I currently serve as an Internal Medicine and Pediatric Hospitalist at Baylor Scott and White Health. Additionally, my research involves analyzing viral genome data and forecasting infectious disease outbreaks. I also have a longstanding personal interest in the intersection of infectious diseases, public health, and society. Lately, my primary focus has been on leveraging machine learning techniques to forecast outbreaks of the Influenza and Dengue viruses. For Influenza, I collaborate with a team from Northeastern University and Harvard School of Public Health on the CDC’s Flusight project. In terms of Dengue, I employ statistical and ensemble methods to predict Dengue cases across more than 170 cities or regions in various tropical countries.
In the past, I was affiliated with Harvard Medical Faculty Physicians at Beth Israel Deaconess Medical Center and served as an Instructor at Harvard Medical School. I was also a clinical fellow in a joint program for adult and pediatric Infectious Diseases, shared between Boston Children’s Hospital and Beth Israel Deaconess Medical Center. I departed from the program earlier than anticipated for personal reasons, but I hold both programs in high regard and would strongly recommend them to anyone looking to specialize in adult or pediatric infectious diseases. My residency was completed in a combined program for Internal Medicine and Pediatrics at Ohio State University and Nationwide Children’s Hospital. During my graduate and postdoctoral studies, I delved into understanding and predicting the evolution of viruses including Influenza, Ebola, HIV, and Machupo virus, protein molecular evolution, and protein structural biology.
My interests span a wide range of fields, including data science, inpatient medicine, infectious diseases, evolution, epidemiology, and health informatics. I relish the challenge of applying mathematical modeling and statistical learning to a variety of problems.
Furthermore, I have a passion for learning and teaching both biostatistics and data science. I am intrigued by opportunities where existing data or methods can clarify ambiguous clinical reasoning. My interests also extend to data visualization, experimenting with innovative presentation tools, and creating web applications that render information more accessible to those without expert knowledge. I have helped to build statistical or machine learning models to investigate several disparate projects including using CBC data to report the probability of leukemia and understanding whether procalcitonin as a biomarker can discriminate infection probability.
While I once worked as an experimental biologist, my current endeavors are strictly in the realm of computational and data analytics. I kindly request no advertisements related to antibody production.
To learn more about the projects I’ve contributed to, please visit my research page. For educational slide decks and web applications I’ve developed, refer to my extras page. Additionally, you can explore other projects in my GitHub repository, even if they aren’t directly linked on this site.
Follow me on twitter @austingmeyer.