Melanie Rosenberg is interested in Big Data. When she started her career with a statistical consulting firm, she discovered that the modeling techniques she used for litigation clients translated easily to health. After whetting her appetite with a research project on diet and obesity, she wanted to pursue her growing interest in chronic disease prevention.
“Statistics is hard in health because of multiple risk factors and small effect sizes,” says Melanie, “but there is a lot of room to develop new methods.” For example, computers can scan great quantities of raw data from multiple sources, such as medical records, genomic sequences, and health surveys, to detect patterns and learn more about the underlying causes of disease. With an abundance of electronic medical data being stockpiled, biostatisticians are racing to develop new tools to interpret it.
This summer Melanie will be interning with a start-up company that is leveraging this data to build an artificial intelligence platform for personalized risk predictions and clinical decisions. She is already working with Assistant Professor Michael Kane on using machine learning to predict diabetes risk from biometric and lifestyle surveys for her Master’s thesis.
In addition to her research and classwork, Melanie has worked as a teaching fellow and programming tutor at the Yale School of Public Health.