Thesis (Ph.D.)--Duquesne University, 2004. / Title from document title page. Abstract included in electronic submission form. Includes bibliographical references (p. 204-209 ) and index.

This dissertation focuses on utilizing data-driven approaches to objectively measure variation in the quality of care across different hospitals, understand how physicians make dynamic admission and routing decisions for patients, and propose potential changes in practice to improve the quality of care and patient flow management. This analysis was performed in the context of Intensive Care Units (ICUs) and the Emergency Department (ED). In the first part, we assess variation in the overall quality of care provided by both urban and rural hospitals under the same integrated healthcare delivery system when augmenting administrative data with detailed patient severity scores from the electronic medical records (EMRs). Using a new template matching methodology for more objective comparison, we found that the use of granular EMR data significantly reduces the variation across hospitals in common patient severity-of-illness levels. Further, we found that hospital rankings on 30-day mortality and estimates of length-of-stay (LOS) are statistically different from rankings based on administrative data. In the second part, we study ICU admission decision-making dynamically throughout a patient’s stay in the general ward/the Transitional Care Unit (TCU). We first used an instrumental variable approach and modern multivariate matching methods to rigorously estimate the potential benefits and costs of transferring patients to the ICU based on a real-time risk score for deterioration. We then used the quantified impact to calibrate a comprehensive simulation model to evaluate system performances under various new ICU transfer policies. We show that proactively transferring the most severe patients to the ICU could reduce mortality rates and LOS without increasing ICU congestion and causing other adverse effects. In the third part, we focus on understanding how physicians make ICU admission decisions for patients in the ED. We first used two sets of reduced-form regressions to understand 1) what and how patient risk factors and system controls impact the admission decision from the ED; and 2) what are the potential benefits of admitting patients from the ED to the ICU. We then proposed a dynamic discrete choice structural model to estimate to what extent physicians account for the inter-temporal externalities when deciding to admit a specific patient to the ICU, to the ward or let him/her wait in the ED. Note that the structural model estimation is still an ongoing process and more investigation is required to fine tune the details. Therefore, we will not discuss the structural model estimation results in this chapter, but only present the modeling framework and key estimation strategy.

Background: Cancer treatment and management require complicated clinical decision making to provide the highest quality of care for an individual patient. This is facilitated in part with ever-increasing availability of medications and treatments but hindered due to barriers such as access to care, cost of medications, clinician knowledge, and patient preferences or clinical factors. Although guidelines for cancer treatment and many symptoms have been developed to inform clinical practice, implementation of these guidelines into practice is often delayed or does not occur. Informatics-based approaches, such as clinical decision support, may be an effective tool to improve guideline implementation by delivering patient-specific and evidence-based knowledge to the clinician at the point of care to allow shared decision making with a patient and their family. The large amount of data in the electronic health record can be utilized to develop, evaluate, and implement automated approaches; however, the quality of the data must first be examined and evaluated. Methods: This dissertation addresses gaps the literature about clinical decision making for cancer care delivery. Specifically, following an introduction and review of the literature for relevant topics to this dissertation, the researcher presents three studies. In Study One, the researcher explores the use of clinical decision support in cancer therapeutic decision making by conducting a systematic review of the literature. In Study Two, the researcher conducts a quantitative study to describe the rate of guideline concordant care provided for prevention of acute chemotherapy-induced nausea and vomiting (CINV) and to identify predictors of receiving guideline concordant care. In Study Three, the researcher conducts a mixed-methods study to evaluate the completeness, concordance, and heterogeneity of clinician documentation of CINV. The final chapter of this dissertation is comprised of key findings of each study, the strengths and limitations, clinical and research implications, and future research. Results: In Study One, the systematic review, the researcher identified ten studies that prospectively studied clinical decision support systems or tools in a cancer setting to guide therapeutic decision making. There was variability in these studies, including study design, outcomes measured, and results. There was a trend toward benefit, both in process and patient-specific outcomes. Importantly, few studies were integrated into the electronic health record. In Study Two, of 180 patients age 26 years or less, 36% received guideline concordant care as defined by pediatric or adult guidelines, as appropriate. Factors associated with receiving guideline concordant care included receiving a cisplatin-based regimen, being treated in adult oncology compared to pediatric oncology, and solid tumor diagnosis. In Study Three, of the 127 patient records reviewed for the documentation of chemotherapy-induced nausea and vomiting, 75% had prescriber assessment documented and 58% had nursing assessment documented. Of those who had documented assessments by both prescriber and nurse, 72% were in agreement of the presence/absence of chemotherapy-induced nausea and vomiting. After mapping the concept through the United Medical Language System and developing a post-coordinated expression to identify chemotherapy-induced nausea and vomiting in the text, 85% of prescriber documentation and 100% of nurse documentation could be correctly categorized as present/absent. Further descriptors of the symptoms, such as severity or temporality, however, were infrequently reported. Conclusion: In summary, this dissertation provides new knowledge about decision making in cancer care delivery. Specifically, in Study One the researcher describes that clinical decision support, one potential implementation strategy to improve guideline concordant care, is understudied or under published but a promising potential intervention. In Study Two, I identified factors that were associated with receipt of guideline concordant care for CINV, and these should be further explored to develop interventions. Finally, in Study Three, I report on the limitations of the data quality of CINV documentation in the electronic health record. Future work should focus on validating these results on a multi-institutional level.

No description available.

No description available.

Heterogeneous treatment responses are commonly observed in patients with mental disorders. Thus, a universal treatment strategy may not be adequate, and tailored treatments adapted to individual characteristics could improve treatment responses. The theme of the dissertation is to develop statistical and machine learning methods to address patients heterogeneity and derive robust and generalizable individualized treatment strategies by integrating evidence from multi-domain data and multiple studies to achieve precision medicine. Unique challenges arising from the research of mental disorders need to be addressed in order to facilitate personalized medical decision-making in clinical practice. This dissertation contains four projects to achieve these goals while addressing the challenges: (i) a statistical method to learn dynamic treatment regimes (DTRs) by synthesizing independent trials over different stages when sequential randomization data is not available; (ii) a statistical method to learn optimal individualized treatment rules (ITRs) for mental disorders by modeling patients' latent mental states using probabilistic generative models; (iii) an integrative learning algorithm to incorporate multi-domain and multi-treatment-phase measures for optimizing individualized treatments; (iv) a statistical machine learning method to optimize ITRs that can benefit subjects in a target population for mental disorders with improved learning efficiency and generalizability. DTRs adaptively prescribe treatments based on patients' intermediate responses and evolving health status over multiple treatment stages. Data from sequential multiple assignment randomization trials (SMARTs) are recommended to be used for learning DTRs. However, due to the re-randomization of the same patients over multiple treatment stages and a prolonged follow-up period, SMARTs are often difficult to implement and costly to manage, and patient adherence is always a concern in practice. To lessen such practical challenges, in the first part of the dissertation, we propose an alternative approach to learn optimal DTRs by synthesizing independent trials over different stages without using data from SMARTs. Specifically, at each stage, data from a single randomized trial along with patients' natural medical history and health status in previous stages are used. We use a backward learning method to estimate optimal treatment decisions at a particular stage, where patients' future optimal outcome increment is estimated using data observed from independent trials with future stages' information. Under some conditions, we show that the proposed method yields consistent estimation of the optimal DTRs, and we obtain the same learning rates as those from SMARTs. We conduct simulation studies to demonstrate the advantage of the proposed method. Finally, we learn DTRs for treating major depressive disorder (MDD) by stage-wise synthesis of two randomized trials. We perform a validation study on independent subjects and show that the synthesized DTRs lead to the greatest MDD symptom reduction compared to alternative methods. The second part of the dissertation focuses on optimizing individualized treatments for mental disorders. Due to disease complexity, substantial diversity in patients' symptomatology within the same diagnostic category is widely observed. Leveraging the measurement model theory in psychiatry and psychology, we learn patient's intrinsic latent mental status from psychological or clinical symptoms under a probabilistic generative model, restricted Boltzmann machine (RBM), through which patients' heterogeneous symptoms are represented using an economic number of latent variables and yet remains flexible. These latent mental states serve as a better characterization of the underlying disorder status than a simple summary score of the symptoms. They also serve as more reliable and representative features to differentiate treatment responses. We then optimize a value function defined by the latent states after treatment by exploiting a transformation of the observed symptoms based on the RBM without modeling the relationship between the latent mental states before and after treatment. The optimal treatment rules are derived using a weighted large margin classifier. We derive the convergence rate of the proposed estimator under the latent models. Simulation studies are conducted to test the performance of the proposed method. Finally, we apply the developed method to real-world studies. We demonstrate the utility and advantage of our method in tailoring treatments for patients with major depression and identify patient subgroups informative for treatment recommendations. In the third part of the dissertation, based on the general framework introduced in the previous part, we propose an integrated learning algorithm that can simultaneously learn patients' underlying mental states and recommend optimal treatments for each individual with improved learning efficiency. It allows incorporation of both the pre- and post-treatment outcomes in learning the invariant latent structure and allows integration of outcome measures from different domains to characterize patients' mental health more comprehensively. A multi-layer neural network is used to allow complex treatment effect heterogeneity. Optimal treatment policy can be inferred for future patients by comparing their potential mental states under different treatments given the observed multi-domain pre-treatment measurements. Experiments on simulated data and real-world clinical trial data show that the learned treatment polices compare favorably to alternative methods on heterogeneous treatment effects and have broad utilities which lead to better patient outcomes on multiple domains. The fourth part of the dissertation aims to infer optimal treatments of mental disorders for a target population considering the potential distribution disparities between the patient data in a study we collect and the target population of interest. To achieve that, we propose a learning approach that connects measurement theory, efficient weighting procedure, and flexible neural network architecture through latent variables. In our method, patients' underlying mental states are represented by a reduced number of latent state variables allowing for incorporating domain knowledge, and the invariant latent structure is preserved for interpretability and validity. Subject-specific weights to balance population differences are constructed using these compact latent variables, which capture the major variations and facilitate the weighting procedure due to the reduced dimensionality. Data from multiple studies can be integrated to learn the latent structure to improve learning efficiency and generalizability. Extensive simulation studies demonstrate consistent superiority of the proposed method and the weighting scheme to alternative methods when applying to the target population. Application of our method to real-world studies is conducted to recommend treatments to patients with major depressive disorder and has shown a broader utility of the ITRs learned from the proposed method in improving the mental states of patients in the target population.

No description available.

Introduction: Forty years ago the life saving and life prolonging therapy of dialysis was rationed. It was extremely unlikely that people aged over 50 years would be offered treatment. Today, those aged over 65 years are becoming the fastest growing group of patients on dialysis. Changing population demographics and referral patterns, the opening up of eligibility for dialysis to high risk individuals, refinement and developments in dialysis technology and its ‘success’ in keeping more patients alive for longer periods, along with rising public expectation, are just some of the reasons behind this change in the age profile of those being currently treated for kidney failure. Older people are likely to have multiple co-morbidities and decreased functional status that may complicate their decision-making about dialysis and limit their treatment options. / Enhancing choice and involvement in treatment decision-making to the patient’s satisfaction is a central theme of health care ethics. Current national and international ethical guidelines about the initiation of dialysis recommend shared or joint decision-making and discuss patient ‘benefit’ and patient ‘need’. This project sought to determine how these recommendations, and other ethical issues related to informed consent, possible withdrawal of treatment and quality of life, were embodied in the personal experiences of a group of older people facing dialysis decisions. / Aim: The general aim of this research was to follow the dialysis decision-making process over time amongst a group of people aged 65 years and older. More specifically, this research sought to explore with the participants the following issues: what factors impacted on their dialysis decision-making; how they understood both what was happening to them and the goals of treatment; their preferences for information seeking; how they perceived any future decision-making; how or whether the commencement and experience of dialysis influenced their decision-making; and once treatment had been initiated, how they felt about their initial decisions. / Method: A predominantly longitudinal qualitative study was undertaken. Meetings were conducted prior to the potential initiation of dialysis with 21 participants. These meetings involved a semi-structured interview and the administration of three questionnaires focusing on preferences for decision-making, information seeking and quality of life. Data was also collected from the participants’ health records. For those participants who commenced dialysis a further two meetings were undertaken one month and then six months after treatment was instigated. The qualitative data was analysed thematically using concepts that had either been pre-determined and explored within the interviews or, had emerged from the participants’ stories. / Findings: Findings from this study include: participants not feeling that they had a choice about dialysis; a mismatch between theoretical expectations of informed consent and shared decision-making and the ‘actor centred experiential’ model of decision-making adopted by participants; a need to re-evaluate the balance and relationships between physiological measures of effectiveness emphasised by health professionals, and psychosocial and functional markers valued by participants; and treatment goals not being individually negotiated. / Conclusion: An interest in remaining alive was the driving force behind why participants chose to have dialysis. Other factors impacting on decisions about dialysis were multi-faceted and were based on priorities other than what health professionals consider important. Shared decision-making, as described in the literature, is not unproblematic. However, health professionals need to accept the underlying premises on which shared decision-making is based so that they can find out what expectations patients have of treatment, beyond that of saving life. Such expectations need to be discussed with patients and the various treatment options need to be negotiated in an attempt to achieve patients’ goals. Patients should be encouraged however to be involved in decision-making to the extent to which they desire.

Recent federal legislation has incentivized hospitals to focus on quality of patient care. A primary metric of care quality is patient readmissions. Many methods exist to statistically identify patients most likely to require hospital readmission. Correct identification of high-risk patients allows hospitals to intelligently utilize limited resources in mitigating hospital readmissions. However, these methods have seen little practical adoption in the clinical setting. This research attempts to identify the many open research questions that have impeded widespread adoption of predictive hospital readmission systems. Current systems often rely on structured data extracted from health records systems. This data can be expensive and time consuming to extract. Unstructured clinical notes are agnostic to the underlying records system and would decouple the predictive analytics system from the underlying records system. However, additional concerns in clinical natural language processing must be addressed before such a system can be implemented. Current systems often perform poorly using standard statistical measures. Misclassification cost of patient readmissions has yet to be addressed and there currently exists a gap between current readmission system evaluation metrics and those most appropriate in the clinical setting. Additionally, data availability for localized model creation has yet to be addressed by the research community. Large research hospitals may have sufficient data to build models, but many others do not. Simply combining data from many hospitals often results in a model which performs worse than using data from a single hospital. Current systems often produce a binary readmission classification. However, patients are often readmitted for differing reasons than index admission. There exists little research into predicting primary cause of readmission. Furthermore, co-occurring evidence discovery of clinical terms with primary diagnosis has seen only simplistic methods applied. This research addresses these concerns to increase adoption of predictive hospital readmission systems. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2017. / FAU Electronic Theses and Dissertations Collection

This dissertation aims to enhance our understanding of the experiences of surrogates (e.g., family, close friends) who make medical decisions for a loved one in the intensive care unit (ICU) after a cardiac arrest. Nearly 500,000 Americans experience a cardiac arrest annually; given high mortality (80%-90%), most surrogates become bereaved. For those who receive post-cardiac arrest care in an ICU, almost three in four surrogates make decisions to limit life-sustaining treatments. The burden of medical decision-making for a loved one has been well-documented and those who serve as surrogate decision-makers in the ICU are known to experience symptoms (e.g., depression, post-traumatic stress) for months after their loved one’s hospitalization. However, it is unknown to what extent decision-making experiences near a loved one’s end-of-life influence symptom burden among bereaved surrogates after cardiac arrest. Decisional conflict, uncertainty about which course of action to take, is reported by half of surrogates faced with ICU treatment decisions and one in five report regret around their decisions after 6 months. Following a cardiac arrest, prognostic uncertainty can complicate surrogate decision-making and potentially worsen decisional conflict and/or regret. The overall objective of this dissertation is to inform future interventions to improve outcomes for this highly vulnerable group. The dissertation study aims were to (1) evaluate the efficacy of interventions for ICU surrogates facing end-of-life decisions, (2) explore differences in surrogate decision-making experiences by level of decisional conflict reported around end-of-life decisions after cardiac arrest, (3) assess physical and psychological symptoms among surrogates during the first 6 months of bereavement after a loved one’s cardiac arrest, and (4) explore relationships between decisional conflict, decision regret, and symptoms. To address these aims, three studies were conducted. Study 1 was a systematic review and meta-analysis to evaluate the efficacy of interventions to improve symptoms among surrogates whose loved one had either died in the ICU or had high predicted likelihood of mortality. The study demonstrated that interventions have yielded only small, significant improvement in depression and post-traumatic stress at 3 months and anxiety at 6 months; findings derived from the meta-analysis have moderate-to-very-low certainty of evidence and have potentially limited clinical utility. Most interventions were delivered in the ICU, suggesting that different approaches (e.g., beyond the ICU) warrant exploration. Studies 2 and 3 report findings from a convergent mixed methods study of bereaved cardiac arrest surrogates. Study design was informed by the Integrative Risk Factor Framework for the Prediction of Bereavement Outcome which includes various inter- and intrapersonal risk factors in addition to bereavement-related stressors that influence outcomes such as symptoms. Surrogates were recruited and enrolled ~1-month after the death of their loved one and were followed through 6 months. Survey data were collected at ~1-, 2-, 3-, and 6-months. Most surrogates also completed interviews which were conducted at ~1-month and 3-months. Study 2 aimed to explore differences in surrogate decision-making experiences by decisional conflict reported around end-of-life decisions in the ICU. Among the 16 surrogates who completed both surveys and interviews at ~1-month, decisional conflict survey scores were relatively low with more than half reporting no decisional conflict. Three themes emerged from interview data, two related to decision-making experiences and one related to broader experiences during the first month after the loved one’s death. Compared to those who reported no decisional conflict, those who did described lack of clarity around their loved one’s preferences for treatment, less support from other family or clinicians, and a poorer understanding of medical treatments or prognosis. All surrogates described challenges navigating life after the loss. Qualitative data provided insight into limitations of retrospective assessment of decisional conflict, highlighted opportunities for enhanced measurement of the construct among surrogate decision-makers, and identified potential areas of focus for future interventions. Study 3 aimed to assess physical and psychological symptoms during the first 6 months of bereavement and explore relationships between decisional conflict, decision regret, and symptoms. Findings demonstrated that more than a third experienced high grief intensity and/or post-traumatic stress 6 months after medical decision-making. Strong correlations were seen between 1-month and 6-month symptoms (i.e., depression, post-traumatic stress, fatigue, sleep disturbance), suggesting that those with high symptom burden early on are likely to have symptoms that persist. Decisional conflict moderately correlated with decision regret at 6 months which moderately correlated with other psychological symptoms (i.e., anxiety, post-traumatic stress, grief intensity). The exploratory findings suggest that early screening may be helpful in identifying surrogates at highest risk for poor outcomes at 6 months and may help target future interventions towards those who need them most. This dissertation makes valuable contributions to our current understanding of the experiences of surrogate medical decision-making near a loved one’s end-of-life in the ICU after cardiac arrest and of surrogate experiences during bereavement. Chapter 5 summarizes each study, reviews key findings, identifies strengths and limitations, and discusses implications for future research, clinical practice, and health policy. Together, these studies support the need for enhanced care for surrogates bereaved after a loved one’s cardiac arrest/critical illness. Surrogates described the burden of medical decision-making near a loved one’s end-of-life in the ICU and the challenges encountered during bereavement. Findings suggest that end-of-life decision-making experiences may influence symptoms through the first 6 months of bereavement. Novel approaches to supporting surrogates are warranted to improve health outcomes for this important, vulnerable group.