Even though most clinical information systems (CIS) today are technically sound, the number of successful implementations of these systems is low. For that reason, understanding the characteristics and challenges for organizations implementing CIS is now considered key to successful information technology deployment (Lorenzi & Riley, 1997). Although theory driven information systems models and CIS studies exist, an integrated model to predict a successful CIS has not been evaluated. The purpose of this research was to evaluate the ability of a theoretically-based integrated model of CIS success (CISSM) to predict a successful CIS from the clinicians' perspective. Data were collected and analyzed from 234 registered nurses in 4 hospitals who had used the Cerner PowerChart Admission Health Profile (AHP) longer than 3 months. Construct validity and internal consistency reliability of the 23-item online instrument were established. The results of stepwise multiple regression analyses provided tentative support for the CISSM model.

abstract: Surgery as a profession requires significant training to improve both clinical decision making and psychomotor proficiency. In the medical knowledge domain, tools have been developed, validated, and accepted for evaluation of surgeons' competencies. However, assessment of the psychomotor skills still relies on the Halstedian model of apprenticeship, wherein surgeons are observed during residency for judgment of their skills. Although the value of this method of skills assessment cannot be ignored, novel methodologies of objective skills assessment need to be designed, developed, and evaluated that augment the traditional approach. Several sensor-based systems have been developed to measure a user's skill quantitatively, but use of sensors could interfere with skill execution and thus limit the potential for evaluating real-life surgery. However, having a method to judge skills automatically in real-life conditions should be the ultimate goal, since only with such features that a system would be widely adopted. This research proposes a novel video-based approach for observing surgeons' hand and surgical tool movements in minimally invasive surgical training exercises as well as during laparoscopic surgery. Because our system does not require surgeons to wear special sensors, it has the distinct advantage over alternatives of offering skills assessment in both learning and real-life environments. The system automatically detects major skill-measuring features from surgical task videos using a computing system composed of a series of computer vision algorithms and provides on-screen real-time performance feedback for more efficient skill learning. Finally, the machine-learning approach is used to develop an observer-independent composite scoring model through objective and quantitative measurement of surgical skills. To increase effectiveness and usability of the developed system, it is integrated with a cloud-based tool, which automatically assesses surgical videos upload to the cloud. / Dissertation/Thesis / Ph.D. Biomedical Informatics 2013

A dissertation submitted to the Faculty of Arts in fulfilment of the requirements for the Degree of Doctor of Philosophy (Library and Information Studies) in the Department of Information Studies at the University Of Zululand, 2017 / This study examined access and use of clinical informatics among medical doctors at University College Hospital, Nigeria and King Edward VIII Hospital, South Africa. The specific objectives of the study were to explain the purposes of using clinical informatics; determine the benefits of using clinical informatics in the selected teaching hospitals; ascertain the availability of clinical informatics infrastructure in the selected teaching hospitals; identify the clinical informatics facilities that are accessible to medical doctors in the selected teaching hospitals; determine the factors that influence the behavioural intention to use clinical informatics by medical doctors in the selected teaching hospitals; determine the policies that guide the effective accessibility and utilisation of clinical informatics among medical doctors in the selected teaching hospitals; and investigate the challenges that faced both the access to and the use of clinical informatics among medical doctors in the selected teaching hospitals. The study adopted the post-positivist paradigm which combines both qualitative and quantitative research methods. The study largely used a survey design. The sample for the study was drawn from medical doctors in two purposively selected teaching hospitals in Nigeria and South Africa. The teaching hospitals were King Edward V111 hospital, Durban, South Africa and University College Hospital, Ibadan, Nigeria. The two teaching hospitals were selected because they belong to the first generation of teaching hospitals in Nigeria and South Africa, among other reasons. It was believed that they would be well established in terms of funding towards infrastructure and human development in their respective countries. Convenience sampling was used to select the respondents for the study. The questionnaire was administered to 413 medical doctors, 258 (63%) of whom returned the questionnaire. Interviews were also conducted with the heads of the ICT units at the University College Hospital in Ibadan, Nigeria, and King Edward VIII Hospital in Durban, South Africa. The quantitative data aspect of the study was analysed using descriptive statistics and Statistical Package for Social Sciences (SPSS), while the qualitative aspect of the data was analysed through the use of qualitative contents analysis. The study was guided by the Unified theory of acceptance and use of technology (UTAUT). The essence of using this theory is to identify the factors that influence the use of clinical informatics. The finding of the study reveals that there was an association between the demographic variables and the use of clinical informatics. It was established that there was a significant association between the medical department and the use of electronic medical records. An assessment of the socio-demographic characteristics and the use of the Clinical Decision Support System revealed that there was a significant association between the years of medical practice and the use of Clinical Decision Support System. The finding also revealed that social demographic variables such as age, years of practice and position were all significant related with the use of diagnostic image archiving. Furthermore, the surveyed medical doctors stated that their main purpose of using clinical informatics is for medical diagnosis. It was also discovered that there is association between the teaching hospitals and the use of clinical informatics for knowledge sharing. In addition, clinical informatics was found to influence the spirit of team work amongst the medical doctors through knowledge sharing with their professional colleagues and their medical students. Similarly, there were association between the teaching hospitals treatment of patients and effective healthcare delivery. In addition, the major benefit of using clinical informatics in the two hospitals was to reduce medical errors. The most available clinical informatics tools in the selected teaching hospitals were the Diagnosis Image Archiving and Clinical Decision Support System. Performance expectancy and effort expectancy were identified as the factors from the UTAUT that influenced the medical doctors’ behavioural intention to use clinical informatics resources in the selected teaching hospitals. The non-availability of clinical informatics resources was identified as the main challenge facing the effective access to and use of clinical informatics. In addition, the two hospitals relied on the ICT policies of other institutions and did not have their own ICT policies, which was problematic. The study concluded that the clinical informatics environments in the two teaching hospitals are inadequate and there is poor access to clinical informatics resources among medical doctors in the selected teaching hospitals. Major recommendations of the study include the need to establish ICT policies and increase investment in clinical informatics resources at the surveyed teaching hospitals in order to promote effective and value-based healthcare delivery. In addition, the hospital management should create awareness on the importance and benefits of clinical informatics particularly for the medical doctors through informal and continuing education and training such as workshops and short courses. Moreover, the hospital managements need to partner with relevant stakeholders such as government, corporate bodies, and departments of health. This is for the provision of adequate and suitable environment to support the access and use of clinical informatics. Further studies on the various types of health informatics such as nursing informatics, pharmacy informatics and veterinary informatics are recommended. It is also suggested that the study should be extended to other regions of Africa. The study is significant and makes tangible contributions to technology acceptance and use in clinical medicine from developing country contexts such as Nigeria and South Africa giving the increasing role of information and communication technology in diagnosis, prescription, treatment, monitoring and overall management of patient care in an environment characterized by complex diseases. The study has the potential to inform policy, practises, and also contribute to this research in the general area of social information in Africa.

Indiana University-Purdue University Indianapolis (IUPUI) / Healthcare providers in hospital intensive care units (ICUs) maintain patient situation awareness by following task management and communication practices. They create and manipulate several paper-based and digital information sources, with the overall aim to constantly inform themselves and their colleagues of dynamically evolving patient conditions. However, when increased communication means that healthcare providers potentially interrupt each other, enhanced patient-situation awareness comes at a price. Prior research discusses both the use of technology to support increased communication and its unintended consequence of (wanted and unwanted) notification interruptions. Using qualitative research techniques, I investigated work practices that enhance the patient-situation awareness of physicians, fellows, residents, nurses, students, and pharmacists in a medical ICU. I used the Locales Framework to understand the observed task management and communication work practices. In this study, paper notes were observed to act as transitional artifacts that are later digitized to organize and coordinate tasks, goals, and patient-centric information at a team and organizational level. Non digital information is often not immediately digitized, and only select information is communicated between certain ICU team members through synchronous mechanisms such as face-to-face or telephone conversations. Thus, although ICU providers are exceptionally skilled at working together to improve a critically ill patient’s condition, the use of paper-based artifacts and synchronous communication mechanisms induces several interruptions while contextually situating a clinical team for patient care. In this dissertation, I also designed and evaluated a mobile health technology tool, known as PANI (Patient-centered Notes and Information Manager), guided by the Locales framework and the participatory involvement of ICU healthcare providers as co designers. PANI-supported task management induces minimal interruptions by: (1) rapidly generating, managing, and sharing clinical notes and action-items among clinicians and (2) supporting the collaboration and communication needs of clinicians through a novel visual and tactile notification system. The long-term contribution of this research suggests guidelines for designing mobile health technology interventions that enhance ICU patient situation-awareness and reduce unwanted interruptions to clinical workflow.

No description available.

No description available.

Information and communication technologies can be used to deliver healthcare services and improve the healthcare system. Any electronic healthcare system whose usage results in the efficient and enhanced quality of healthcare is an eHealth system and can be beneficial for medical enterprises. Despite the advantages that eHealth systems offer, medical enterprises are often reluctant to abandon their paper-based systems and embrace eHealth solutions. Through a review of existing eHealth literature, this study identified generic technologies used within South African medical enterprises. Fourteen (14) technologies, that represent a basket of eHealth systems for supporting the business management, professional clinical informatics, patient information storage and consumer health informatics functional areas, were identified. The study then aimed to determine the state of adoption of these technologies as well as the factors influencing adoption. The technological, organisational and environmental (TOE) factors that contributed to the current state of adoption were identified through a review of existing TOE literature. A model that explores the effects of these pre-determined TOE factors on the propensity to adopt eHealth was developed and tested. A cross-sectional, quantitative study was carried out and survey data was collected from a sample of 130 medical enterprises in South Africa. Data was collected using a structured questionnaire. Correlation analysis was used to test the model’s hypotheses and hierarchical regression was used to test the overall TOE model. By using the TOE framework, the study has provided a theoretical contribution and addressed a gap in the literature into the barriers and determinants of the adoption of information and communication technologies (ICTs) in healthcare. The results of the study show that South African medical enterprises use systems that range from simple electronic fund transfer systems to more complex electronic record and clinical decision support systems. Of the 14 technologies that were identified, business information systems such as medical aid claims submission systems and electronic record systems for patient and fee related information were the most adopted while a steady, but continued increase in the adoption of clinical health information systems was observed. Specifically, the study reveals that electronic fund transfer systems are the most adopted systems while ePrescription systems are the least used. Furthermore, the study shows that in addition to the enterprises’ operating period, perceived benefits, IT infrastructure, senior clinician involvement, resource commitment and external pressure are correlated with the propensity to adopt while system complexity is a barrier to technology adoption.

The aim of this study is to examine the impact of a cloud-based CDS alerting system for SIRS, a precursor to sepsis, and sepsis itself, on adult patient and process outcomes at VCU Health System. The two main hypotheses are: 1) the implementation of cloud-based SIRS and sepsis alerts will lead to lower sepsis-related mortality and lower average length of stay, and 2) the implementation of cloud-based SIRS and sepsis alerts will lead to more frequent ordering of the Sepsis PowerPlan and more recording of sepsis diagnoses. To measure these outcomes, a pre-post study was conducted. A pre-implementation group diagnosed with sepsis within the year leading up to the alert intervention consisted of 1,551 unique inpatient visits, and the three-year post-implementation sample size was 9,711 visits, for a total cohort of 11,262 visits. Logistic regression and multiple linear regression were used to test the hypotheses. Study results showed that sepsis-related mortality was slightly higher after the implementation of SIRS alerts, but the presence of sepsis alerts did not have a significant relationship to mortality. The average length of stay and the total number of recorded sepsis diagnoses were higher after the implementation of both SIRS and sepsis alerts, while ordering of the Sepsis Initial Resuscitation PowerPlan was lower. There is preliminary evidence from this study that more sepsis diagnoses are made as a result of alert adoption, suggesting that clinicians can consider the implementation of these alerts in order to capture a higher number of sepsis diagnoses.

Disease subtyping has been a critical aim of precision and personalized medicine. With the potential to improve patient outcomes, unsupervised and semi-supervised methods for determining phenotypes of subtypes have emerged with a recent focus on matrix and tensor factorization. However, interpretability of proposed models is debatable. Principal component analysis (PCA), a traditional method of dimensionality reduction, does not impose non-negativity constraints. Thus coefficients of the principal components are, in cases, difficult to translate to real physical units. Non-negative matrix factorization (NMF) constrains the factorization to positive numbers such that representative types resulting from the factorization are additive. Archetypal analysis (AA) extends this idea and seeks to identify pure types, archetypes, at the extremes of the data from which all other data can be expressed as a convex combination, or by proportion, of the archetypes. Using AA, this study sought to evaluate the sufficiency of AKI staging criteria through unsupervised subtyping. Archetype analysis failed to find a direct 1:1 mapping of archetypes to physician staging and also did not provide additional insight into patient outcomes. Several factors of the analysis such as quality of the data source and the difficulty in selecting features contributed to the outcome. Additionally, after performing feature selection with lasso across data subsets, it was determined that current staging criteria is sufficient to determine patient phenotype with serum creatinine at time of diagnosis to be a necessary factor.