Download Big Data for Breast Cancer: A Patient/Advocate

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

World Values Survey wikipedia , lookup

Transcript
Big Data for Breast Cancer: A
Patient/Advocate Perspective
Jane Perlmutter
October 8, 2015
,
1989
Topics
• What is Big Data & why is it
important?
• What are some issues &
concerns to
patients/advocates?
• What can we learn about
these issues from examples
of Big Data projects?
• How can we make a
difference?
What is Big Data?
The Three Vs of Big Data
JP View of What Big Data Is (and Isn’t)
Types of
Data/Examples
Quantity/ Quality Inference Method
of Data
Interventional—
Small / Excellent
Randomized Clinical
Trials
Observational—
Medium / Fair
Registries, Surveys
Unstructured—
Large/Challenging
Social Media, research
articles
Analysis of Variance
Big Data—Combining Large / Poor
Multiple Types & Data
Sources
Multi-dimensional
Analyics and
Visualization Tools
Regression
Artificial
Intelligence, Natural
Language Processing
Types of Health Data
Patient Records
• Patient Charts
• Electronic health
records (EHRs)
Billing/Payment History
Patient Provided Input
• Patient reported
outcomes
• Passively collected
patient data
• Social media
Clinical Trials Data
‘omics Data
• Mutations
• Copy number alterations
• INDELs/SNPs
• RNA/protein expression
• Epigenetics
• Metabiome
• ...
Why Big Data?
JP View of Why Big Data
Promise
• Better predictions about
heath risks
• Faster development of
treatments
• More rapid progress toward
precision medicine
• More efficient use of health
resources
Risk
• Immature methodology
 erroneous inferences
• Breach of security
 loss of privacy
• Hoarding of data
 slowing progress
Patient/Advocate Issues
• Patient/Advocate issues are not unique
to them
• Sponsors & Investigators share these
concerns, though they sometime take a
backseat to technical & scientific issues
• Patients/advocates have a different filter,
are more focused on these issues, and
can bring them to the forefront
Patient/Advocate Issues
• Research Priorities
• Data Quality &
Representativeness
• Data Control & Sharing
• Who Pays & How is it
Sustained
• Security & Privacy
• Informed Consent &
Returning Results
OHRP’s NPRM
• OHRP--Office of Human
Research Protection
• Common Rule--Rule of
ethics regarding biomedical
and behavioral research
involving human subjects in
the US
• NPRM--Notice of Public
Rule Making (9/8/15)
Announced New Requirements
• Written consent is required for all research use of
biospecimens, even those that have been stripped of
identifiers
• Must specify that biospecimens might be used for commercial
profit, but not patient profit
• Must specify whether and how relevant research results
(individual and/or aggregate) will be disclosed to patients
• Some exempt and all non-exempt research must provide
privacy safeguards for biospecimens and identifiable private
information.
– Surveys, interviews, educational tests, etc.
– Secondary research
• Defines data security protections that are required and that
they must be described in consent documents
Cancer Big Data Examples and
Some Issues They Raise
• ‘Omics: Visualization, analysis and
download of large-scale cancer
genomics data sets for research
• Learning Systems: Real world data
for quality improvement and
research
• Clinical Trials: Data sharing from
clinical trials for research
Other Interesting Health Examples
• Surveillance: Multi-source data to
monitor unidentified toxicities and
drug interactions
• Infrastructure: For comparative
effectiveness research and other
patient-centered health research
• Patient Entered Data: Patient
support and information sharing
• Artificial Intelligence Processing:
How to Make a Difference?
• Ensure patients/advocates are “at the table”
and heard when decisions are made about
Big Data projects
• Inform patients/advocates and the public
about potential benefits and concerns
associated with health data
• Be discriminating in providing support to
excellent projects by encouraging patients
and researchers to share data
• Learn more
Take Home Messages
• Big Data has lot’s of potential,
but its more complicated than
we can imagine
– Technical issues
– Political/economic issues
– Patient ethical issues
• Including patients/advocates
from the beginning will lead to
better, faster, and more
acceptable results