In Silico Hypothesis Discovery - Translational Informatics: Realizing the Promise of Knowledge-Driven Healthcare - page 141

￿ Novel evidence and/or policy frameworks can be inferred based upon

previously undiscovered patterns or motifs in historical data sets , thus allow-
ing such knowledge or decision making to be informed by the best possible
information.

8.5.2 Providers and Healthcare Organizations

￿ Providers are able to engage in the delivery of evidence-based and precision

medicine informed by a full spectrum of scientifi c knowledge that has been
formulated by identifying and testing large numbers of hypotheses against all
available data types and resources

￿ Healthcare organizations can leverage their investments in EHR technolo-

gies and bio-molecular instrumentation so as to rapidly learn from all patient-
centered data being created during the course of normal clinical operations; that
is, achieving the vision of a “learning healthcare system” wherein every patient
encounter is an opportunity to both create new knowledge and improve care for
that patient, their family, and their community.

8.5.3 Patients and Their Communities

￿ Patients are able to be part of the “learning healthcare system” such that they

both become an integral component of research processes and benefi t from the
knowledge generated therein

￿ Interested community members can begin to identify novel or interesting

associations between disparate data that spans healthcare providers and the
world-at-large , thus becoming part of the research enterprise. For example,
community members could use in silico hypothesis discovery tools to identify
relationships between healthcare outcomes and socio-demographic factors that
could inform advocacy and/or community development activities intended to
promote wellness.

8.6 Conclusions

As has been discussed in a variety of ways throughout this topic, the ongoing
growth and increasing complexity of biomedical data presents a wealth of chal-
lenges and opportunities relative to informing a Translational Informatics vision
for knowledge-drive healthcare. In this chapter, we have discussed a specifi c aspect
of those challenges and opportunities, concerned with the disconnect between the
volume of data being generated in numerous settings and the current state-of-the-art