Prediction of Post-Spinal Hypotension During Cesarean Delivery Using Machine Learning Algorithms
Prediction of Hypotension Following Spinal Anesthesia During Cesarean Delivery Using Machine Learning Algorithms: A Retrospective Training and Prospective Validation Study
This study aims to develop and prospectively validate machine learning models for predicting hypotension following spinal anesthesia in pregnant women undergoing elective cesarean delivery. The study consists of two cohorts: a retrospective training cohort including at least 200 patients and an independent prospective validation cohort including 50 patients.
Three machine learning algorithms (Random Forest, XGBoost, and Logistic Regression) will be trained using preoperative demographic, anthropometric, and baseline hemodynamic variables, including age, body mass index, parity, gestational age, baseline systolic blood pressure, and baseline heart rate.
The primary outcome is post-spinal hypotension, defined as a decrease in systolic blood pressure of at least 20% from baseline and/or the requirement for vasopressor administration within the first 15 minutes after spinal anesthesia.
The best-performing model will be evaluated in the independent prospective cohort to assess its predictive performance in a real clinical setting.
Study Overview
Status
Status
Conditions
Conditions
Study Type
Study Type
Enrollment (Estimated)
Enrollment
Contacts and Locations
Study Contact
Study Contact
- Name: ilke dolğun
- Phone Number: +905555485632
- Email: ilkeser2004@gmail.com
Study Locations
-
-
Merkez Mahallesi
-
Istanbul, Merkez Mahallesi, Turkey (Türkiye), 34250
- Istinye Üniversity
-
-
Participation Criteria
Eligibility Criteria
Eligibility Criteria
Ages Eligible for Study
Accepts Healthy Volunteers
Genders Eligible for Study
Sampling Method
Study Population
The study population will consist of pregnant women aged 18-45 years with ASA physical status I-II, singleton pregnancies, and scheduled for elective cesarean delivery under spinal anesthesia. The study will include two cohorts: a retrospective training cohort of at least 200 eligible patients identified from hospital records between January 1, 2025, and October 1, 2026, and an independent prospective validation cohort of 50 eligible pregnant women. Participants will be assessed according to predefined inclusion and exclusion criteria. The study population will include women with no history of chronic hypertension or preeclampsia/eclampsia and without contraindications to neuraxial anesthesia.
Description
Inclusion Criteria:
- Age between 18 and 45 years.
- ASA physical status I-II.
- Singleton pregnancy.
- Scheduled for elective cesarean delivery under spinal anesthesia.
Exclusion Criteria:
- Multiple pregnancy.
- Emergency cesarean delivery, including cases of fetal distress.
- Chronic hypertension.
- History of preeclampsia or eclampsia.
- Contraindications to neuraxial anesthesia.
Study Plan
How is the study designed?
Design Details
- Observational Models: COHORT
- Time Perspectives: OTHER
What is the study measuring?
Primary Outcome Measures
Primary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
Predictive Performance of Machine Learning Models for Post-Spinal Hypotension
Time Frame: Within the first 15 minutes following spinal anesthesia.
|
The predictive performance of machine learning models (Random Forest, XGBoost, and Logistic Regression) for identifying post-spinal hypotension will be evaluated using the area under the receiver operating characteristic curve (AUC-ROC). Post-spinal hypotension is defined as a decrease in systolic blood pressure of at least 20% from baseline and/or the requirement for vasopressor administration within the first 15 minutes following spinal anesthesia. Models will be developed using the retrospective training cohort and evaluated in the independent prospective validation cohort. |
Within the first 15 minutes following spinal anesthesia.
|
Collaborators and Investigators
Sponsor
Sponsor
Publications and helpful links
General Publications
- Yang X, Li YM, Wang Q, Li R, Zhang P. Machine learning model based on RCA-PDCA nursing methods and differentiating factors to predict hypotension during cesarean section surgery. Comput Biol Med. 2024 May;174:108395. doi: 10.1016/j.compbiomed.2024.108395. Epub 2024 Apr 2.
- Hung KC, Liu CC, Huang YT, Wu JY, Chen JY, Ko CC, Lin CM, Hsing CH, Yew M, Chen IW. Predictive Efficacy of the Perfusion Index for Hypotension following Spinal Anesthesia in Parturient Undergoing Elective Cesarean Section: A Systematic Review and Meta-Analysis. Diagnostics (Basel). 2023 Aug 3;13(15):2584. doi: 10.3390/diagnostics13152584.
Study record dates
Study Major Dates
Study Start (Estimated)
Study Start
Primary Completion (Estimated)
Primary Completion
Study Completion (Estimated)
Study Completion
Study Registration Dates
First Submitted
First Submitted
First Submitted That Met QC Criteria
First Submitted That Met QC Criteria
First Posted (Actual)
First Posted
Study Record Updates
Last Update Posted (Actual)
Last Update Posted
Last Update Submitted That Met QC Criteria
Last Update Submitted That Met QC Criteria
Last Verified
Last Verified
More Information
Terms related to this study
Other Study ID Numbers
Other Study ID Numbers
- HASEKI-CS-ML-2026
Drug and device information, study documents
Studies a U.S. FDA-regulated drug product
Studies a U.S. FDA-regulated device product
This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.