MCURES
Overview
Michigan COVID-19 Utilization and Risk Evaluation System, or M-CURES, is an open-source patient deterioration model that was developed by DHI Co-Director Jenna Wiens and Mike Sjoding, including fellow Co-Director Brahmajee Nallamothu , IHPI Director John Ayanian, and Tom Valley, was implemented to improve care at the University of Michigan’s health system. In addition to the model’s effectiveness, the way it was made points the way to the dramatically faster development of future models, working around the challenges of sharing sensitive patient data. Patient deterioration models help doctors and nurses make better decisions about care by proactively transferring the highest risk patients to the ICU before they deteriorate. They can also help providers identify patients who may benefit from earlier hospital discharge or transfer to a lower-intensity care setting.
“We were able to develop the M-CURES model in a fraction of the time it took to build past models through close collaboration between clinicians and data scientists and by enabling other health systems to validate the model without sharing any of their patient data,” said DHI Co-Director Jenna Wiens, an associate professor of electrical engineering and computer science at U-M, College of Engineering.
Development of the M-CURES model, she says, began in early 2020, at the onset of the COVID-19 pandemic. The U-M health system, Michigan Medicine, needed a better way to predict the outcomes of COVID-19 patients. The team worked closely with Michigan Medicine clinicians to shorten the typically months-long process of boiling down thousands of data points into a handful of key predictive indicators. They developed a hybrid approach where data scientists and clinicians worked together to weed out potentially misleading variables. That enabled them to validate the effectiveness of M-CURES at Michigan Medicine in just weeks.
To speed up the crucial step of validating their model at other health systems, Wiens’ team pioneered an approach to avoid the months-long process of getting access to sensitive patient data. Instead, they simply sent their newly developed code to teams at other hospitals, which applied the model in-house and reported back the results. The team validated the M-CURES model at a dozen hospitals around the United States with different structures and demographics, helping to ensure the algorithm is accurate and equitable.
“Rapid response teams are specialized clinical teams that can act quickly to intervene on patients before they experience bad outcomes,” said Michael Sjoding, associate professor in pulmonary and critical care medicine at Michigan Medicine and clinical lead of the M-CURES development. “We are excited that the M-CURES model will support this effort.” Perhaps the most significant outcome of the project is the ability to use the tactics developed for the M-CURES model to develop predictive models for emerging health threats more quickly in the future.
The collaboration also included researchers at Mass General Brigham, University of Texas Southwestern, and University of California San Francisco.
The work was supported by the National Science Foundation; National Institutes of Health; National Library of Medicine; National Heart, Lung, and Blood Institute; Agency for Healthcare Research and Quality; Centers for Disease Control and Prevention; National Center for Emerging and Zoonotic Infectious Diseases; Digital Health Innovation at U-M; and Institute for Healthcare Policy and Innovation at U-M.
Read More:
“Early Identification of Hospitalized Patients with COVID-19 at Risk of Clinical Deterioration: Model Development and Multi-Site External Validation Study.” (DOI: 10.1136/bmj-2021-068576)
Principal Investigator(s)
Jenna Wiens, PhD
Michael W. Sjoding, M.D.
Thomas S. Valley, M.D.
Digital Health Innovation Support
Digital Health Innovation provided EHR data to develop the model. This model runs on a Digital Innovation supported pipeline, Near-Real Time RDW. Retrospective and prospective validation of the model was supported using this pipeline. With newly developed IT infrastructures, the model generates a CDI risk score on a daily basis at MM. The generated score helps clinicians identify which patients should receive interventions, and what interventions should be applied. The Model Deployment team also engaged with the Health Information Technology and Services (HITS) to integrate survey questions in MiChart during the order entry process for a C. difficile order. This integration enabled the researchers to assess reasoning behind provider suspicion of CDI and to use this qualitative data to improve the predictive algorithm.
Partnerships
College of Engineering
Clinical Intelligence Committee (CIC)
Health Information Technology and Services (HITS)
Office of Clinical Informatics (OCI)
Learning Health Sciences (LHS)
Publications
Oh et al 2018: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6421072/
Li et al 2019: https://pubmed.ncbi.nlm.nih.gov/31139672/
Otles et al 2021: https://static1.squarespace.com/static/59d5ac1780bd5ef9c396eda6/t/60fb3ba110343004004f24ba/1627077538209/Performance_Gap___Prospective_Validation.pdf