Browsing by Subject "type 2 diabetes"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Understanding Diabetes Self-Management Behaviors among American Indian Adults
    (2016-08) Aronson, Benjamin
    Background: American Indians (AI) experience disparate prevalence, complications, and rates of death from diabetes compared to the general population. Diabetes self-management behaviors (DSMB) including healthy eating, physical activity, and medication adherence can improve glycemic control and prevent long-term complications. Prior studies, generally in non-AI populations, have suggested that distress negatively and resources positively impact DSMB participation, but have often studied influential determinants in isolation. In addition, the influence of contextual social-ecological determinants on personal determinants has been neglected. Aim: This work describes the frequency of DSMB and tested a proposed model, based upon Andersen’s Behavioral Model, to understand the relationships between appraisal of community distress and resources, personal distress and resources, and DSMB among a clinic sample of AI adults with type 2 diabetes. Method: A cross-sectional computer assisted personal interview survey was administered to a random sample of 194 AI adults with a recent diagnosis of type 2 diabetes using care at Indian Health Service facilities in one of five upper Midwest reservation communities. Survey items included measures of healthy eating, physical activity, medication adherence, personal distress, personal resources, appraisal of community distress, appraisal of community resources, and demographic variables. Relying on Andersen’s Behavioral Model as the conceptual framework, one model for each DSMB was tested using structural equation modeling. Results: The mean days per week of healthy eating and physical activity reported by participants were 2.93 and 2.95, respectively. Based upon the 4-item Morisky Medication Adherence scores 27.5% of the participants using medications met criteria for high and 20.5% for low adherence. The structural equation models for healthy eating and medication adherence displayed good fit and accounted for 60.4% and 29.6% of the variance in the DSMB, respectively. The model for physical activity did not fit the data and explained only 17% of the variance in physical activity. Personal resources and personal distress had strong direct relationships with healthy eating, while both gender and income had significant indirect relationships. Personal distress had a direct negative relationship with medication adherence, and both gender and education had indirect effects in this model. Indirect effects in each model were primarily due to paths through personal distress and personal resources. No significant direct or indirect paths were observed for appraisal of community distress or appraisal of community resources. Conclusion: Rates of healthy eating and medication adherence found in this study are somewhat lower than previous estimates in other Native and non-Native samples. The proposed models fit well for healthy eating and medication adherence, but not for physical activity. For individuals from these communities, physical activity behaviors are not explained by this model and may be induced by other mechanisms. Given the strength of the relationships in the models, personal distress and personal resources may influence DSMB. In addition, several demographic variables may exert indirect influence upon DSMB: female gender through a strong positive relationship with personal distress, and income and education through a strong positive relationship with personal resources. The failure of appraised community determinants in the model may indicate the use of poor measured indicators of the latent constructs. Implications: Facilitating and building personal resources and mitigating personal distress are potentially important clinical targets to improve healthy eating and medication adherence. Although appraised community level factors did not have relationships with DSMB, education and income had positive indirect effects. The community and contextual environment influence these demographic factors, thus future research may explore the possible distal relationship here. The findings also suggest that diabetes distress may act as a mediator between gender and DSMB.
  • Thumbnail Image
    Item
    The Use of Artificial Intelligence for Precision Medicine in the Metabolic Syndrome
    (2019-02) Kim, Era
    Type 2 Diabetes Mellitus (T2DM) is a chronic, progressive metabolic disorder, associated with an increased risk of developing micro- and macrovascular complications. Because of its interactive and heterogeneous nature, the management of T2DM is very complex. For the successful management of T2DM, the use of individualized and evidence-based clinical guidelines is necessary. Randomized controlled trials (RCTs) are considered the gold standard for clinical research. However, the results from RCTs can be inconclusive, leaving many aspects of T2DM management unaddressed. Therefore, there exists a huge gap between the optimal individualized and the current patient care. To fill some of the gap, there are opportunities of artificial intelligence (AI) in medicine, because big data and advanced machine learning (ML) techniques offer a new way to generate evidence that enhances clinical practice guidelines with more personalized recommendations. My overarching goal is to build clinically useful and transferable machine learning models on big data that can influence individual T2DM patient care towards the implementation of precision medicine. Under this goal, I had three specific aims, which I successfully achieved. • Specific aim 1: To develop a semi-supervised divisive hierarchical clustering algorithm for a subpopulation-based T2DM risk score. • Specific aim 2: To develop a Multi-Task Learning (MTL)-based methodology to reveal outcome-specific effects by separating the overall deterioration of metabolic health from progression to individual complications. • Specific aim 3: To demonstrate that even a complex ML model built on nationally representative data can be transferred to two local health systems without significant loss of predictive performance. In the management of T2DM, which is complex, the availability of reliable clinical evidence is critical for clinicians to make the right decision and produce high-quality care in healthcare delivery. Against the backdrop of RCTs, AI in medicine can reduce the gap between optimal individualized and current T2DM patient care. And building clinically useful and transferable ML models will especially facilitate the implementation of precision medicine in T2DM.