence the decision making process so as to better support telenurse practice in terms of education as well as other supports. This thesis identified those factors and used Rasmussen’s Decision Ladder as a model in order to provide a framework for telenursing. It was found that there were several factors identified that influenced how telenurses made decisions while using a CDSS. Additionally, the decision ladder was validated as a framework to describe telenurse practice. / Graduate

Poisonings account for 0.8% of emergency room visits each year. Our review of current toxicological resources revealed a gap in their ability to provide expedient calculations and recommendations, as they are broad in scope and time-consuming to read. Time is crucial in a toxicologic emergency. Delay in first dose can lead to life-threatening sequelae. To bridge the gap, we developed the Antidote Application (AA), a computational system that automatically provides patient-specific antidote treatment recommendation(s) and individualized dose calculation(s). We implemented 27 algorithms that describe FDA approved use and evidence-based practices found in primary literature for the treatment of common toxin exposure. The AA covers 29 antidotes recommended by Poison Control and toxicology experts, 31 toxins from 19 toxin classes, and over 200 toxic entities. We implemented the AA in two formats: a standalone downloadable application for offline use and an online web application. The AA represents a unique educational resource for the study of toxicology with the potential of being adopted for point of care decision support. The system also provides guidance for reporting toxic exposures regionally and nationally as required by accrediting bodies and some states. The AA system has the potential for reducing initial dose delays and medication errors. To the best of our knowledge, the AA is the first educational and decision support system in toxicology that provides patient-specific treatment recommendations and drug dose calculations. The downloadable and online Antidote Applications are publically available at http://www.met-hilab.org/files/antidote/antidote_application.jar and http://projects.met-hilab.org/antidote/ respectively.

We describe an online clinical decision support (CDS) system, Lung Cancer Assistant (LCA), which we have developed to aid the clinicians in arriving at informed treatment decisions for lung cancer patients at multidisciplinary team (MDT) meetings. LCA integrates rule-based and probabilistic decision support within a single platform. To our knowledge, this is the first time this has been achieved in the context of CDS in cancer care. Rule-based decision support is achieved by an original ontological guideline rule inference framework that operates on a domain-specific module of Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT), containing clinical concepts and guideline rule knowledge elicited from the major national and international guideline publishers. It adopts a conventional argumentation-based decision model, whereby the decision options are listed along with arguments derived by matching the patient records to the guideline rule base. As an additional feature of this framework, when a new patient is entered, LCA displays the most similar patients to the one being viewed. Probabilistic inference is provided by a Bayesian Network (BN) whose structure and parameters have been learned based on the English Lung Cancer Database (LUCADA). This allows LCA to predict the probability of patient survival and lay out how the selection of different treatment plans would affect it. Based on a retrospective patient subset from LUCADA, we present empirical results on the treatment recommendations provided by both functionalities of LCA and discuss their strengths and weaknesses. Finally, we present preliminary work, which may allow utilising the BN to calculate survival odd ratios that could be translated into quantitative degrees of support for the guideline rule-based arguments. An online version of LCA is accessible on http://lca.eng.ox.ac.uk.

No description available.

No description available.

<p> The constantly changing and dynamic nature of medical knowledge has proven to be challenging for healthcare professionals. Due to reliance on human knowledge the practice of medicine in many cases is subject to errors that endanger patients' health and cause substantial financial loss to both public and governmental health sectors. Computer based clinical guidelines have been developed to help healthcare professionals in practicing medicine. Currently, the decision making steps within most guideline modeling languages are limited to the evaluation of basic logic expressions. On the other hand, data mining analyses aim at building descriptive or predictive mining models that contain valuable knowledge; and researchers in this field have been active to apply data mining techniques on health data. However, this type of knowledge can not be represented using the current guideline specification standards.</p> <p> In this thesis, we focus is on encoding, sharing and finally using the results obtained from a data mining study in the context of clinical care and in particular at the point of care. For this purpose, a knowledge management framework is proposed that addresses the issues of data and knowledge interoperability. Standards are adopted to represent both data and data mining results in an interoperable manner; and then the incorporation of data mining results into guideline-based Clinical Decision Support Systems is elaborated. A prototype tool has been developed as a part of this thesis that serves as the proof of concept which provides an environment for clinical guideline authoring and execution. Finally three real-world clinical case studies are presented.</p> / Thesis / Master of Applied Science (MASc)

Clinical risk assessment of chronic illnesses is a challenging and complex task which requires the utilisation of standardised clinical practice guidelines and documentation procedures in order to ensure consistent and efficient patient care. Conventional cardiovascular decision support systems have significant limitations, which include the inflexibility to deal with complex clinical processes, hard-wired rigid architectures based on branching logic and the inability to deal with legacy patient data without significant software engineering work. In light of these challenges, we are proposing a novel ontology and machine learning-driven hybrid clinical decision support framework for cardiovascular preventative care. An ontology-inspired approach provides a foundation for information collection, knowledge acquisition and decision support capabilities and aims to develop context sensitive decision support solutions based on ontology engineering principles. The proposed framework incorporates an ontology-driven clinical risk assessment and recommendation system (ODCRARS) and a Machine Learning Driven Prognostic System (MLDPS), integrated as a complete system to provide a cardiovascular preventative care solution. The proposed clinical decision support framework has been developed under the close supervision of clinical domain experts from both UK and US hospitals and is capable of handling multiple cardiovascular diseases. The proposed framework comprises of two novel key components: (1) ODCRARS (2) MLDPS. The ODCRARS is developed under the close supervision of consultant cardiologists Professor Calum MacRae from Harvard Medical School and Professor Stephen Leslie from Raigmore Hospital in Inverness, UK. The ODCRARS comprises of various components, which include: (a) Ontology-driven intelligent context-aware information collection for conducting patient interviews which are driven through a novel clinical questionnaire ontology. (b) A patient semantic profile, is generated using patient medical records which are collated during patient interviews (conducted through an ontology-driven context aware adaptive information collection component). The semantic transformation of patients’ medical data is carried out through a novel patient semantic profile ontology in order to give patient data an intrinsic meaning and alleviate interoperability issues with third party healthcare systems. (c) Ontology driven clinical decision support comprises of a recommendation ontology and a NICE/Expert driven clinical rules engine. The recommendation ontology is developed using clinical rules provided by the consultant cardiologist from the US hospital. The recommendation ontology utilises the patient semantic profile for lab tests and medication recommendation. A clinical rules engine is developed to implement a cardiac risk assessment mechanism for various cardiovascular conditions. The clinical rules engine is also utilised to control the patient flow within the integrated cardiovascular preventative care solution. The machine learning-driven prognostic system is developed in an iterative manner using state of the art feature selection and machine learning techniques. A prognostic model development process is exploited for the development of MLDPS based on clinical case studies in the cardiovascular domain. An additional clinical case study in the breast cancer domain is also carried out for the development and validation purposes. The prognostic model development process is general enough to handle a variety of healthcare datasets which will enable researchers to develop cost effective and evidence based clinical decision support systems. The proposed clinical decision support framework also provides a learning mechanism based on machine learning techniques. Learning mechanism is provided through exchange of patient data amongst the MLDPS and the ODCRARS. The machine learning-driven prognostic system is validated using Raigmore Hospital's RACPC, heart disease and breast cancer clinical case studies.

Background: Type 2 diabetes mellitus (T2DM) is a complex health condition that impacts multiple organ systems and contributes to both acute and chronic health problems. In the United States (U.S.), T2DM is a growing health concern with increasing prevalence among both adult and pediatric populations (American Diabetes Association [ADA], 2015; Dea, 2011). Developing a comprehensive plan of care that incorporates a multifaceted treatment and prevention plan is necessary to address this growing health concern and reduce overall morbidity and mortality. Problem: The Edmund Primary Care (EPC) practice data for routine annual diabetic foot exams, annual eye exams, annual urine microalbumin, smoking cessation education and recommendations for pneumococcal polysaccharide do not meet the ADA (American Diabetes Association, 2015) recommendations for patients with T2DM.Design: Quality improvement (QI) project applying the Plan-Do-Study-Act (PDSA) cycle to develop a process change to improve diabetic preventative care measures for hemoglobin A1C, urine microalbumin, diabetic foot exams, and optometry referrals. Setting: A small, nurse practitioner owned, family practice clinic targeting patients 18 years and older with a diagnosis of T2DM.Intervention: A fishbone diagram to conduct a root cause analysis led to identification of key factors contributing to the problem. A comprehensive process change integrating a Diabetic Assessment Flow Sheet (DAFS) and diabetic foot exam sheet was developed to address the problem. Expected Outcome: Increase in rates of completion to at least 90% over eight weeks. Results: Analyzed with run charts demonstrating an increase in rates of completion to 100% for A1C, urine microalbumin, diabetic foot exams, and optometry referrals. A positive percent of change for each measure is as follows: A1C 7%; urine microalbumin 43%; diabetic foot exams 150%; and referrals to optometrist 43%. Significance: This QI project emphasizes the importance of implementing a system to evaluate the quality of care being delivered. It also highlights the usefulness of the PDSA cycle as a method to implementing quality improvement measures in health care. Lastly, this QI project demonstrated the effectiveness of flow sheets in improving the quality of care delivered to patients with T2DM.