I have ample experience contributing to the health technology space, and I am passionate about utilizing data analytics tools to help provide key insights.
I have proficient knowledge of statistical hypothesis testing, including how to calculate probability, how to compare hypotheses, and how to identify the power of an experiment.
In my most recent technical position as Principal Trainer at the San Francisco Department of Public Health, I successfully led the implementation of Epic’s Home Health Clinical application. I oversaw the technical training of 50 clinicians in 6 different specialties. With each training milestone, I provided key insights to the various ancillary teams in order to maintain the implementation’s progression, concluding in clinician readiness to utilize the new electronic health records.
Previously, as a Performance Analyst at Augmedix, I provided in-depth qualitative and quantitative feedback on remote scribe performance to various stakeholders. I took the initiative to improve quality tracking assessments in order to add robustness to KPIs. In this pursuit, I created Python scripts that standardized the grading metrics across auditors and auto-generated visualizations, which quickly assessed the Performance team’s strategic hypotheses and could lead to informed workflow changes.
My most significant contribution as Ergonomics Analyst at UCSF Medical Center was spearheading a project that automated preventive and work-related injury evaluation requests from an employee population of over 6,000. I designed software enabling our team to expeditiously triage over 100 evaluation requests per week, significantly reducing work-related injuries in the short term and laying the foundation for an increase in long-term productivity.
I also increased communication across the medical center campuses by collaborating with vendors, ergonomists, and administrators in order to create and implement a new equipment- purchasing protocol that would significantly decrease the time gap in which an employee could sustain post-evaluation work-related injuries. I extensively analyzed usage reports and constructed preventive formularies to accomplish this.
I once analyzed the data that was presented during a famous court case in which it was alleged that the UC Berkeley graduate school admissions process discriminated by gender, favoring men over women. By evaluating the data as a whole, it did appear that gender discrimination played a role, but this trend was actually reversed when an analysis was conducted on a more granular level, in this case, looking at the rates of admission across genders for each graduate department. At this level, women were more often admitted to a graduate department than men. This is an example of the Simpson’s Paradox, in which a trend seen in different groups of data either reverses or disappears in the combined data.