Machine Learning-Based Model for Individualized Drug Dose Prediction for Propofol

NCT06703879 | Completed

• 1 other identifier: Huiwen Zhang-2024-11
• Study Type: observational
• Target: 1,200
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this observational study is to develop an individualized prediction model for drug dosage during propofol-induced loss of consciousness in anticipation of advances in research in this area. An appropriate delivery model to reduce perianesthesia complications in patients, especially in outpatient painless endoscopy patients. The main question it aims to answer is: What type of machine learning algorithm should be used to build a drug dose prediction model that is suitable for patient awareness of anesthesia induction? 1000 participants routinely with propofol induced anesthesia loss of consciousness included in this study.

Conditions

Anesthesiology; Anesthesiology Management

Keywords

machine learning; propofol-induced loss of consciousness in patients; predict model

Outcome Measures

Primary Outcomes (1)

• Drug dosage of propofol for inducing loss of consciousness in patients

  Propofol was pumped at 100 mg/kg/h. The anesthesiologist assessed the patient's sedation level with the MOAA/S scale until the patient was deeply sedated and the MOAA/S score was less than or equal to 1, and pumping of propofol was stopped. Propofol Continuous Pumping Volume Recorded(mg). Record propofol pumping duration.

  through study completion, an average of six months

Secondary Outcomes (3)

• Relevant factors that can influence the intravenous dose of propofol

  through study completion, an average of six months

• Patient's peri-anesthetic vital signs

  through study completion, an average of six months

• Characteristics of the patient's perianesthesia electroencephalogram

  through study completion, an average of six months

Interventions

Anesthesia induction with propofol DRUG

Establishment of a database of clinical characteristics of propofol-induced loss of consciousness in patients with complete clinical information Acquisition of basic perioperative monitoring data and extended monitoring data: 1,000 patients aged ≥18 years who needed to undergo surgical treatment were included (according to the machine learning diagnosis results, if the poor model fit was due to the small sample size, the necessary number of samples could be continued to be collected), and perioperative monitoring and management of the patients was performed, and a video recorder was used to videotape the whole anesthesia induction process in real time, so as to facilitate the postoperative integration of various data. The basic characteristics of the patients and the perioperative monitoring characteristics were extracted from the surgical anesthesia recording system, including gender, age, height, weight, blood pressure, ASA classification, electroencephalographic parameters, the a

Also known as: Induction of anesthesia by intravenous infusion of propofol

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Inpatients requiring elective surgery or outpatient painless endoscopic surgery； Induction of anesthesia with propofol

You may qualify if:

• Inpatients requiring elective surgery or outpatient painless endoscopic surgery； Induction of anesthesia with propofol； Age≥18 years old； ASA classifications I-III

You may not qualify if:

• Propofol allergy； Contraindication to anesthesia; Declined to participate in the study

Sponsors & Collaborators

• General Hospital of Ningxia Medical University: lead

Study Sites (1)

General Hospital of Ningxia Medical University

Yinchuan, Ningxia, 750004, China

Location

MeSH Terms

Interventions

Propofol

Intervention Hierarchy (Ancestors)

Phenols; Benzene Derivatives; Hydrocarbons, Aromatic; Hydrocarbons, Cyclic; Hydrocarbons; Organic Chemicals

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: November 18, 2024
• First Posted: November 25, 2024
• Study Start: November 20, 2024
• Primary Completion: March 30, 2025
• Study Completion: July 30, 2025
• Last Updated: August 19, 2025

Record last verified: 2024-11

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)