Prediction of complications after major gastrointestinal surgery with machine learning and point of care ultrasound: an observational cohort study.
Recruiting
- Conditions
- perioperatieve complicaties en vochthuishouding/hypotensieperioperative complications and fluid tolerance.
- Registration Number
- NL-OMON53240
- Lead Sponsor
- Amsterdam UMC
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Recruiting
- Sex
- Not specified
- Target Recruitment
- 200
Inclusion Criteria
>=18 years of age.
elective major gastrointestinal surgery: esophagectomy, gastrectomy,
pancreactomy or major liver resection (3 segments or more).
Exclusion Criteria
- no informed consent
- Patients with major cardiac shunts
- Patients with dialysis shunts or peritoneal dialysis
- Patients in whom POCUS is not possible or assessment of fluid status is
unreliable e.g. BMI> 40, pulmonary fibrosis.
Study & Design
- Study Type
- Observational invasive
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method <p>The main study endpoint is a machine learning framework based on the<br /><br>hemodynamic profile to predict major complications, especially<br /><br>cardiovascular/pulmonary instability, including, sepsis and septic shock. Data<br /><br>from the ClearSight will be used to collect non-invasive arterial pressure<br /><br>waveforms. point of care ultrasound of heart, lungs and abdominal veins, and<br /><br>clinical data from the electronic medical record will be collected</p><br>
- Secondary Outcome Measures
Name Time Method <p>point of care ultrasound of heart, lungs and abdominal veins, and clinical<br /><br>data from the electronic medical record will be collected. In a subgroup of 40<br /><br>patients RAAS levels and portal blood samples will be analysed. </p><br>