Mining the Bibliome - Translational Informatics: Realizing the Promise of Knowledge-Driven Healthcare - page 71

Chapter 5
Mining the Bibliome

Indra Neil Sarkar

By the End of This Chapter, Readers Should Be Able to

￿ Understand the role of literature in biomedicine (the “bibliome”);

￿ Explore approaches to impute knowledge from the bibliome; and

￿ Demonstrate the potential of bibliome mining for a learning healthcare system

5.1 Data-Driven Knowledge in Biomedicine

Data in biomedicine originate from a plethora of sources that span the continuum of
healthcare. Molecular data may originate from whole genome sequencing, identifi -
cation of gene sequence variants (such as Single Nucleotide Polymorphisms
[SNPs]), or transcriptomic signatures associated with gene expression (such as
microarrays). Health data may originate from electronic systems that gather data
directly from patients (e.g . , using “quantifi ed self” technologies or personal health
records), as part of the health care system (e.g . , through electronic health record
systems or as recorded in health care utilization data sets), or as a result of popula-
tion health initiatives (e.g . , vital records or infectious disease surveillance). To be
deemed useful, biomedical data must be analyzed and interpreted through a system-
atic and repeatable process. The results of these processes, and the foundation on
which future insights are often based, are ensconced in biomedical literature.