College of Health Professions
Permanent URI for this collectionhttps://hdl.handle.net/10877/17051
Browse
Browsing College of Health Professions by Type "Poster"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item A Unique Way of Delivering Aerosolized medications to Adults: A Translational Research with High Flow Nasal Cannula(2019-02) Ari, Arzu; Alcoforado, Luciana; Dornelas, ArmeleHigh flow nasal cannula (HFNC) has been developed to promote oxygenation and positive airway pressure in critically ill patients with respiratory failure. Although HFNC was not designed for aerosol drug delivery, we developed a unique way of delivering aerosolized medications to adults using a mesh nebulizer with HFNC.Item Comparison of Ankle Strategies for Balance in Persons After Mild Head Injury(1/2/2010) Gobert, Denise V.; Liao, Ursula; Grattan, Shannon; Marie, Martha N.Objective: The purpose of this project was to characterize and compare balance in persons after MHI using an assessment of ankle strategies. Design: This project used an observational cohort study design. Methodology: Thirty male and female participants aged 18 - 40 years of age provided written consent according to university guidelines and were grouped as being with or without a history of MHI over the past 12 months. Computerized protocols of the NeuroCom EquiTest® system included assessments of static and dynamic standing balance during six sensory conditions in the Sensory Organization Test (SOT) and during translational perturbations of the Motor Control Test (MCT). In addition to standard balance scores, a new method proposed by Zhiming et al. (2004) called the “Postural Stability Index” (PSI) was used to process platform data to document ankle stiffness. Data Analysis: Data analysis included standardized Student T-Test statistics (SPSS v.16) at an alpha level of 0.05. Also, a Pearson’s Correlation Coefficient was calculated to identify significant relationships within the data pool. Preliminary Results: Preliminary findings indicate no significant differences according to standard SOT or MCT scores. Results indicate significant differences in ankle stiffness or PSI scores which have been shown to be highly correlated to decreased balance skills in other patient populations. Clinical Relevance: Preliminary results indicate that assessment of ankle strategies used during challenged balance may be a more sensitive indicator of balance skills in patients after MHI. Final results will be presented along with a discussion of possible clinical use in rehabilitation programs.Item Machine Learning Approaches for Identification of Alzheimer's Disease using Social Determinants and Imagery(2018-02) Fulton, Lawrence V.Purpose: The purpose of this study is to predict the presence of Alzheimer's Disease (AD) using socio-demographic, clinical, and Magnetic Resonance Imaging (MRI) 4D data. Significance: Early detection of AD enables family planning and may reduce costs by delaying long-term care (Alzheimer's Association, 2018). Accurate, non-imagery methods also reduce patient costs. Methods: Extreme Gradient Boosted random forests (XGBoost) predict Clinical Dementia Rating (CDR) presence and severity as a function of gender, age, education, socioeconomic status (SES), and Mini-Mental Status Exam (MMSE). Convulutional Neural Networks (CNN) predict CDR from MRI's transformed to Eigenbrain imagery. XGBoost also predicts CDR with additional clinical variables. Results: XGBoost provides 93% prediction accuracy for CDR using socio-demographic and clinical non-imagery variables-92% accuracy when clinical measures are excluded. CNN using the transformed Eigenbrain imagery results in 93% prediction accuracy. Conclusion: ML methods predict AD with high accuracy. Non-imagery analysis may be nearly as efficacious as imagery prediction at a fraction of the cost.