Machine Learning for Risk Stratification in the Emergency Department: A Pilot Clinical Trial
Recruiting
- Conditions
- Acute aandoeningen bij patiënten op de SEHn.v.t.
- Registration Number
- NL-OMON54014
- Lead Sponsor
- Medisch Universitair Ziekenhuis Maastricht
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Recruiting
- Sex
- Not specified
- Target Recruitment
- 1300
Inclusion Criteria
- Adult, defined as >= 18 years of age
- Assessed and treated by an internal medicine specialist in the ED
- Willing to give written consent, either directly or after deferred consent
procedure
Exclusion Criteria
- <4 different laboratory results available (hematology or clinical chemistry)
within the first two hours of the ED visit (calculation ML prediction score
otherwise not possible)
- Unwilling to provide written consent, either directly or after deferred
consent procedure
Study & Design
- Study Type
- Interventional
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method <p>- Calculated ML risk scores and observed mortality, to evaluate discriminatory<br /><br>performance of ML risk score to predict 31-day mortality.<br /><br>- Physicians self-reported policy changes to evaluate whether presentation of<br /><br>the ML risk score causes changes in clinical decision making. Policy changes<br /><br>include treatment policy, requesting ancillary investigations, treatment<br /><br>restrictions (i.e., no intubation or resuscitation).</p><br>
- Secondary Outcome Measures
Name Time Method <p>- Clinical endpoints such as 31-day mortality, ICU and MC admission and<br /><br>readmission will be compared between the control an intervention group to<br /><br>evaluate differences.<br /><br>- Diagnostic performance of other clinical risk scores and physicians will be<br /><br>compared to the ML score.</p><br>