Prediction of Sepsis in the Emergency Room with Pulse Wave applied Machine Learning

Recruiting

Conditions: spoedeisende hulp
bloedvergifiting
sepsis

Registration Number: NL-OMON51532

Lead Sponsor: Academisch Medisch Centrum

Brief Summary: Not available

Detailed Description: Not available

Recruitment & Eligibility

Status: Recruiting

Sex: Not specified

Target Recruitment: 1500

Inclusion Criteria

- >18 years of age
- Informed consent
- Admitted to the emergency department

Exclusion Criteria

- Patients admitted to the trauma room
- Subjects will be excluded if noninvasive blood pressure cannot be measured
with the finger cuff according to the Instructions for Use of the CS/EV1000
system.

Study & Design

Study Type: Observational non invasive

Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
<p>The primary aim of this study is to predict deterioration in patients admitted<br /><br>to the ED. More specifically, we aim to predict sepsis, septic shock and<br /><br>cardiovascular instability based on the hemodynamic profile of the patient.<br /><br>Therefore, we will collect the continuous noninvasive arterial pressure<br /><br>waveform signals with the ClearSight (CS) finger cuff. In combination with the<br /><br>electronic medical record (EMR) data of the patient, we will develop a machine<br /><br>learning framework for the predictive tasks. </p><br>

Secondary Outcome Measures

Name	Time	Method
<p>The secondary aim of this study is to determine the optimal patient-specific<br /><br>therapeutic pathway and thereby aiming to determine fluid responsiveness of the<br /><br>patient. Furthermore, within the machine learning framework, we will<br /><br>investigate whether hospitalization (ICU or general ward) of ED patients can be<br /><br>predicted.</p><br>