Ethical, Legal, and Social Implications of ELSI Learning Health Systems 2017 Conference, University of Michigan. Learning from the experience and outcomes of every cancer patient
1. Lessons Learned in Scaling up –
Implications for LHSs
Warren A. Kibbe, Ph.D.
Professor, Biostats & Bioinformatics
Chief Data Officer, Duke Cancer Institute
warren.kibbe@duke.edu
@wakibbe
2. Take homes
• Data should be liquid
• Data sharing needs to scale
• Consent is a process
• Precision Medicine means many
common diseases will be a collection
of rare diseases
We need to learn from every patient
3. (10,000+ patient tumors and increasing)
Courtesy of P. Kuhn (USC)
2006-2015:
A Decade of Illuminating the
Underlying Causes of Primary
Untreated Tumors Omics
Characterization
Cancer is a grand challenge
• Deep biological understanding
• Advances in scientific methods
• Advances in instrumentation
• Advances in technology
• Data and computation
• Mathematical models
Cancer Research and Care generate
detailed data that is critical to
create a learning health system for cancer
Requires:
5. Health vs Disease
• What is ’normal’?
• Systematic and measurement error
• Biological heterogeneity
• Population Health
6. Team Science is critical
Clinical Trials
Biostatists
Bioinformatics
Clinical Care
Clinical Research
EHRs, Imaging, Lab Systems
Data Science
Analytics and Visualization
Open Data enhances collaboration and team science!
8. How do we solve problems in Cancer
• Support and incentives for team science,
collaboration
• We need FAIR, open data
• Support open source, open science
• Support for rapid innovation
10. Data Liquidity
• Data that is electronic ‘at birth’ is
ideal. Lab data, sensor data, modern
imaging
• Manual annotation reduces liquidity,
stops scaling, automation
• Manual processes are an investment
– one to carefully make
Asking pathologists, nurses, clinicians, care team members to
denote outcomes already present in labs, images, automated or
automatable feeds introduces costs, errors, and impedes scaling
11. Machine Learning
• Large data sets, particularly
population-based with a well-
annotated comparator set, are ideal
• Machine Learning and Deep Learning
on image features is feasible,
accurate, reproducible and scalable
14. Biology and Medicine are now
data intensive enterprises
Scale is rapidly changing
Technology, data, computing and
IT are pervasive in the lab, the
clinic, in the home, and across the
population
Data liquidity in healthcare is key
+ve –ve protein expression levels, ALK- Anaplastic lymphoma kinase, Squamous is a cell type (epidermoid),
We now have tools to let us both understand social determinants of health and build ‘early warning systems’ to identify people who are have acute medical issues
The scale of genomics, population science and data science is dramatically changing!
But people can make effective decisions on the same number of factors…
How can we use machine learning and other techniques to reduce cognitive overload?