This repository is under review for potential modification in compliance with Administration directives.
Dr. Jiang explored how a groundbreaking discovery was utilized to generate 30 metadata-based features through machine learning for the automatic detection of PHI fields in structured Electronic Health Record (EHR) data.
Dr. Salimi offered insights for data management, machine learning, and responsible data science, emphasizing the significance of handling selection bias in algorithmic decision-making.
This term reflects the paper's emphasis on using high-throughput machine learning models to precisely detect sensitive data, specifically Protected Health Information (PHI), in electronic health records.
In today's digital age, algorithmic decision-making systems play a crucial role in fields like credit scoring and medical diagnoses. While they are often praised for being 'objective,' these systems can exhibit biases, mostly stemming from the data they rely on.
Dr. Malin drew upon examples from large-scale data-driven projects like the EMR and bio-repository at Vanderbilt University Medical Center, the eMERGE consortium of the NIH, and the All of Us Research Program, aiming to create a comprehensive database of EMRs, genome sequences, and mHealth records from one million Americans.
“Dignitary privacy is based on a belief that privacy is intrinsically valuable, whereas resource privacy is based on a belief that privacy is simply a tool that has instrumental value.”
Hughes, RL David.
Dr Mathews provided an overview of the recent NASEM consensus study report that focused on the use of race and ethnicity and other population descriptors in genomics research, including the recommendations made by the committee.
In a recent article in the Stanford Social Innovation Review, a group of authors “define a social license as the process of building trust and legitimacy from ongoing (i.e., constantly renewed) community or stakeholder engagement and acceptance of how data is being accessed and reused.”
American Indians experience elevated rates of health conditions like diabetes, chronic kidney disease, and cardiovascular disease, as well as greater exposure to environmental hazards.
The term data subject refers to an individual whose data are used in data science research using de-identified, public datasets.