Camille Krieger
Undergraduate Student, Brigham Young University
1 active project
Cancer Misdiagnosis in EHR
Scientific Questions Being Studied
We hope to repurpose variant detection algorithms from genomics to characterize and quantify the impact of cancer misdiagnosis in electronic health records from the All of Us Research Program. Through these algorithms, we hope to compile a phenotype for cancer through electronic health records that can identify cancer diagnoses earlier. This project has enormous potential for clinical applications such as clinical trials, hospital and patient surveillance, improving cancer survival rates, and finding precise clinical precursors to cancer without using black-box algorithms.
Project Purpose(s)
- Disease Focused Research (cancer)
Scientific Approaches
We aim to merge genomic alignment algorithms with electronic health records (EHR) to predict cancer misdiagnosis in the All of Us Research Program. We will identify optimal similarity metrics to compare patients’ insurance billing codes, prescriptions, timing, and other clinical and demographic data. We will use post-cancer diagnosis events, i.e., billing codes, drugs, and lab tests, to improve and evaluate our similarity algorithms. We plan to include data from all participants in the All of Us datasets that have electronic health records relating to cancer.
Anticipated Findings
We anticipate that insertion-like and deletion-like events are tractable within electronic health records. Furthermore, we anticipate these events will vary drastically between genetic ancestry and socioeconomic demographics. These findings would provide the research community with fresh ideas on how to assess patient similarity using electronic health records and how these similarities and differences vary across many demographics found in the United States. In addition to this, we anticipate that the resulting algorithms could be expanded to predict misdiagnosis phenotypes in other diseases.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Controlled TierResearch Team
Owner:
- Camille Krieger - Undergraduate Student, Brigham Young University
Collaborators:
- Ethan Bang - Undergraduate Student, Brigham Young University
- Matthew Bailey - Early Career Tenure-track Researcher, Brigham Young University
- Brian Kim - Undergraduate Student, Brigham Young University
Request a Review of this Research Project
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.
