Realizing the power of data science to advance cancer research and cancer care
Like hundreds of thousands of starlings aloft in the sky flying together to create a mass that swoops and dips in unison until the swarm of birds roosts, so too can our data be harmonized and aggregated together to converge on the cancer problem and envelop it to unlock solutions.
MD Anderson’sInstitute for Data Science in Oncology (IDSO) will harness the power of data and bring data science to every decision we make. This will accelerate the pace of our mission to end cancer and improve the lives of cancer patients and their families.
“IDSO is designed to bend the knee of data science for MD Anderson’s mission to end cancer,” says David Jaffray, Ph.D., inaugural director for IDSO, and chief technology and digital officer and senior vice president for MD Anderson.
The institute is dedicated to enabling the full power of data science. By achieving meaningful integration of diverse data, IDSO seeks to not only derive new insights but to use them through advanced, data-driven approaches and decision-making. Ultimately, this will advance drug discovery efforts and bring new, precise medicines to patients sooner, improving scheduling and access to care, enhancing safety and quality of care, and reducing the time between diagnostic procedures and treatment decisions.
Creating a metadata supply chain through stewardship and shared understanding
On average, 175,000 patients are seen and more than 400 types of cancer are treated each year at MD Anderson, with each patient’s care experience generating more than 2 GB of data annually. The sheer volume of data often causes data scientists and researchers to spend an excessive amount of time and energy on finding, assembling and curating data to assure the data extracted are robust and can be applied appropriately.
“We need to use next-generation computational technologies and approaches to aid what our minds alone can’t realize to reach potentials unknown,” says Jaffray. “The urgency to address the cancer problem is too great to continue with our traditional approaches.”
MD Anderson is investing heavily in the process of governing our data and creating a “metadata supply chain” that will bring together data of unprecedented quality and with known provenance or lineage. This also includes comprehensive data governance that allows the promise of artificial intelligence (AI) technology to be realized to its full potential in clinical practice.
“This is a collective effort to maximize the availability of data with appropriate curation for learning through the next generation of data science methods. It’s aligned under our core value of Stewardship with our substantial research, clinical and operational teams, our emerging data management system and our digital architecture teams collaborating closely,” says Caroline Chung, M.D., inaugural chief data officer and vice president for Data Impact and Governance. Chung is responsible for shaping MD Anderson’s data strategy and leading its implementation from an operational and cultural perspective, as well as through her role as director of Data Science Development and Implementation for IDSO.
Teaming, recruiting and collaborating to advance data science
As part of Our Strategy, MD Anderson is advancing our substantial clinical and research enterprise as the nation’s largest and most impactful cancer care and research institution that generates unique cancer-specific data at an ever-increasing rate.
“Supported by our institutional commitment and investment in team data science, we are building and enhancing an unprecedented oncological data ecosystem to enable effective and impactful data collaborations with other world-leading organizations and data scientists from across many fields to bring novel perspectives to accelerate research and treatment innovation,” says Chung. “It will transition our approach from precision to predictive oncology.”
Currently, the standard of care is to follow a patient’s treatment protocol until imaging shows that a tumor has progressed and then adjust treatment. Through IDSO, the aim is to use a combination of biomarkers, such as tumor measurement and circulating tumor cells, to proactively anticipate if a patient won’t respond well to a treatment course. Using data-driven predictive approaches will improve our patients’ outcomes. IDSO further establishes MD Anderson as the leader in data science for cancer care, discovery and operations. It will provide programs to create the next, and – in many cases – the first, generation of data science being applied to the challenge of ending cancer.
Our data science community is seeking expertise in impact-driven data science from within and outside health care to accelerate our engagement with industry to bring new approaches to important everyday problems facing our patients and their families.
“IDSO will help us make a real, tangible impact on our patients’ experiences, turning innovation into clinical practices and treatments,” says Jaffray. “MD Anderson alone can’t do this. We need to augment our exceptional data science talent by tapping into industries within and beyond health care to attract others to join us and leverage their expertise.”
“MD Anderson’s wealth of data and investment to ever improve the quality and granularity of the data, collaborative and inclusive environment, and dedication to a bold mission makes it the ideal place to build capacity for utilizing and implementing data science to dramatically accelerate progress against cancer,” says Chung. “IDSO is the vehicle to bridge data scientists with cancer researchers, clinical teams and patients to make an impact for humanity.”