Skip to main content

Using Machine Learning to Improve the Accuracy of Patient Deterioration Predictions: Mayo Clinic Early Warning Score (MC-EWS)

This on-demand webinar does not offer CE credit.

Romero-Brufau S, Whitford D, Johnson MG, et al. Using machine learning to improve the accuracy of patient deterioration predictions: Mayo Clinic Early Warning Score (MC-EWS) [published online ahead of print, 2021 Feb 26]. J Am Med Inform Assoc. 2021;ocaa347. doi:10.1093/jamia/ocaa347

Read the article

Watch the Recording


Santiago Romero-Brufau, MD, PhD
Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA
Department of Medicine, Mayo Clinic, Rochester, MN

Santiago Romero-Brufau, MD, PhD, is an Assistant Professor of Medicine and Healthcare Systems Engineering at Mayo Clinic, where he also serves as Principal Data Scientist for the Department of Medicine. His work focuses on the development and implementation of machine-learning models into clinical practice. He is also instructor in the Department of Biostatistics and in Health Data Science at the Harvard T.H. Chan School of Public Health.


Hannah Burkhardt
PhD candidate
University of Washington School of Medicine
Biomedical Informatics and Medical Education


Yuqi Si
PhD Candidate
The University of Texas Health Science Center at Houston (UTHealth)

Statement of Purpose

Physiological deterioration in the hospital is often unrecognized and can lead to increased patient mortality. To improve the identification and response to acute deterioration, more than 70 early warning scores have been developed. Some recent models have used machine learning to increase prediction accuracy for adult acute inpatient deterioration, but the value of nursing assessments and the incorporation of interaction variables has not been sufficiently explored. MC-EWS uses a machine learning approach and incorporates nursing assessments and clinically relevant interactions as predictors to achieve a higher predictive accuracy.

Target Audience

The target audience for this activity is professionals and students interested in health informatics.

Learning Objectives

The general learning objective for all of the JAMIA Journal Club webinars is that participants will

  • Use a critical appraisal process to assess article validity and to gauge article findings' relevance to practice

After participating in this webinar, the listener should be able to:

  • Measure the accuracy of predictive models using clinically-relevant metrics
  • Incorporate clinically-relevant interaction variables into machine learning prediction models
  • Recognize the predictive value of nursing assessments for the prediction of inpatient deterioration

Commercial Support

No commercial support was received for this activity.

Disclosures for this Activity

Santiago Romero-Brufau discloses that he receives an IP License Royalty from Jvion, Inc. 

The following presenters, planners, and staff who are in a position to control the content of this activity disclose that they and their life partners have no relevant financial relationships with commercial interests:

JAMIA Journal Club planners: Hannah Burkhardt, Kirk E. Roberts, Yuqi Si
AMIA Staff: Susanne Arnold, Pesha Rubinstein


Dates and Times: -
Type: Webinar
Course Format(s): On Demand