Deep Learning Models for Prediction of Intraoperative Hypotension Using Non-invasive Parameters

General Anesthesia Clinical Trial

Official title:

Prediction of Intraoperative Hypotension Using Non-invasive Monitoring Devices: Development of Deep Learning Model

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT05762237
• Other study ID #: SMC 2022-09-096
• Status: Recruiting
• Start date: April 1, 2023
• Est. completion date: September 30, 2023

Study information

• Verified date: July 2023
• Source: Samsung Medical Center
• Contact: Heejoon Jeong, MD
• Phone: 821087282414
• Email: heejoonjeong[@]skku.edu
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The investigators aimed to investigate the deep learning model to predict intraoperative hypotension using non-invasive monitoring parameters.

Description:

Intraoperative hypotension is associated with various postoperative complications such as acute kidney injury. Therefore, precise prediction and prompt treatment of intraoperative hypotension are important. However, it is difficult to accurately predict intraoperative hypotension based on the anesthesiologists' experience and intuition. Recently, deep learning algorithms using invasive arterial pressure monitoring showed the good predictive ability of intraoperative hypotension. It can help the clinician's decisions. However, most patients undergoing general surgery are monitored by non-invasive parameters. Therefore, the investigators investigate the prediction model for intraoperative hypotension using non-invasive monitoring.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 5064
• Est. completion date: September 30, 2023
• Est. primary completion date: August 31, 2023
• Accepts healthy volunteers: No
• Gender: All
• Age group: N/A and older

Eligibility

Inclusion Criteria:

• The patients who are included in the open database, VtialDB.

• The patients who underwent inhaled general anesthesia for non-cardiac surgery.

• The patients who have non-invasive monitoring data including blood pressure, electrocardiography, pulse oximetry, bispectral index, and capnography.

Exclusion Criteria:

• The patient with missing data.

Related Conditions & MeSH terms

• General Anesthesia
• Hypotension
• Intraoperative Hypotension

Locations

Country	Name	City	State
Korea, Republic of	Samsung Medical Center	Seoul

Sponsors (1)

Lead Sponsor	Collaborator
Samsung Medical Center

Country where clinical trial is conducted

Korea, Republic of, 

References & Publications (2)

Lee HC, Jung CW. Vital Recorder-a free research tool for automatic recording of high-resolution time-synchronised physiological data from multiple anaesthesia devices. Sci Rep. 2018 Jan 24;8(1):1527. doi: 10.1038/s41598-018-20062-4. — View Citation

Lee S, Lee HC, Chu YS, Song SW, Ahn GJ, Lee H, Yang S, Koh SB. Deep learning models for the prediction of intraoperative hypotension. Br J Anaesth. 2021 Apr;126(4):808-817. doi: 10.1016/j.bja.2020.12.035. Epub 2021 Feb 6. — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Deep learning model's prediction ability on intraoperative hypotension event	Area under the curve the receiver operating characteristic (AUROC) curve for the deep learning model to predict intraoperative hypotension.	through study completion, an average of 3 hour