research Projects

 

accelerated digitization and patient portal use

The Impact of Accelerated Digitization on Patient Portal Use by Underprivileged Racial Minority Groups During COVID-19: Longitudinal Study

J Med Internet Res 2023;25:e44981

URL: https://www.jmir.org/2023/1/e44981 

DOI: 10.2196/44981 

 

Predictive modeling using social health data

Diabetes affects 37.3 million Americans, accounts for an estimated $24.6B in wasteful and avoidable spending, and its incidence is growing. The disease is a key cause of many comorbidities such as end-stage renal disease and complications such as neuropathy. Exposure to health-impeding social care, or the social and behavioral health, contributes to poor diabetes outcomes. Our goal is to develop a predictive model that identifies patients with type 2 diabetes at risk of developing complications.  

 

Geocoding

Capturing built environment factors associated with patients is a powerful approach to gaining additional insights about obstacles that may prevent individuals from living a more fulfilling and healthy lives. Easy access to groceries (vs eateries), health centers, pharmacies, or public transportation are examples that geocoding can help further explain the quality of health care and outcomes. 

 

Inertia_DM.pdf

therapeutic inertia

Therapeutic inertia, a failure to intensify or commence therapy in a timely manner, is a key impediment to effective type 2 diabetes management. It raises the chance of complications developing or progressing, and prior literature warns that it harms a significant proportion of patients. We empirically examine whether a patient portal reduces therapeutic inertia among type 2 diabetes patients. We find strong evidence from a rich and granular panel dataset that contains 85,001 unique type 2 diabetes patients spanning from 2012 to 2021 covering the roll-out of a patient portal in a large medical center in the U.S. We further find in mechanism analysis that this effect is fueled in part by information access, multi-functional assistance, the transfer of healthcare ownership to patients, and provider’s effective decision-making process. Findings emanating from this study can help public health officials and care providers design policies and strategies that make the most of the patient portal’s potential benefits for effective chronic disease management.

 

T2DM Clinical Decision Support System_ Comprehensive Patient Care.pdf
dia.2023.2525.abstracts.pdf

clinical decision support system

Achieving adequate glycemic control reduces costs, morbidity, and mortality. Control can be achieved by using the American Diabetes Association standards to guide care. However, these guidelines fail to consider real-world evidence (RWE), social determinants of health, and patient preferences regarding treatment decisions and barriers to adherence. A major obstacle to obtaining control is a lack of personalized treatment strategies aimed at improving medication adherence. Current clinical decision support systems that have been tested for managing diabetes have failed to show meaningful improvements in glycemic control because they lack RWE incorporation and integration of large complex and unstructured data sets. 

Grants: (1) UC Office of Research Major Proposal Support Program; (2) UC Office of Research Collaborative Research Advancement Program: Pilot Grant ($25k)

AMCIS 2022 Proceedings

ATTD: p. A67-68