Advances in technology have enabled us to generate massive, rich health data in research and as part of healthcare delivery. Data from electronic health records (EHR), -omics, imaging and mobile health (mHealth), among other areas, promise to greatly advance precision health and to transform our learning health system. Yet they are also highly complex and present significant analytical challenges.
Cancer data science is broadly defined as transdisciplinary; biostatistics, bioinformatics, biomathematics, computational biology, computational science and other relevant quantitative science pursuits play important roles. The field focuses, in particular, on the development and application of algorithms, methods and theory for the analysis of rich, complex health data (e.g. registry, claims, EHRs, -omics, imaging, mHealth, and clinical trials data) that continue to proliferate in cancer research and cancer care.
The Center for Cancer Data Science seeks to accelerate innovation by harnessing the full power of rich, complex health data, and exerting sustained, powerful impact on cancer research, prevention and care through a transdisciplinary, team-science approach.