News

The Gabriella Miller Kids First Data Resource Center has officially launched its Data Resource Portal, a powerful, open-source resource for research in pediatric disorders. The portal brings together clinical and genomic data related to childhood diseases, including pediatric cancer and birth defects, and enables researchers to collaborate with one another and analyze data in a secure, cloud-based environment.

The CRI is committed to several efforts to use cross-institutional data sharing to study and combat diseases, especially rare diseases such as pediatric cancer. We are proud to be part of the development of this important resource, with our Sr. Programmer Luca Graglia, MS, fully dedicated to the project. Read more about the Kids First DRC and our role here.

The CRI Seminar Series 2018-19 season kicks off this Friday with a talk from Sam Volchenboum, “Including Informatics in Grant Applications.” The full schedule for this academic year includes twelve sessions, in topics ranging from parallel computing to natural language processing to REDCap. In October, we will welcome guest speakers from the Human Imaging Research Office; the other sessions will be presented by experts in each field from the CRI.

Creating opportunities for informatics education is an important part of our mission. CRI Seminar Series talks are free and open to all members of the University of Chicago community and partner institutions. Check out the full schedule here.

REDCapCon, the annual education and networking conference for REDCap administrators, will be held this year from August 19-22 at the Palmer House Hilton in Chicago. The CRI is honored to be hosting this year’s event, with our REDCap Administrator Julissa Acevedo playing an important role in bringing the conference to UChicago. 

Now in its tenth year, the conference is designed to help REDCap administrators and technical team members support the effective use of REDCap at their home institutions. The three days of programming include presentations, breakout sessions, and networking. In addition to educational opportunities, the conference works to foster collaborative relationships between member institutions, ultimately contributing to the ongoing improvement of the REDCap software.

Learn more how you can use REDCap with the CRI here.

The CRI is pleased to announce a new collaborative project with Elligo Health Research in which both teams will assist the US Food and Drug Administration (FDA) with developing a standard common data model to guide evidence generation in biomedical research studiesand bridge clinical research and clinical care. As part of a grant awarded by the Patient Centered Outcomes Research (PCOR) Trust Fund, the FDA is currently involved in an effort to harmonize multiple common data models and open standards. By mapping data from disparate sources to one consensus-based model, the project will facilitate interoperability between data networks and make new research possible.

The CRI’s rich Clinical Research Data Warehouse and experience in the development and maintenance of data models make us a natural partner for Elligo and the FDA in developing and implementing interoperability standards. In addition to providing the FDA with valuable information about the safety of new cancer treatments, this project will help assess the value of the standard common data model for real world evidence research, as well as the tools and methods used to achieve the data harmonization. Learn more about what we’ll be working on here.

As the CRI-supported collaboration between the University of Chicago and Google continues, the successes of this machine learning project are capturing attention.

In Bloomberg News, CRI Director Sam Volchenboum and other experts weigh in on the meaning of the project’s accomplishments so far, potential pitfalls, and what they hope to see next. For Sam, health records are one piece of the puzzle, but they could be made even more meaningful if analyzed in combination with other types of data that influence health outcomes.

Read more: Google Is Training Machines to Predict When a Patient Will Die

This week’s issue of the New York Times Magazine features the article “Trying to Put a Value on the Doctor-Patient Relationship,” which profiles Dr. David Meltzer’s unique Comprehensive Care Program (CCP) study. The CCP is an experiment in returning to a now-uncommon model for the doctor-patient relationship, in which patients receive consistent care from one provider whether they are outpatient or in the hospital.

The CRI has proudly been a part of the CCP study since it began; our Applications Development team built the custom dashboard and notification system that comprise the technological infrastructure for the study. The dashboard is used in the clinic to collect study information and integrate it with patients’ electronic medical records, and the notification system, which was the first of its kind at UCM, alerts physicians when patients enrolled in the study visit the emergency department or are admitted to the hospital.

With the recent publication of the first paper to come out of the University of Chicago’s collaboration with Google, our director Sam Volchenboum sat down with The Forefront for a Q&A about the project. Read the interview to learn more about how the researchers leveraged EHR data from the CRDW for the development of new predictive algorithms for heathcare, how patient privacy is protected throughout the process, and where Sam thinks the future of EHR data mining could take us.

Getting More from Electronic Health Records

Machine learning algorithms are getting better and better at predicting and diagnosing disease — even though sometimes, researchers can’t fully explain why. In a recent paper supported by CRI effort and CRDW data, researchers from the University of Chicago, Stanford University, the University of California, San Francisco, and Google determined that these algorithms could use patterns in patient data to predict diseases and the likelihood of certain medical outcomes with extraordinary accuracy.

In the Harvard Business Review, CRI Director Sam Volchenboum and Immuta Chief Privacy Officer and Legal Engineer Andrew Burt write, “This future is alarming, no doubt, due to the power that doctors and patients will start handing off to machines. But it’s also a future that we must prepare for — and embrace — because of the impact these new methods will have and the lives we can potentially save.” 

Read More

In a paper published in the May 4, 2018 issue of Nature Communications, University of Chicago researchers confirmed the existence of a curable intermediate state of cancer called oligometastasis. Samuel Hellman, MD, Ralph Weichselbaum, MD, and their co-authors were able to use molecular analysis to reliably predict which patients with colorectal cancer could benefit from surgery. Their findings should improve the treatment of patients with colorectal metastases that have spread to the liver, and could potentially be applicable to many types of cancer.

The CRI contributed bioinformatics analysis to the study, with our Senior Bioinformatician Lei Huang, PhD, and Director of Bioinformatics and Research Assistant Professor Jorge Andrade, PhD, named as co-authors.

Read more: Study confirms curable state between single and widespread cancers