Thesis (Ph. D.)--Indiana University, 2005. / Includes bibliographical references (leaves 69-76). Also available online (PDF file) by a subscription to the set or by purchasing the individual file.

Thesis (Ph. D.)--Indiana University, 2005. / Includes bibliographical references (leaves 69-76).

Thesis--University of Florida. / Description based on print version record. Typescript. Vita. Includes bibliographical references (leaves 137-143).

Physician assistants are medical professionals educated in an allopathic medical education model in the United States. In order to successfully matriculate, educate and graduate safe and effective health care providers in a 2-year time frame, the 4-year M.D. curriculum has been abbreviated and condensed leading to an intense, full-time cohort educational experience that taxes physician assistant students to their limits. The demanding workload can lead to fluctuations in mood and morale along with increased levels of psychological distress. This dissertation explores this under examined student experience by first introducing the physician assistant profession and the process by which it educates its members. The cohort patterns of mood and morale observed by faculty during the educational process are described using the conceptual and theoretical models of transformative learning, transition, change and cross-cultural adaptation as explanations for the observed experience. A retrospective naturalistic research paradigm utilizing focus groups elucidated the student perspective of the cohort medical education experience over the course of the didactic curriculum, and study results highlight a three-stage experience consistent with stages-of-change theories from multiple disciplines. In addition, a prominent pattern of emotional subthemes provide a window into the psychological significance of this transformative experience. A better understanding of the effects of this academically rigorous and psychologically challenging medical education process on physician assistant students clarifies opportunities for amelioration of student challenges while simultaneously enhancing the ultimate goal of developing safe and effective health care providers.

The supply of non-physician clinicians (NPCs), such as physician assistant (PAs), could significantly influence demand requirements in medical workforce projections. This study predicts supply of and demand for PAs from 2006 to 2020. The PA supply model utilized the number of certified PAs, the educational capacity (at 10% and 25% expansion) with assumed attrition rates, and retirement assumptions. Gross domestic product (GDP) chained in 2000 dollar and US population were utilized in a transfer function trend analyses with the number of PAs as the dependent variable for the PA demand model. Historical analyses revealed strong correlations between GDP and US population with the number of PAs. The number of currently certified PAs represents approximately 75% of the projected demand. At 10% growth, the supply and demand equilibrium for PAs will be reached in 2012. A 25% increase in new entrants causes equilibrium to be met one year earlier. Robust application trends in PA education enrollment (2.2 applicants per seat for PAs is the same as for allopathic medical school applicants) support predicted increases. However, other implications for the PA educational institutions include recruitment and retention of qualified faculty, clinical site maintenance and diversity of matriculates. Further research on factors affecting the supply and demand for PAs is needed in the areas of retirement age rates, gender, and lifestyle influences. Specialization trends and visit intensity levels are potential variables.

Burnout among primary care providers, which include physicians, nurse practitioners, and physician assistants, can negatively impact patients, providers, and organizations. Researchers have reported that up to 37% of primary care physicians experience burnout, yet the prevalence, predictors, and outcomes associated with primary care nurse practitioner burnout remains unknown. Since 69% of nurse practitioners provide primary care to patients, this dissertation investigates the predictors and outcomes associated with primary care nurse practitioner burnout. A history of burnout as well as the importance of investigating burnout among primary care nurse practitioners are discussed in the first chapter. A systematic review of the predictors and outcomes of primary care provider burnout is discussed in the second chapter. The third chapter describes a cross-sectional study conducted among 396 primary care nurse practitioners from New Jersey and Pennsylvania, which investigated whether the practice environment is associated with nurse practitioner burnout. The fourth chapter describes a cross-sectional study investigating whether the use of multifunctional electronic health records is associated with primary care nurse practitioner burnout. The fifth chapter includes another cross-sectional study examining the relationship between primary care nurse practitioner burnout and quality of care, and if the practice environment moderates the relationship between burnout and quality of care. Finally, the sixth concluding chapter summarizes the findings from chapters two to five and provides recommendations for future research, practice, and policy.

Background The landscape of clinical decision support systems (CDSSs) is evolving to include increasingly sophisticated data-driven methods, such as machine learning, to provide clinicians with predictions about patients’ risk for negative outcomes or their likely responses to treatments (predictive CDSSs). However, trust in predictive CDSSs has shown to challenge clinician adoption of these tools, precluding the ability to positively impact patient outcomes. This is particularly salient in the hospital setting where clinician time is scarce, and predictive CDSSs have the potential to decrease preventable mortality. Many have advised that clinicians should be involved in the development, implementation, and evaluation of predictive CDSSs to increase translation from development to adoption. Yet, little is known about the prevalence of clinician involvement or the factors that influence clinicians’ trust in predictive CDSSs for the hospital setting. The specific aims of this dissertation were: (a) to survey the literature on predictive CDSSs for the hospital setting to describe the prevalence and methods of clinician involvement throughout stages of system design, (b) to identify and characterize factors that influence clinicians’ trust in predictive CDSSs for in-hospital deterioration, and (c) to explore the use of a trust conceptual framework for incorporating clinician expertise into machine learning model development for predicting rapid response activation among hospitalized non-ICU patients using electronic health record (EHR) data. Methods To address the first aim (presented in Chapter Two), a scoping review was conducted to summarize the state of the science of clinician (nurse, physician, physician assistant, nurse practitioner) involvement in predictive CDSS design, with a specific focus on systems using machine learning methods with EHR data for in-hospital decision-making. To address the second aim (presented in Chapter Three), semi-structured interviews with nurses and prescribing providers (i.e., physicians, physicians assistants, nurse practitioners) were conducted and analyzed inductively and deductively (using the Human-Computer Trust conceptual framework) to identify factors that influence trust in predictive CDSSs, using an implemented predictive CDSS for in-hospital deterioration as a grounding example. Finally, to address the third aim (presented in Chapter Four), clinician expertise was elicited in the form of model specifications (requirements, insights, preferences) for facilitating factors shown to influence trust in predictive CDSSs, as guided by the Human-Computer Trust conceptual framework. Specifications included: (a) importance ranking of input features, (b) preference for a more sensitive or specific model, (c) acceptable false positive and negative rates, and (d) prediction lead time. Specifications informed development and evaluation of machine learning models predicting rapid response activation using retrospective EHR data. Results The scoping review identified 80 studies. Seventy-six studies described developing a machine learning model for a predictive CDSS, 28% of which described involving clinicians during development. Clinician involvement during development was categorized as: (a) determining clinical relevance/correctness, (b) feature selection, (c) data preprocessing, and (d) serving as a gold standard. Only five studies described implemented predictive CDSSs and no studies described systems in routine use. The qualitative investigation with 17 clinicians (9 prescribing providers, 8 nurses) confirmed that the Human-Computer Trust concepts of perceived understandability and perceived technical competence are factors that influence hospital clinicians’ trust in predictive CDSSs and further characterized these factors (i.e., themes). This study also identified three additional themes influencing trust: (a) actionability, (b) evidence, and (c) equitability, and found that clinicians’ needs for explanations of machine learning models and the impact of discordant predictions may vary according to the extent to which clinicians rely on the predictive CDSS for decision-making. Only two of 28 categories/sub-categories and one theme emerged uniquely to nurses or prescribing providers. Finally, the third study elicited model specifications from fifteen total clinicians. Not all clinicians answered all questions. Vital sign frequency was ranked the most important feature category on average (n = 8 clinicians), the most frequently preferred prediction lead time was shift-change/8-12 hours (n = 9 clinicians), most preferred a more specific than sensitive model (71%; n = 7 clinicians), the average acceptable false positive rate was 42% (n = 9 clinicians), the average acceptable false negative rate was 29% (n = 6 clinicians). These specifications informed development and testing of four machine learning classification models (ridge regression, decision trees, random forest, and XGBoost). 249,676 patient admissions from 2015–2018 at a large northeastern hospital system were modeled to predict whether or not patients would have a rapid response within the 12-hour shift. The random forest classifier met clinician’s average acceptable false positive (27.7%) and negative rates (28.9%) and was marginally more specific (72.2%) than sensitive (71.1%) on a holdout test set. Conclusions Studies do not routinely report clinician involvement in model development of predictive CDSSs for the hospital setting and publications on implementation considerably lag those on development. Nurses and prescribing providers described largely shared experiences of trust in predictive CDSSs. Clinicians’ reliance on the predictive CDSS for decision-making within the target clinical workflow should be considered when aiming to facilitate trust. Incorporating clinician expertise into model development for the purpose of facilitating trust is feasible. Future research is needed on the impact of clinician involvement on trust, clinicians’ personal attributes that influence trust, and explanation design. Increased education for clinicians about predictive CDSSs is recommended.