Early Prediction of ICU Hypotension Using Machine Learning
ConditionHypotension
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorKutahya Health Sciences University
About this trial
This prospective observational study aims to develop and internally validate a machine learning model for the early prediction of hypotension in adult intensive care unit patients. The model will use routinely collected non-invasive vital signs, heart rate, medication-dose records, and fluid-balance data recorded during standard ICU care. No intervention will be assigned by the study, and patient management will not be changed according to the model output. The primary aim is to predict hypotension 30 minutes before its occurrence; shorter 5- and 15-minute prediction horizons will also be evaluated.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 18 years or older
Admission to the adult intensive care unit during the study period
Length of stay in the intensive care unit of at least 24 hours
Availability of routine intensive care unit monitoring data
Disqualifiers
Age younger than 18 years
Length of stay in the intensive care unit of less than 24 hours
Absence of usable blood pressure monitoring data
Records with irrecoverable timestamp inconsistencies
Trial population
The study population will consist of consecutive adult patients monitored in the adult intensive care unit of Kutahya Health Sciences University during the study period. Routine clinical monitoring data, including non-invasive blood pressure, heart rate, medication-dose records, and fluid-balance data, will be used for machine learning model development and internal validation. No treatment or intervention will be assigned by the study protocol.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Routine ICU Data Collection
Other interventionRoutinely collected intensive care unit data, including non-invasive blood pressure, heart rate, medication-dose records, and fluid-balance data, will be recorded and analyzed for development and internal validation of a machine learning model. The study does not assign any treatment, medication, device, alarm, or clinical decision.
Treatment groups
100 Participants
are divided into 1 treatment groupGroup A: Adult Intensive Care Unit Patients1 intervention
Trial outcomes
Primary outcomes
1
Area Under the Receiver Operating Characteristic Curve for 30-Minute Hypotension Prediction
Discriminative performance of the machine learning model for predicting hypotension 30 minutes before its occurrence. Hypotension will be defined as systolic blood pressure below 90 mmHg, mean arterial pressure below 65 mmHg, or diastolic blood pressure below 60 mmHg at a five-minute observation point.
Time frame
From enrollment through the end of ICU monitoring, up to 4 monthsSecondary outcomes
1
Area Under the Receiver Operating Characteristic Curve for 5- and 15-Minute Hypotension Prediction
Discriminative performance of separate machine learning models for predicting hypotension at 5-minute and 15-minute prediction horizons.
Time frame
From enrollment through the end of ICU monitoring, up to 4 months2
Classification Performance of the Hypotension Prediction Model
Classification performance of the machine learning model will be assessed using sensitivity, specificity, positive predictive value, negative predictive value, and F1 score at predefined classification thresholds.
Time frame
From enrollment through the end of ICU monitoring, up to 4 monthsSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov