Browsing by Subject "Informatics"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Bone marrow diagnostic discordance determination: a foundation for clinical decision support.
    (2010-05) Pitkus, Andrea Renee’
    Bone marrow testing by the hematopathology, flow cytometry and cytogenetics laboratories provides valuable information utilized in the diagnosis, prognosis and treatment of leukemias. Not much is known about unexpected informatics issues which arise during the analysis of bone marrow, which impact information about the patient's hematological status. This status needs to be clearly communicated to the clinician since it impacts clinical decision making and patient care. This research addresses whether bone marrow diagnostic discordance can be utilized as an indicator of issues in the bone marrow information process, providing the foundation for clinical decision support tool development. The study first measures disagreement in the diagnoses reported by the three laboratories, on bone marrow specimens collected at the same time, to determine lexical diagnostic discordance. Semantic diagnostic discordance is determined utilizing the 2001 World Health Organization leukemia classifications. Statistical significance of diagnostic discordance is measured with Cohen's Kappa statistic. The second research phase categorizes factors contributing to the discordances found in the first phase to further understand the etiology of the discordances. It is important to distinguish discordances due to expected testing process limitations from unexpected discordances due to other etiologies. It is also vital to denote which are clinically significant and likely to impact patient care. These factors are critical in designing an effective decision support tool which alerts the clinician appropriately. Results of the first research phase show lexical and semantic discordance can be measured successfully from three laboratories reporting on bone marrows. Cohen's Kappa statistic also provides an automatic means of detection and measurement of semantic discordance. Categorization of discordances distinguishes which discordances are due to limitations in laboratory testing. Categorization also indicates where in the testing process interventions such as a decision support tool are optimally placed in alerting pathologists of problems in the information process needing further assessment.
  • Thumbnail Image
    Item
    Discovering Hidden Patterns in Anesthesia Data Associated with Unanticipated Intensive Care Unit Admissions
    (2017-04) Peterson, Jessica
    Unanticipated intensive care unit admissions (UIA) are a metric of quality anesthesia care since they have been associated with intraoperative incidents and nearly four times as likely to die within 30 days of surgery compared to patients that were not admitted to the intensive care unit unexpectedly. Patient age, American Society of Anesthesiology Classification, type of procedure, tachycardia, hypotension, and cardiovascular and neuromuscular blocking drugs administered in the operating room have all been associated with patient UIA. Intraoperative anesthesia data is generated in real-time and can be used to identify patterns in patient care associated with UIA. Knowledge about patterns in intraoperative medication administration and hemodynamic data is important to develop interventions that can be used to prevent intraoperative deterioration. Patterns were defined as two or more characteristics in the line graphs. This data visualization study discovered, labeled, and tested patterns in intraoperative hemodynamic management for association with patient UIA. Data from 68 adult, inpatient, elective surgical patients were matched to 34 patients with UIA in the University of Minnesota, Academic Health Center, Clinical Data Repository. A prototype line graph was evaluated to identify salient (obvious) patterns in intraoperative hemodynamic management for the data set. Line graphs for patients with and without UIA were created and visualized. Patterns in intraoperative hemodynamic management were discovered using data visualization with line graphs and operationally defined. Odds ratios were used to test categorical patterns and one-way analysis of variance was used to test continuous numeric patterns for association with patient UIA. Seven patterns were significantly associated with patient UIA (p < .05).
  • Thumbnail Image
    Item
    Exploration of the Clinical Utility of High Risk Medication Regimens
    (2014-11) Olson, Catherine
    Title: Exploration of the Clinical Utility of High Risk Medication Regimens Background: Unnecessary hospital readmissions are a costly problem for the U.S. health care system. An automated algorithm was developed to target this problem and proven to predict elderly patients at greater risk of re-hospitalization based on their medication regimens. Objective: Create an automated algorithm for predicting elderly patients' medication-related risks for re-hospitalization (study 1), optimize the algorithm by improving the sensitivity of its medication criteria (study 2), and determine its usefulness within different patient populations (study 3). Materials and methods: Outcome and Assessment Information Set (OASIS) and medication data were reused from a previous, manual study of 911 patients from 15 Medicare-certified home health care agencies. Medication data was converted to standardized drug codes using APIs managed by the National Library of Medicine (NLM), and then integrated in an automated algorithm that calculations patients' high risk medication regime scores (HRMRs). A comparison of results between the automated and manual processes was conducted to determine HRMR score match rates (study 1). Odds Ratio analyses, literature reviews and clinical judgments were used to adjust the scoring of patients' High Risk Medication Regimens (HRMRs). Receiver Operating Characteristic (ROC) analysis evaluated whether these adjustments improved the predictive strength of the algorithm (study 2). Unsupervised clustering was used to determine patient population subgroups. HRMR scores were then applied to these subgroups, and ROC & FDR analysis evaluated whether the predictive strength of the algorithm increased for a specific patient population subgroup (study 3). Results: HRMR scores are composed of polypharmacy (number of drugs), potentially inappropriate medications (PIM) (drugs risky to the elderly), and Medication Regimen Complexity Index (MRCI) (complex dose forms, instructions or administration). The automated algorithm produced polypharmacy, PIM and MRCI scores that matched with 99, 87, 99 percent of the scores, respectively, from the manual analysis (study 1). Strongest ROC results for the HRMR components were .68 for polypharmacy when excluding supplements; and .60 for PIM and .69 for MRCI using the original HRMR criteria (study 2). Subgroups consisting of males who have adult children as primary caregivers show stronger AUC curves than the entire population. (study 3). Conclusion: The automated algorithm can predict elderly patients at risk of hospital readmissions and is improved by a modification to its polypharmacy criteria. A hypothesis for future study includes that the algorithm is more predictive in the subgroup of males who have adult children as their caregiver.
  • Thumbnail Image
    Item
    Personalized surgical risk assessment using population-based data analysis
    (2013-02) AbuSalah, Ahmad Mohammad
    The volume of information generated by healthcare providers is growing at a relatively high speed. This tremendous growth has created a gap between knowledge and clinical practice that experts say could be narrowed with the proper use of healthcare data to guide clinical decisions and tools that support rapid information availability at the clinical setting. In this thesis, we utilized population surgical procedure data from the Nationwide Inpatient Sample database, a nationally representative surgical outcome database, to answer the question of how can we use population data to guide the personalized surgical risk assessment process. Specifically, we provided a risk model development approach to construct a model-driven clinical decision support system utilizing outcome predictive modeling techniques and applied the approach on a spinal fusion surgery which was selected as a use case. We have also created The Procedure Outcome Evaluation Tool (POET); which is a data-driven system that provides clinicians with a method to access NIS population data and submit ad hoc multi-attribute queries to generate average and personalized data-driven surgical risks. Both systems use patient demographics and comorbidities, hospital characteristics, and admission information data elements provided by NIS data to inform clinicians about inpatient mortality, length of stay, and discharge disposition status.
  • Thumbnail Image
    Item
    Picturing Patterns in Whole-Person Health: Leveraging Visualization Techniques with Structured Consumer-Generated mHealth Data
    (2018-12) Austin, Robin
    Cardiovascular disease (CVD) is a leading cause of death in women. In cardiac care-management, women have experienced being seen “as the disease” rather than as a whole person. Current methods are lacking to better understand a whole person perspective to include strengths, challenges, and needs. Health information technology (HIT) holds promise for capturing data that represents the whole-person perspective. A literature review identified that women with cardiovascular disease have strengths and would like their strengths used as part of managing care. A consumer-facing application, MyStrengths+MyHealth app, was developed to enable self-report of strengths, challenges, and needs using a consumer-facing version of the Omaha System, a multi-disciplinary standardized health terminology. The Omaha System problem concept, Circulation, was used as a surrogate for women with cardiovascular disease. Participants (N=604) used the MSMH app at Midwestern state fair and women with Circulation signs/symptoms (n=80) were matched to an equal number of women without Circulation signs/symptoms. Data generated by participants were analyzed using descriptive statistics and data visualizations techniques to evaluate and compare standardized strengths, challenges, and needs for women with Circulation signs/symptoms. This study revealed women with Circulation signs/symptoms had more strengths, challenges, and needs compared to women without Circulation signs/symptoms. Data visualizations techniques detected differing patterns in the data for women with and without Circulation signs/ symptoms. Future research is needed to validate these findings and extend this research to other populations and programs. This research creates a foundation for what is possible using data visualizations to enhance understanding of consumer-generated health data.
  • Thumbnail Image
    Item
    Towards A Model Representation Of Residence, Living Conditions, And Living Situation: An Evaluation Of Clinical Practice In Documentation, And Associated Standards And Informational Models
    (2017-03) Winden, Tamara
    Social determinants of health (SDOH) play an important role in diagnosis, prevention, health outcomes, and quality of life and have long been a consideration in the provision of care. SDOH can cause illness, exacerbate chronic illness, but can also improve health. The SDOH target domains of interest for this proposal are Residence, Living Situation, and Living Conditions. Historically, these three topic areas are either not well documented in the EHR or, if they are documented, they are in unstructured or semi-structured text making the information inaccessible to clinical decision support tools or secondary use in research. Building upon previous work, the overall goal of this three-part study is to enhance current information models of these three domains through the evaluation of content and completeness of existing standards and terminologies and examine how coherent our documentation is of these target domains is in the electronic health record through analysis of specific ancillary notes as well as other structured and unstructured sections of the EHR. Examination of 27 standards and terminology sources contributed to an enhanced model representation for Residence, Living Situation, and Living Conditions. However, our findings show there are no fully comprehensive standards for EHR documentation of these topic areas. An analysis of unstructured text from the EHR demonstrated that SDOH are being documented in notes and these data contributed to further enhanced model. Lastly, an examination of flowsheet data showed many inconsistencies in flowsheet build and documentation, many of which could be solved if we have a comprehensive standard for documentation of SDOH.