University of Texas at Austin
1 active project
Scientific Questions Being Studied
We are currently exploring the data at this stage to formalize a specific research question. We want to know whether the unstructured data can be processed using natural language processing (NLP) methods to extract meaningful insights regarding disease prevention, diagnosis, and/or treatment. These NLP algorithms require training on large datasets that have adequate representation for each category/combination of conditions. Therefore, we would like to explore the available data to determine whether such a study would be possible using this data.
- Disease Focused Research (pulmonary hypertension)
- Population Health
- Methods Development
The research approach and methods will depend on the availability and quality of the data that we will get access to. In general, we are considering retraining of a pretrained NLP model followed by several statistical analysis techniques to extract the required information out of the electronic health records.
If the data include adequate representation of various conditions and categories of patients, we anticipate that the study could lead to development of a practical tool that would assist healthcare providers and insurance companies in improving their existing processes regarding prevention, diagnosis, and/or treatment of certain diseases. This tool would be of more significant use in online and virtual healthcare systems, where patient input could be used to prioritize certain follow-up questions and guidance towards pertinent healthcare provider and/or streamline insurance claims processes.
Demographic Categories of Interest
This study will not center on underrepresented populations.
- Andrew Drach - Other, University of Texas at Austin
You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.