Related Experiment Video
Updated: May 20, 2026
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
A clinical deterioration prediction tool for internal medicine patients
Lisa L Kirkland1, Michael Malinchoc, Megan O'Byrne
1Mayo Clinic Rochester, 200 First Street SW, Rochester, MN 55905, USA. Kirkland.lisa@mayo.edu
Summary
A new clinical deterioration prediction tool uses Braden Scale, respiratory rate, oxygen saturation, and shock index to forecast patient decline. This early warning system aids hospitalized medical patients by identifying risks hours in advance.
Area of Science:
- Medical Informatics
- Clinical Prediction Models
- Patient Monitoring
Background:
- Early warning systems for hospitalized patients often lack rigorous derivation and validation.
- Existing models frequently rely on admission data, limiting their predictive power for ongoing deterioration.
Purpose of the Study:
- To develop and validate a clinical deterioration prediction tool using routinely collected patient data.
- To identify key clinical and nursing measurements predictive of future patient decline.
Main Methods:
- Multivariate regression analysis was employed to identify variables associated with clinical deterioration.
- The derived prediction model was retrospectively validated on a separate cohort of medical inpatients.
Main Results:
- The Braden Scale, respiratory rate, oxygen saturation, and shock index were statistically significant predictors of clinical deterioration within 2-12 hours.
- The developed tool showed fair concordance with actual patient outcomes in the validation cohort.
Conclusions:
- A novel early warning system for hospitalized medical patients was created using readily available clinical measurements.
- This tool demonstrates potential for timely identification of patients at risk of clinical deterioration.
