Population Informatics: Applying Data Science to Advance the Health and Welfare of Populations
Thursday, January 15, 2015: 8:00 AM-12:00 PM
Balconies K, Fourth Floor (New Orleans Marriott)
Hye-Chung Kum, PhD, MSW, MS, Texas A&M Health Science Center
Data science is the systematic study of digital data using scientific techniques of observation, theory development, systematic analysis, hypothesis testing, and rigorous validation. Data scientists are those that can apply data science to continuously changing deluge of digital raw data that are often inconsistent and erroneous to extract and deliver actionable knowledge in a timely manner. The ability to convert existing raw data (e.g., administrative data, EHR, claims data) into timely information that is useful, applicable, and ultimately transformational requires specialized interdisciplinary data science teams with individuals who are cross-trained in the domain science (i.e. social work, health sciences), computer science, and statistics. The three types of data scientists are (1) domain knowledgeable computer scientists with strong expertise in programming and data mining, (2) data capable domain scientists with strong expertise in the problem domain and statistical modeling methods used in the domain, and (3) data savvy decision makers with expertise in the domain, in particular to applying the knowledge based on data and statistics to real decisions.