Research

Data-driven risk-adjusted models for predicting hospital readmissions.

different types of graphs overlayed on top of each other with numbers over a dark blue background.

This research project aims to develop data-driven models for predicting hospital readmissions by considering the risk factors that contribute to this outcome. The models are designed to analyze nationwide patient datasets and identify key variables that increase the likelihood of readmissions in different groups of patients. The use of risk-adjusted models will enable hospitals to improve patient outcomes by identifying high-risk patients and implementing targeted interventions to reduce readmission rates. By utilizing data-driven approaches, this research helps healthcare providers make informed decisions about patient care and potentially reduce the burden on healthcare systems by preventing unnecessary readmissions.

Health equity in the age of AI: identifying and addressing racial and ethnic disparities in healthcare outcomes.

a person in a white lab coat and stethoscope around their neck reaching their hand out toward you with a small light projecting out medical and technology related graphics

The primary goal of this research is to address racial and ethnic disparities in healthcare outcomes by leveraging the power of artificial intelligence (AI) and data analytics. The project focuses on identifying the root causes of these disparities, including social determinants of health, and developing targeted interventions to improve health equity. By utilizing AI and data analytics, this research aims to identify patterns and trends that may not be immediately visible to human analysts. The ultimate goal is to improve health outcomes for all individuals, regardless of their race or ethnicity, and to ensure that healthcare systems are equitable and accessible to all.

Advancing clinical decision-making through explainable AI-driven risk-adjusted design of electronic health record systems.

three people standing and talking to each other in a hallway wearing lab coats

This research project aims to develop explainable artificial intelligence (AI) models for risk-adjusted design of electronic health record (EHR) systems. By utilizing AI algorithms, the models will identify key risk factors that contribute to patient outcomes and develop personalized treatment plans that can be incorporated into EHR systems. The explainable AI component of the model will enable clinicians to understand the reasoning behind the decisions made by the algorithm and provide insights that can inform clinical decision-making. Ultimately, the goal of this research is to improve patient outcomes by providing clinicians with data-driven insights that can inform treatment decisions and reduce the likelihood of adverse events.