A Machine Learning Approach to Continuous Vital Sign Data Analysis

This study is enrolling participants by invitation only.
Sponsor:
Information provided by (Responsible Party):
University of Colorado, Denver
ClinicalTrials.gov Identifier:
NCT01448161
First received: October 5, 2011
Last updated: March 8, 2013
Last verified: March 2013
  Purpose

Study hypothesis: Machine Learning algorithms and techniques previously developed for use in the robotics field can be applied to the field of medicine. These state-of-the-art, feature extraction and machine learning techniques can utilize patient vital sign data from bedside monitors to discover hidden relationships within the physiological waveforms and identify physiological trends or concerning conditions that are predictive of various clinical events. These algorithms could potentially provide preemptive alerts to clinicians of a developing patient problem, well before any human could detect a worrisome combination of events or trend in the data.

Specific aims:

  1. Collect physiological waveform and numeric trend data from patient vital signs monitors in ICUs at the University of Colorado Hospital and Children's Hospital Colorado.
  2. Combine the physiological data from patient monitors with clinical data obtained from patient Electronic Medical Records including IV fluids, medications, ventilator settings, urine output, etc. for use in developing models of various clinical conditions.
  3. Apply Machine Learning techniques to these models to identify physiological waveform features and trend information, which are characteristic and predictive of common clinical conditions including but not limited to:

    • Post-operative atrial fibrillation and other cardiac dysrhythmias
    • Post-operative cardiac tamponade
    • Tension pneumothorax
    • Optimal post-operative and post-resuscitation fluid needs
    • Intracranial hypertension and cerebral perfusion pressure

Condition
Vital Signs

Study Type: Observational
Study Design: Observational Model: Case-Only
Time Perspective: Prospective
Official Title: A Machine Learning Approach to Continuous Vital Sign Data Analysis

Further study details as provided by University of Colorado, Denver:

Primary Outcome Measures:
  • Relevant Clinical Features [ Time Frame: 2 years ] [ Designated as safety issue: No ]
    The Primary outcome utilized in this study will be the identification of the most relevant clinical features for detecting a chosen clinical event as determined by the Machine Learning feature-extraction techniques.


Estimated Enrollment: 250
Study Start Date: December 2011
Estimated Study Completion Date: March 2014
Estimated Primary Completion Date: December 2013 (Final data collection date for primary outcome measure)
Groups/Cohorts
Pediatric and Adult ICU patients
Pediatric and Adult ICU patients

  Eligibility

Ages Eligible for Study:   31 Days to 89 Years
Genders Eligible for Study:   Both
Accepts Healthy Volunteers:   No
Sampling Method:   Non-Probability Sample
Study Population

Pediatric and Adult ICU patients

Criteria

Inclusion Criteria:

  1. Age: 31 days - 89 years
  2. Admitted to the surgical intensive care unit (SICU) at the University of Colorado Hospital or to the pediatric intensive care unit (PICU) or children's intensive care unit (CICU) at Children's Hospital Colorado or patients in the Childrens Hospital Colorado (CHC) emergency room with the following conditions

    1. Hemodynamic instability
    2. Febrile >38.5
    3. Respiratory distress
    4. Requiring mechanical ventilation
    5. Requiring central access
    6. Requiring vasoactive medications As well as the time that any of these patients might be in the operating rooms at Children's Hospital Colorado.

Exclusion Criteria:

  1. Pregnant
  2. Incarcerated
  3. Limited access to or compromised monitoring sites for non-invasive finger and forehead sensors
  4. Brain death (GCS 3 with fixed, dilated pupils)
  Contacts and Locations
Please refer to this study by its ClinicalTrials.gov identifier: NCT01448161

Sponsors and Collaborators
University of Colorado, Denver
Investigators
Principal Investigator: Steve Moulton, MD Children's Hospital Colorado
  More Information

No publications provided

Responsible Party: University of Colorado, Denver
ClinicalTrials.gov Identifier: NCT01448161     History of Changes
Other Study ID Numbers: 11-0858
Study First Received: October 5, 2011
Last Updated: March 8, 2013
Health Authority: United States: Institutional Review Board

Keywords provided by University of Colorado, Denver:
Pediatric
Adult
ICU

ClinicalTrials.gov processed this record on April 17, 2014